← PicsartCONTENT HISTORY

Update to Picsart

Snapshot Nov 7, 2026 · 00:09 UTC · version 2.4.0

Collection source: downloaded plugin package.

WHAT CHANGED

Instructions updated for reel-structure

Full description — Now says: Read a reference reel's structure and format, never its content - its beats, shots, caption pattern, pace and bed into a structure sheet (or parse a written...

Observed in instructions or declared skills. Runtime behavior has not been tested.

Save Picsart and check future changes in Following.

Up to 3 plugins free · no card required.

All fields and original values.

Full description

Before

Nov 3, 2026 · 18:14 UTC

Copy a reference reel's structure, never its content - read its beats, shots, caption pattern, pace and sound bed into a structure sheet (or parse a written beat-by-beat breakdown for free), fit the user's own script to those beats, and ...

After

Nov 7, 2026 · 00:09 UTC

Read a reference reel's structure and format, never its content - its beats, shots, caption pattern, pace and bed into a structure sheet (or parse a written breakdown for free), its layout, captions, hook and end card into the record's f...

Skill instructions

Before

Nov 3, 2026 · 18:14 UTC

Copy a reference reel's structure, never its content - read its beats, shots, caption pattern, pace and sound bed into a structure sheet (or parse a written beat-by-beat breakdown for free), fit the user's own script to those beats, and ...

After

Nov 7, 2026 · 00:09 UTC

Read a reference reel's structure and format, never its content - its beats, shots, caption pattern, pace and bed into a structure sheet (or parse a written breakdown for free), its layout, captions, hook and end card into the record's f...

Supporting files

Before

Nov 3, 2026 · 18:14 UTC

[{"relative_path":"scripts/map_structure.py","size_in_bytes":13347},{"relative_path":"scripts/reuse_guard.py","size_in_bytes":7118},{"relative_path":"scripts/sheet.py","size_in_bytes":34804},{"relative_path":"scripts/structure_report.py"...

After

Nov 7, 2026 · 00:09 UTC

[{"relative_path":"references/format.md","size_in_bytes":5615},{"relative_path":"scripts/map_structure.py","size_in_bytes":15055},{"relative_path":"scripts/ref_format.py","size_in_bytes":19619},{"relative_path":"scripts/reuse_guard.py","...

Compare saved observations

Download comparison JSON

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -1,6 +1,6 @@
 ---
 name: reel-structure
-description: Copy a reference reel's structure, never its content - read its beats, shots, caption pattern, pace and sound bed into a structure sheet (or parse a written beat-by-beat breakdown for free), fit the user's own script to those beats, and report each beat as matched, changed, dropped or added, with the content rules checked. Use when a short should be built the way a reference reel is built, or when a script must be checked against a reference's beats.
+description: Read a reference reel's structure and format, never its content - its beats, shots, caption pattern, pace and bed into a structure sheet (or parse a written breakdown for free), its layout, captions, hook and end card into the record's format, with what the footage can match; fit the user's script to the beats, and report each beat as matched, changed, dropped or added, with the content rules checked. Use when a short should be built the way a reference reel is built or looks, including the user's own channel.
 metadata:
   source: channel team breakdowns and tools/reuse_guard.py, commit 3f064f0
 ---
@@ -12,8 +12,13 @@
 viewer can see or hear of the reference reaches the user's video: no words, no frames, no audio
 or music. Only its pattern is copied.
 
-The method has four steps: read the structure into a sheet, check the sheet with the user, map
-the user's script onto it, and report what matched and what changed.
+The method has five steps: read the structure into a sheet, check the sheet with the user, read
+the format and what the footage can match of it, map the user's script onto the beats, and report
+what matched and what changed. A job with no script (cutting footage to a reference) stops after
+the format.
+
+**The user's own channel is different**: its format is the spec to reproduce, and its logo, end
+card, fonts and copy are theirs (own-brand mode, `references/format.md`).
 
 ## 1. Read the structure
 
@@ -38,7 +43,7 @@
 | `picsart_media_analyze_audio` | the bed: tempo and loudness |
 | `picsart_media_video_stills` | one still per beat, **for the user to look at only**, never an input to a generation |
 
-Save each result as it came back, then draft the sheet from them. No video is decoded here:
+Keep each result as it came back (as files, where you run commands), then draft the sheet from them. No video is decoded here:
 
 ```
 python3 scripts/sheet.py draft --shots shots.json --transcript transcript.json \
@@ -72,7 +77,11 @@
 - **`?` is unknown**, never a value and never an error: a `?` time, a `?` cell, or `?` with a
   note. Never guess one. The map step needs every beat timed and named, and says which are not.
 - A header above the table, as `- Key: value` lines: Format (talking head, POV skit, screen
-  tutorial, list, reaction), Length, Cut rate, Caption style, Bed, Loudness and Source. Length,
+  tutorial, list, reaction), Length, Cut rate, Caption style, Layout, Bed, Loudness and Source.
+  **Layout** names the mode and who sits where: `split-v (top host, bottom guest)`.
+- Two more columns after Sound when the reference has a format to keep: **Frame** (the beat's
+  layout, or who fills it: `split-v`, `full: guest`) and **Caption position** (`seam`, `top`,
+  `centre`, `lower third`). Length,
   cut rate and loudness keep their number and the line as written (`- Cut rate: ~19 cuts/min
   (21 picture changes…)`). A file with several sheets parses with `parse --all`.
 
@@ -89,7 +98,25 @@
 Show the user the sheet with the stills, and fix what they correct. Then ASK (with the host's own choice tool where it offers one, such as request_user_input in Codex's Plan mode, so the user taps an option; a Picsart board the step names asks there instead; only where neither works, the options numbered in one message, the recommended one first; in unattended pace, never ask: write it to the project record's openDecisions with the answer you assumed, as picsart-video-rules says) whether the sheet
 is the structure to copy, before anything is mapped onto it.
 
-## 3. Map the script
+## 3. The format, and what the footage can match
+
+Read how the reference looks into the record's `format`, as `references/format.md` says: the
+layout and who sits where, the emphasis, the captions' style and **position**, the hook, the end
+card and, for the user's own channel, the brand files. Draft it from the sheet, then fill it from
+the stills:
+
+```
+python3 scripts/ref_format.py from-sheet sheet.json --source own-brand --out format.json
+python3 scripts/ref_format.py check format.json
+```
+
+Then answer each element against the user's footage: reproduced, approximated (say how) or
+impossible. Anything not reproduced: ASK (with the host's own choice tool where it offers one, such as request_user_input in Codex's Plan mode, so the user taps an option; a Picsart board the step names asks there instead; only where neither works, the options numbered in one message, the recommended one first; in unattended pace, never ask: write it to the project record's openDecisions with the answer you assumed, as picsart-video-rules says) with a rendered mock (one free frame of their
+footage in the format) beside the reference still, and keep the answer in the block.
+`ref_format.py feasibility format.json` refuses while an element is open. The reference stage is
+done only with a sheet that passes `sheet.py validate` and no open feasibility row.
+
+## 4. Map the script
 
 The user's script is a table with a Time column, and a Beat column where the writer said which
 reference beat a row copies. Fit it to the sheet:
@@ -110,13 +137,16 @@
   clip keeps its length.
 - A beat no row takes is **dropped**, and the report says so. **No row is ever dropped.**
 
-## 4. Report
+## 5. Report
 
 ```
 python3 scripts/structure_report.py sheet.json mapping.json --transcript transcript.json \
   --media media.json
 ```
 
+Add `--own-brand` for the user's own channel, with its logo, end card and fonts listed under
+`brand` in the media list: they and its on-screen copy are reported "own brand, allowed".
+
 The report has one line per reference beat (its time, the user's rows, matched / changed /
 dropped, the reason), then one per added row. Below it, the content rules, each passed, failed
 or not checked:
@@ -128,7 +158,7 @@
 | pictures | no still or clip of the reference is a generation input |
 | sound | no audio or music of the reference is in the cut |
 
-`media.json` lists the reference's URL and every still or clip made from it, the URLs given to
+The media list (`media.json` where you run commands, else kept in the record) lists the reference's URL and every still or clip made from it, the URLs given to
 each generation, and the audio in the cut; an empty list says none was used, and a missing list is
 not checked. Without it, pictures and sound are not checked, and the report says so; never call
 them passed. Likewise words and captions are not checked while the reference's Voice or On screen
Full technical diff · 3 changed fields

changed /description

BEFORE
"Copy a reference reel's structure, never its content - read its beats, shots, caption pattern, pace and sound bed into a structure sheet (or parse a written beat-by-beat breakdown for free), fit the user's own script to those beats, and report each beat as matched, changed, dropped or added, with the content rules checked. Use when a short should be built the way a reference reel is built, or when a script must be checked against a reference's beats."
AFTER
"Read a reference reel's structure and format, never its content - its beats, shots, caption pattern, pace and bed into a structure sheet (or parse a written breakdown for free), its layout, captions, hook and end card into the record's format, with what the footage can match; fit the user's script to the beats, and report each beat as matched, changed, dropped or added, with the content rules checked. Use when a short should be built the way a reference reel is built or looks, including the user's own channel."

changed /included_files

BEFORE
[
  {
    "relative_path": "scripts/map_structure.py",
    "size_in_bytes": 13347
  },
  {
    "relative_path": "scripts/reuse_guard.py",
    "size_in_bytes": 7118
  },
  {
    "relative_path": "scripts/sheet.py",
    "size_in_bytes": 34804
  },
  {
    "relative_path": "scripts/structure_report.py",
    "size_in_bytes": 22831
  }
]
AFTER
[
  {
    "relative_path": "references/format.md",
    "size_in_bytes": 5615
  },
  {
    "relative_path": "scripts/map_structure.py",
    "size_in_bytes": 15055
  },
  {
    "relative_path": "scripts/ref_format.py",
    "size_in_bytes": 19619
  },
  {
    "relative_path": "scripts/reuse_guard.py",
    "size_in_bytes": 9134
  },
  {
    "relative_path": "scripts/sheet.py",
    "size_in_bytes": 40067
  },
  {
    "relative_path": "scripts/structure_report.py",
    "size_in_bytes": 28761
  }
]

changed /skill_md_contents

BEFORE
"---\nname: reel-structure\ndescription: Copy a reference reel's structure, never its content - read its beats, shots, caption pattern, pace and sound bed into a structure sheet (or parse a written beat-by-beat breakdown for free), fit the user's own script to those beats, and report each beat as matched, changed, dropped or added, with the content rules checked. Use when a short should be built the way a reference reel is built, or when a script must be checked against a reference's beats.\nmetadata:\n  source: channel team breakdowns and tools/reuse_guard.py, commit 3f064f0\n---\n\n# Reel structure\n\nA reference reel lends its **structure**: where its beats fall, how its shots and captions\nwork, how fast it talks, what sits under the voice. Its **content** stays its own. Nothing the\nviewer can see or hear of the reference reaches the user's video: no words, no frames, no audio\nor music. Only its pattern is copied.\n\nThe method has four steps: read the structure into a sheet, check the sheet with the user, map\nthe user's script onto it, and report what matched and what changed.\n\n## 1. Read the structure\n\n**A written breakdown is free.** When the user brings a beat-by-beat breakdown, parse it and skip\nthe read:\n\n```\npython3 scripts/sheet.py parse breakdown.md --out sheet.json\n```\n\n**A reference video is read with the tools.** Every call below except the probe and the stills\nmay charge credits, and a tool charges only when its description says so. Quote what the read\nwill cost, then SPEND (quote it in one line, then get the yes as an ASK with \"Yes, go ahead\" / \"Yes, up to N credits for this task\" / \"No\": the host's own choice tool where it offers one, otherwise those options numbered in one message; the host's own confirmation before a tool runs is not this yes; unless a spend limit the user stated covers it: N credits or an explicit no-limit (\"as much as needed\"), never inferred from words like \"go ahead\". Within it, ask nothing: quote it in one line (\"About 8 credits; 12 of 20 left after this\"), call it, then say what it spent and what remains, keeping a running total that includes failed calls, and stop to ask before the first call that would cross it. A money amount is asked once to restate it in credits; in unattended pace, never ask: call only with a consent or a stated spend limit already recorded, otherwise write the quote to pendingSpends and stop, as picsart-video-rules says). The calls do not depend on each other; run them at the same time,\nand follow each job receipt as picsart-video-rules says.\n\n| Tool | What it gives the sheet |\n|---|---|\n| `picsart_media_probe` | length, frame size, and whether there is audio |\n| `picsart_media_segment_shots` over the whole length | the shots: holds and transitions |\n| `picsart_media_transcribe` | the words' timing, for the pace and for the reuse check, never to reuse them |\n| `picsart_media_describe_video` with `detail: \"deep\"` | shot types, camera moves, on-screen text style, per shot |\n| `picsart_media_analyze_audio` | the bed: tempo and loudness |\n| `picsart_media_video_stills` | one still per beat, **for the user to look at only**, never an input to a generation |\n\nSave each result as it came back, then draft the sheet from them. No video is decoded here:\n\n```\npython3 scripts/sheet.py draft --shots shots.json --transcript transcript.json \\\n  --describe describe.json --audio audio.json --probe probe.json --out sheet.json\n```\n\nThe draft has one row per shot (a long shot is split at its sentences). A short transition is a\ncut, and a long one is a move inside the shot: check each boundary on the stills. Every field\nthe tools cannot know is `?`. **Name every beat yourself**, from the watch and the stills: join\nrows that make one beat, and fill picture, on screen, caption and sound.\n\n## 2. The sheet\n\nOne row per beat, or several rows for a long one, in this table:\n\n```\n| Time (s) | Beat | What happens (picture) | Voice | On screen | Shot | Move | Caption | Sound |\n```\n\n- **Beat** names its role: hook, stake, twist, joke run, feeling, reveal, turn, payoff, CTA,\n  and the retention-hooks skill's intensifier and rehook. Join two with `+` (\"Payoff + CTA\").\n  A reference with its own beat (\"Steps\") keeps that name. Consecutive rows with the same name\n  (reveal, reveal (soft), reveal) stay rows in the sheet and are **one beat** to the mapping\n  and the report, from the first row's start to the last row's end.\n- **`soft`** in the Beat cell marks a beat that starts mid-shot with no line. Its edges are\n  checked within 1 s; every other beat's within 0.5 s.\n- **Voice** is the reference's words, kept only so the reuse check can compare with them, and the\n  pace in words a second comes from it. **On screen** is checked for pattern only. **Caption**\n  is the caption style and timing (\"top, whole reel\"; \"word by word, centre\"). **Sound** is voice\n  only, bed, or effects.\n- **`?` is unknown**, never a value and never an error: a `?` time, a `?` cell, or `?` with a\n  note. Never guess one. The map step needs every beat timed and named, and says which are not.\n- A header above the table, as `- Key: value` lines: Format (talking head, POV skit, screen\n  tutorial, list, reaction), Length, Cut rate, Caption style, Bed, Loudness and Source. Length,\n  cut rate and loudness keep their number and the line as written (`- Cut rate: ~19 cuts/min\n  (21 picture changes…)`). A file with several sheets parses with `parse --all`.\n\nA short breakdown (`| Time | Beat | What happens |`) parses too: its quoted lines become Voice,\nor On screen when the words before them name a caption or a title.\n\nCheck the sheet, and write it as Markdown for the user:\n\n```\npython3 scripts/sheet.py validate sheet.json\npython3 scripts/sheet.py markdown sheet.json --out sheet.md\n```\n\nShow the user the sheet with the stills, and fix what they correct. Then ASK (with the host's own choice tool where it offers one, such as request_user_input in Codex's Plan mode, so the user taps an option; a Picsart board the step names asks there instead; only where neither works, the options numbered in one message, the recommended one first; in unattended pace, never ask: write it to the project record's openDecisions with the answer you assumed, as picsart-video-rules says) whether the sheet\nis the structure to copy, before anything is mapped onto it.\n\n## 3. Map the script\n\nThe user's script is a table with a Time column, and a Beat column where the writer said which\nreference beat a row copies. Fit it to the sheet:\n\n```\npython3 scripts/map_structure.py sheet.json script.md --spans allowed-spans.json --out mapping.json\n```\n\n- The first row opens on the reference's hook.\n- A row named for a beat takes the next beat of that name. A time range on the reference's\n  clock in its Beat cell, with the sheet's id (\"F1 36–54 s\"), carries it over the later beats\n  that range covers. Beats never run backwards.\n- An unnamed row between two rows of one beat joins it. Any other unnamed row is **added**: it is\n  the user's own, and it is kept. When no row is named, each takes the beat its middle falls in.\n- Each beat gets the reference's share of the length. Rows scale by at most 15 %, and a beat\n  within 15 % of its share matches; otherwise it is **changed**, with the reason.\n- **The allowed spans are placed first and never stretched**: a row over the user's own screen\n  clip keeps its length.\n- A beat no row takes is **dropped**, and the report says so. **No row is ever dropped.**\n\n## 4. Report\n\n```\npython3 scripts/structure_report.py sheet.json mapping.json --transcript transcript.json \\\n  --media media.json\n```\n\nThe report has one line per reference beat (its time, the user's rows, matched / changed /\ndropped, the reason), then one per added row. Below it, the content rules, each passed, failed\nor not checked:\n\n| Rule | Checks |\n|---|---|\n| words | no run of 4 or more of the reference's spoken words in a voice line (`scripts/reuse_guard.py`) |\n| captions | the on-screen words are the user's own, short whole-caption copies included; only the caption pattern is copied |\n| pictures | no still or clip of the reference is a generation input |\n| sound | no audio or music of the reference is in the cut |\n\n`media.json` lists the reference's URL and every still or clip made from it, the URLs given to\neach generation, and the audio in the cut; an empty list says none was used, and a missing list is\nnot checked. Without it, pictures and sound are not checked, and the report says so; never call\nthem passed. Likewise words and captions are not checked while the reference's Voice or On screen\ncells are `?` and no `--transcript` covers the speech.\n\n**A failed rule is fixed, not waived.** Rewrite the line, or change the input. A format label\nnobody owns (\"get ready with me\", \"GRWM\", \"POV\", \"storytime\") passes on screen, and the report\nnames it \"genre phrase, allowed\"; show that line to the user. Any other phrase shared with the\nreference stays only when the user chooses it: ASK (with the host's own choice tool where it offers one, such as request_user_input in Codex's Plan mode, so the user taps an option; a Picsart board the step names asks there instead; only where neither works, the options numbered in one message, the recommended one first; in unattended pace, never ask: write it to the project record's openDecisions with the answer you assumed, as picsart-video-rules says) whether to keep it, and pass it as\n`--allow \"<phrase>\"`. To check a whole script file\non its own, `python3 scripts/reuse_guard.py transcript.json script.md` lists every shared run\nwith its line.\n\nShow the user the report beside the sheet. When beats are changed or dropped, ASK (with the host's own choice tool where it offers one, such as request_user_input in Codex's Plan mode, so the user taps an option; a Picsart board the step names asks there instead; only where neither works, the options numbered in one message, the recommended one first; in unattended pace, never ask: write it to the project record's openDecisions with the answer you assumed, as picsart-video-rules says) whether to\nrework the script toward the reference or keep the changes, one beat at a time.\n"
AFTER
"---\nname: reel-structure\ndescription: Read a reference reel's structure and format, never its content - its beats, shots, caption pattern, pace and bed into a structure sheet (or parse a written breakdown for free), its layout, captions, hook and end card into the record's format, with what the footage can match; fit the user's script to the beats, and report each beat as matched, changed, dropped or added, with the content rules checked. Use when a short should be built the way a reference reel is built or looks, including the user's own channel.\nmetadata:\n  source: channel team breakdowns and tools/reuse_guard.py, commit 3f064f0\n---\n\n# Reel structure\n\nA reference reel lends its **structure**: where its beats fall, how its shots and captions\nwork, how fast it talks, what sits under the voice. Its **content** stays its own. Nothing the\nviewer can see or hear of the reference reaches the user's video: no words, no frames, no audio\nor music. Only its pattern is copied.\n\nThe method has five steps: read the structure into a sheet, check the sheet with the user, read\nthe format and what the footage can match of it, map the user's script onto the beats, and report\nwhat matched and what changed. A job with no script (cutting footage to a reference) stops after\nthe format.\n\n**The user's own channel is different**: its format is the spec to reproduce, and its logo, end\ncard, fonts and copy are theirs (own-brand mode, `references/format.md`).\n\n## 1. Read the structure\n\n**A written breakdown is free.** When the user brings a beat-by-beat breakdown, parse it and skip\nthe read:\n\n```\npython3 scripts/sheet.py parse breakdown.md --out sheet.json\n```\n\n**A reference video is read with the tools.** Every call below except the probe and the stills\nmay charge credits, and a tool charges only when its description says so. Quote what the read\nwill cost, then SPEND (quote it in one line, then get the yes as an ASK with \"Yes, go ahead\" / \"Yes, up to N credits for this task\" / \"No\": the host's own choice tool where it offers one, otherwise those options numbered in one message; the host's own confirmation before a tool runs is not this yes; unless a spend limit the user stated covers it: N credits or an explicit no-limit (\"as much as needed\"), never inferred from words like \"go ahead\". Within it, ask nothing: quote it in one line (\"About 8 credits; 12 of 20 left after this\"), call it, then say what it spent and what remains, keeping a running total that includes failed calls, and stop to ask before the first call that would cross it. A money amount is asked once to restate it in credits; in unattended pace, never ask: call only with a consent or a stated spend limit already recorded, otherwise write the quote to pendingSpends and stop, as picsart-video-rules says). The calls do not depend on each other; run them at the same time,\nand follow each job receipt as picsart-video-rules says.\n\n| Tool | What it gives the sheet |\n|---|---|\n| `picsart_media_probe` | length, frame size, and whether there is audio |\n| `picsart_media_segment_shots` over the whole length | the shots: holds and transitions |\n| `picsart_media_transcribe` | the words' timing, for the pace and for the reuse check, never to reuse them |\n| `picsart_media_describe_video` with `detail: \"deep\"` | shot types, camera moves, on-screen text style, per shot |\n| `picsart_media_analyze_audio` | the bed: tempo and loudness |\n| `picsart_media_video_stills` | one still per beat, **for the user to look at only**, never an input to a generation |\n\nKeep each result as it came back (as files, where you run commands), then draft the sheet from them. No video is decoded here:\n\n```\npython3 scripts/sheet.py draft --shots shots.json --transcript transcript.json \\\n  --describe describe.json --audio audio.json --probe probe.json --out sheet.json\n```\n\nThe draft has one row per shot (a long shot is split at its sentences). A short transition is a\ncut, and a long one is a move inside the shot: check each boundary on the stills. Every field\nthe tools cannot know is `?`. **Name every beat yourself**, from the watch and the stills: join\nrows that make one beat, and fill picture, on screen, caption and sound.\n\n## 2. The sheet\n\nOne row per beat, or several rows for a long one, in this table:\n\n```\n| Time (s) | Beat | What happens (picture) | Voice | On screen | Shot | Move | Caption | Sound |\n```\n\n- **Beat** names its role: hook, stake, twist, joke run, feeling, reveal, turn, payoff, CTA,\n  and the retention-hooks skill's intensifier and rehook. Join two with `+` (\"Payoff + CTA\").\n  A reference with its own beat (\"Steps\") keeps that name. Consecutive rows with the same name\n  (reveal, reveal (soft), reveal) stay rows in the sheet and are **one beat** to the mapping\n  and the report, from the first row's start to the last row's end.\n- **`soft`** in the Beat cell marks a beat that starts mid-shot with no line. Its edges are\n  checked within 1 s; every other beat's within 0.5 s.\n- **Voice** is the reference's words, kept only so the reuse check can compare with them, and the\n  pace in words a second comes from it. **On screen** is checked for pattern only. **Caption**\n  is the caption style and timing (\"top, whole reel\"; \"word by word, centre\"). **Sound** is voice\n  only, bed, or effects.\n- **`?` is unknown**, never a value and never an error: a `?` time, a `?` cell, or `?` with a\n  note. Never guess one. The map step needs every beat timed and named, and says which are not.\n- A header above the table, as `- Key: value` lines: Format (talking head, POV skit, screen\n  tutorial, list, reaction), Length, Cut rate, Caption style, Layout, Bed, Loudness and Source.\n  **Layout** names the mode and who sits where: `split-v (top host, bottom guest)`.\n- Two more columns after Sound when the reference has a format to keep: **Frame** (the beat's\n  layout, or who fills it: `split-v`, `full: guest`) and **Caption position** (`seam`, `top`,\n  `centre`, `lower third`). Length,\n  cut rate and loudness keep their number and the line as written (`- Cut rate: ~19 cuts/min\n  (21 picture changes…)`). A file with several sheets parses with `parse --all`.\n\nA short breakdown (`| Time | Beat | What happens |`) parses too: its quoted lines become Voice,\nor On screen when the words before them name a caption or a title.\n\nCheck the sheet, and write it as Markdown for the user:\n\n```\npython3 scripts/sheet.py validate sheet.json\npython3 scripts/sheet.py markdown sheet.json --out sheet.md\n```\n\nShow the user the sheet with the stills, and fix what they correct. Then ASK (with the host's own choice tool where it offers one, such as request_user_input in Codex's Plan mode, so the user taps an option; a Picsart board the step names asks there instead; only where neither works, the options numbered in one message, the recommended one first; in unattended pace, never ask: write it to the project record's openDecisions with the answer you assumed, as picsart-video-rules says) whether the sheet\nis the structure to copy, before anything is mapped onto it.\n\n## 3. The format, and what the footage can match\n\nRead how the reference looks into the record's `format`, as `references/format.md` says: the\nlayout and who sits where, the emphasis, the captions' style and **position**, the hook, the end\ncard and, for the user's own channel, the brand files. Draft it from the sheet, then fill it from\nthe stills:\n\n```\npython3 scripts/ref_format.py from-sheet sheet.json --source own-brand --out format.json\npython3 scripts/ref_format.py check format.json\n```\n\nThen answer each element against the user's footage: reproduced, approximated (say how) or\nimpossible. Anything not reproduced: ASK (with the host's own choice tool where it offers one, such as request_user_input in Codex's Plan mode, so the user taps an option; a Picsart board the step names asks there instead; only where neither works, the options numbered in one message, the recommended one first; in unattended pace, never ask: write it to the project record's openDecisions with the answer you assumed, as picsart-video-rules says) with a rendered mock (one free frame of their\nfootage in the format) beside the reference still, and keep the answer in the block.\n`ref_format.py feasibility format.json` refuses while an element is open. The reference stage is\ndone only with a sheet that passes `sheet.py validate` and no open feasibility row.\n\n## 4. Map the script\n\nThe user's script is a table with a Time column, and a Beat column where the writer said which\nreference beat a row copies. Fit it to the sheet:\n\n```\npython3 scripts/map_structure.py sheet.json script.md --spans allowed-spans.json --out mapping.json\n```\n\n- The first row opens on the reference's hook.\n- A row named for a beat takes the next beat of that name. A time range on the reference's\n  clock in its Beat cell, with the sheet's id (\"F1 36–54 s\"), carries it over the later beats\n  that range covers. Beats never run backwards.\n- An unnamed row between two rows of one beat joins it. Any other unnamed row is **added**: it is\n  the user's own, and it is kept. When no row is named, each takes the beat its middle falls in.\n- Each beat gets the reference's share of the length. Rows scale by at most 15 %, and a beat\n  within 15 % of its share matches; otherwise it is **changed**, with the reason.\n- **The allowed spans are placed first and never stretched**: a row over the user's own screen\n  clip keeps its length.\n- A beat no row takes is **dropped**, and the report says so. **No row is ever dropped.**\n\n## 5. Report\n\n```\npython3 scripts/structure_report.py sheet.json mapping.json --transcript transcript.json \\\n  --media media.json\n```\n\nAdd `--own-brand` for the user's own channel, with its logo, end card and fonts listed under\n`brand` in the media list: they and its on-screen copy are reported \"own brand, allowed\".\n\nThe report has one line per reference beat (its time, the user's rows, matched / changed /\ndropped, the reason), then one per added row. Below it, the content rules, each passed, failed\nor not checked:\n\n| Rule | Checks |\n|---|---|\n| words | no run of 4 or more of the reference's spoken words in a voice line (`scripts/reuse_guard.py`) |\n| captions | the on-screen words are the user's own, short whole-caption copies included; only the caption pattern is copied |\n| pictures | no still or clip of the reference is a generation input |\n| sound | no audio or music of the reference is in the cut |\n\nThe media list (`media.json` where you run commands, else kept in the record) lists the reference's URL and every still or clip made from it, the URLs given to\neach generation, and the audio in the cut; an empty list says none was used, and a missing list is\nnot checked. Without it, pictures and sound are not checked, and the report says so; never call\nthem passed. Likewise words and captions are not checked while the reference's Voice or On screen\ncells are `?` and no `--transcript` covers the speech.\n\n**A failed rule is fixed, not waived.** Rewrite the line, or change the input. A format label\nnobody owns (\"get ready with me\", \"GRWM\", \"POV\", \"storytime\") passes on screen, and the report\nnames it \"genre phrase, allowed\"; show that line to the user. Any other phrase shared with the\nreference stays only when the user chooses it: ASK (with the host's own choice tool where it offers one, such as request_user_input in Codex's Plan mode, so the user taps an option; a Picsart board the step names asks there instead; only where neither works, the options numbered in one message, the recommended one first; in unattended pace, never ask: write it to the project record's openDecisions with the answer you assumed, as picsart-video-rules says) whether to keep it, and pass it as\n`--allow \"<phrase>\"`. To check a whole script file\non its own, `python3 scripts/reuse_guard.py transcript.json script.md` lists every shared run\nwith its line.\n\nShow the user the report beside the sheet. When beats are changed or dropped, ASK (with the host's own choice tool where it offers one, such as request_user_input in Codex's Plan mode, so the user taps an option; a Picsart board the step names asks there instead; only where neither works, the options numbered in one message, the recommended one first; in unattended pace, never ask: write it to the project record's openDecisions with the answer you assumed, as picsart-video-rules says) whether to\nrework the script toward the reference or keep the changes, one beat at a time.\n"
Full snapshot data
{
  "description": "Read a reference reel's structure and format, never its content - its beats, shots, caption pattern, pace and bed into a structure sheet (or parse a written breakdown for free), its layout, captions, hook and end card into the record's format, with what the footage can match; fit the user's script to the beats, and report each beat as matched, changed, dropped or added, with the content rules checked. Use when a short should be built the way a reference reel is built or looks, including the user's own channel.",
  "included_files": [
    {
      "relative_path": "references/format.md",
      "size_in_bytes": 5615
    },
    {
      "relative_path": "scripts/map_structure.py",
      "size_in_bytes": 15055
    },
    {
      "relative_path": "scripts/ref_format.py",
      "size_in_bytes": 19619
    },
    {
      "relative_path": "scripts/reuse_guard.py",
      "size_in_bytes": 9134
    },
    {
      "relative_path": "scripts/sheet.py",
      "size_in_bytes": 40067
    },
    {
      "relative_path": "scripts/structure_report.py",
      "size_in_bytes": 28761
    }
  ],
  "name": "reel-structure",
  "skill_md_contents": "---\nname: reel-structure\ndescription: Read a reference reel's structure and format, never its content - its beats, shots, caption pattern, pace and bed into a structure sheet (or parse a written breakdown for free), its layout, captions, hook and end card into the record's format, with what the footage can match; fit the user's script to the beats, and report each beat as matched, changed, dropped or added, with the content rules checked. Use when a short should be built the way a reference reel is built or looks, including the user's own channel.\nmetadata:\n  source: channel team breakdowns and tools/reuse_guard.py, commit 3f064f0\n---\n\n# Reel structure\n\nA reference reel lends its **structure**: where its beats fall, how its shots and captions\nwork, how fast it talks, what sits under the voice. Its **content** stays its own. Nothing the\nviewer can see or hear of the reference reaches the user's video: no words, no frames, no audio\nor music. Only its pattern is copied.\n\nThe method has five steps: read the structure into a sheet, check the sheet with the user, read\nthe format and what the footage can match of it, map the user's script onto the beats, and report\nwhat matched and what changed. A job with no script (cutting footage to a reference) stops after\nthe format.\n\n**The user's own channel is different**: its format is the spec to reproduce, and its logo, end\ncard, fonts and copy are theirs (own-brand mode, `references/format.md`).\n\n## 1. Read the structure\n\n**A written breakdown is free.** When the user brings a beat-by-beat breakdown, parse it and skip\nthe read:\n\n```\npython3 scripts/sheet.py parse breakdown.md --out sheet.json\n```\n\n**A reference video is read with the tools.** Every call below except the probe and the stills\nmay charge credits, and a tool charges only when its description says so. Quote what the read\nwill cost, then SPEND (quote it in one line, then get the yes as an ASK with \"Yes, go ahead\" / \"Yes, up to N credits for this task\" / \"No\": the host's own choice tool where it offers one, otherwise those options numbered in one message; the host's own confirmation before a tool runs is not this yes; unless a spend limit the user stated covers it: N credits or an explicit no-limit (\"as much as needed\"), never inferred from words like \"go ahead\". Within it, ask nothing: quote it in one line (\"About 8 credits; 12 of 20 left after this\"), call it, then say what it spent and what remains, keeping a running total that includes failed calls, and stop to ask before the first call that would cross it. A money amount is asked once to restate it in credits; in unattended pace, never ask: call only with a consent or a stated spend limit already recorded, otherwise write the quote to pendingSpends and stop, as picsart-video-rules says). The calls do not depend on each other; run them at the same time,\nand follow each job receipt as picsart-video-rules says.\n\n| Tool | What it gives the sheet |\n|---|---|\n| `picsart_media_probe` | length, frame size, and whether there is audio |\n| `picsart_media_segment_shots` over the whole length | the shots: holds and transitions |\n| `picsart_media_transcribe` | the words' timing, for the pace and for the reuse check, never to reuse them |\n| `picsart_media_describe_video` with `detail: \"deep\"` | shot types, camera moves, on-screen text style, per shot |\n| `picsart_media_analyze_audio` | the bed: tempo and loudness |\n| `picsart_media_video_stills` | one still per beat, **for the user to look at only**, never an input to a generation |\n\nKeep each result as it came back (as files, where you run commands), then draft the sheet from them. No video is decoded here:\n\n```\npython3 scripts/sheet.py draft --shots shots.json --transcript transcript.json \\\n  --describe describe.json --audio audio.json --probe probe.json --out sheet.json\n```\n\nThe draft has one row per shot (a long shot is split at its sentences). A short transition is a\ncut, and a long one is a move inside the shot: check each boundary on the stills. Every field\nthe tools cannot know is `?`. **Name every beat yourself**, from the watch and the stills: join\nrows that make one beat, and fill picture, on screen, caption and sound.\n\n## 2. The sheet\n\nOne row per beat, or several rows for a long one, in this table:\n\n```\n| Time (s) | Beat | What happens (picture) | Voice | On screen | Shot | Move | Caption | Sound |\n```\n\n- **Beat** names its role: hook, stake, twist, joke run, feeling, reveal, turn, payoff, CTA,\n  and the retention-hooks skill's intensifier and rehook. Join two with `+` (\"Payoff + CTA\").\n  A reference with its own beat (\"Steps\") keeps that name. Consecutive rows with the same name\n  (reveal, reveal (soft), reveal) stay rows in the sheet and are **one beat** to the mapping\n  and the report, from the first row's start to the last row's end.\n- **`soft`** in the Beat cell marks a beat that starts mid-shot with no line. Its edges are\n  checked within 1 s; every other beat's within 0.5 s.\n- **Voice** is the reference's words, kept only so the reuse check can compare with them, and the\n  pace in words a second comes from it. **On screen** is checked for pattern only. **Caption**\n  is the caption style and timing (\"top, whole reel\"; \"word by word, centre\"). **Sound** is voice\n  only, bed, or effects.\n- **`?` is unknown**, never a value and never an error: a `?` time, a `?` cell, or `?` with a\n  note. Never guess one. The map step needs every beat timed and named, and says which are not.\n- A header above the table, as `- Key: value` lines: Format (talking head, POV skit, screen\n  tutorial, list, reaction), Length, Cut rate, Caption style, Layout, Bed, Loudness and Source.\n  **Layout** names the mode and who sits where: `split-v (top host, bottom guest)`.\n- Two more columns after Sound when the reference has a format to keep: **Frame** (the beat's\n  layout, or who fills it: `split-v`, `full: guest`) and **Caption position** (`seam`, `top`,\n  `centre`, `lower third`). Length,\n  cut rate and loudness keep their number and the line as written (`- Cut rate: ~19 cuts/min\n  (21 picture changes…)`). A file with several sheets parses with `parse --all`.\n\nA short breakdown (`| Time | Beat | What happens |`) parses too: its quoted lines become Voice,\nor On screen when the words before them name a caption or a title.\n\nCheck the sheet, and write it as Markdown for the user:\n\n```\npython3 scripts/sheet.py validate sheet.json\npython3 scripts/sheet.py markdown sheet.json --out sheet.md\n```\n\nShow the user the sheet with the stills, and fix what they correct. Then ASK (with the host's own choice tool where it offers one, such as request_user_input in Codex's Plan mode, so the user taps an option; a Picsart board the step names asks there instead; only where neither works, the options numbered in one message, the recommended one first; in unattended pace, never ask: write it to the project record's openDecisions with the answer you assumed, as picsart-video-rules says) whether the sheet\nis the structure to copy, before anything is mapped onto it.\n\n## 3. The format, and what the footage can match\n\nRead how the reference looks into the record's `format`, as `references/format.md` says: the\nlayout and who sits where, the emphasis, the captions' style and **position**, the hook, the end\ncard and, for the user's own channel, the brand files. Draft it from the sheet, then fill it from\nthe stills:\n\n```\npython3 scripts/ref_format.py from-sheet sheet.json --source own-brand --out format.json\npython3 scripts/ref_format.py check format.json\n```\n\nThen answer each element against the user's footage: reproduced, approximated (say how) or\nimpossible. Anything not reproduced: ASK (with the host's own choice tool where it offers one, such as request_user_input in Codex's Plan mode, so the user taps an option; a Picsart board the step names asks there instead; only where neither works, the options numbered in one message, the recommended one first; in unattended pace, never ask: write it to the project record's openDecisions with the answer you assumed, as picsart-video-rules says) with a rendered mock (one free frame of their\nfootage in the format) beside the reference still, and keep the answer in the block.\n`ref_format.py feasibility format.json` refuses while an element is open. The reference stage is\ndone only with a sheet that passes `sheet.py validate` and no open feasibility row.\n\n## 4. Map the script\n\nThe user's script is a table with a Time column, and a Beat column where the writer said which\nreference beat a row copies. Fit it to the sheet:\n\n```\npython3 scripts/map_structure.py sheet.json script.md --spans allowed-spans.json --out mapping.json\n```\n\n- The first row opens on the reference's hook.\n- A row named for a beat takes the next beat of that name. A time range on the reference's\n  clock in its Beat cell, with the sheet's id (\"F1 36–54 s\"), carries it over the later beats\n  that range covers. Beats never run backwards.\n- An unnamed row between two rows of one beat joins it. Any other unnamed row is **added**: it is\n  the user's own, and it is kept. When no row is named, each takes the beat its middle falls in.\n- Each beat gets the reference's share of the length. Rows scale by at most 15 %, and a beat\n  within 15 % of its share matches; otherwise it is **changed**, with the reason.\n- **The allowed spans are placed first and never stretched**: a row over the user's own screen\n  clip keeps its length.\n- A beat no row takes is **dropped**, and the report says so. **No row is ever dropped.**\n\n## 5. Report\n\n```\npython3 scripts/structure_report.py sheet.json mapping.json --transcript transcript.json \\\n  --media media.json\n```\n\nAdd `--own-brand` for the user's own channel, with its logo, end card and fonts listed under\n`brand` in the media list: they and its on-screen copy are reported \"own brand, allowed\".\n\nThe report has one line per reference beat (its time, the user's rows, matched / changed /\ndropped, the reason), then one per added row. Below it, the content rules, each passed, failed\nor not checked:\n\n| Rule | Checks |\n|---|---|\n| words | no run of 4 or more of the reference's spoken words in a voice line (`scripts/reuse_guard.py`) |\n| captions | the on-screen words are the user's own, short whole-caption copies included; only the caption pattern is copied |\n| pictures | no still or clip of the reference is a generation input |\n| sound | no audio or music of the reference is in the cut |\n\nThe media list (`media.json` where you run commands, else kept in the record) lists the reference's URL and every still or clip made from it, the URLs given to\neach generation, and the audio in the cut; an empty list says none was used, and a missing list is\nnot checked. Without it, pictures and sound are not checked, and the report says so; never call\nthem passed. Likewise words and captions are not checked while the reference's Voice or On screen\ncells are `?` and no `--transcript` covers the speech.\n\n**A failed rule is fixed, not waived.** Rewrite the line, or change the input. A format label\nnobody owns (\"get ready with me\", \"GRWM\", \"POV\", \"storytime\") passes on screen, and the report\nnames it \"genre phrase, allowed\"; show that line to the user. Any other phrase shared with the\nreference stays only when the user chooses it: ASK (with the host's own choice tool where it offers one, such as request_user_input in Codex's Plan mode, so the user taps an option; a Picsart board the step names asks there instead; only where neither works, the options numbered in one message, the recommended one first; in unattended pace, never ask: write it to the project record's openDecisions with the answer you assumed, as picsart-video-rules says) whether to keep it, and pass it as\n`--allow \"<phrase>\"`. To check a whole script file\non its own, `python3 scripts/reuse_guard.py transcript.json script.md` lists every shared run\nwith its line.\n\nShow the user the report beside the sheet. When beats are changed or dropped, ASK (with the host's own choice tool where it offers one, such as request_user_input in Codex's Plan mode, so the user taps an option; a Picsart board the step names asks there instead; only where neither works, the options numbered in one message, the recommended one first; in unattended pace, never ask: write it to the project record's openDecisions with the answer you assumed, as picsart-video-rules says) whether to\nrework the script toward the reference or keep the changes, one beat at a time.\n"
}

SHA-256 of public snapshot: 81bb54d7e8a90b0c366e4ae591a296c4eec966f7cefa45f14c6f8d1408f63ce1