Update to BlitzReels
Snapshot Nov 3, 2026 · 18:14 UTC · version 4.0.1
Collection source: downloaded plugin package. These snapshots do not have a confirmed matching collection source. Differences in file lists alone do not establish changes to the package.
Payment or plan references changed
Full description — Now says: Clipping: turn webinars, interviews, demos or uploaded recordings into captioned business clips; review moments, choose, repair or export clips with BlitzReels.
Observed in published text. Live prices and checkout terms have not been verified by this change.
Up to 3 plugins free · no card required.
All fields and original values.
Full description
Sep 30, 2026 · 22:47 UTC
Clipping: create, inspect, reselect, repair, caption, or export short clips from an uploaded file, BlitzReels asset, or permitted public video URL.
Nov 3, 2026 · 18:14 UTC
Clipping: turn webinars, interviews, demos or uploaded recordings into captioned business clips; review moments, choose, repair or export clips with BlitzReels.
Skill instructions
Sep 30, 2026 · 22:47 UTC
create, inspect, reselect, repair, caption, or export short clips from an uploaded file, BlitzReels asset, or permitted public video URL." Create or adjust one clip batch, follow its bounded state, and return verified results. ## 1. Reso...
Nov 3, 2026 · 18:14 UTC
turn webinars, interviews, demos or uploaded recordings into captioned business clips; review moments, choose, repair or export clips with BlitzReels." Repurpose the identified recording into complete, source-grounded moments for the use...
Compare saved observations
Download comparison JSONSKILL.md text changes
− removed · + added
--- before +++ after @@ -1,46 +1,69 @@ --- name: create-short-clips -description: "Clipping: create, inspect, reselect, repair, caption, or export short clips from an uploaded file, BlitzReels asset, or permitted public video URL." +description: "Clipping: turn webinars, interviews, demos or uploaded recordings into captioned business clips; review moments, choose, repair or export clips with BlitzReels." --- # Clipping -Create or adjust one clip batch, follow its bounded state, and return verified results. +Repurpose the identified recording into complete, source-grounded moments for the user's business. -## 1. Resolve the source +## 1. Resolve source and context -- Use the identified BlitzReels asset ID when the user already chose one. -- For a ChatGPT attachment, call `media_upload_file` and use its returned asset ID. -- For an unidentified workspace file, call `media_list`; ask the user only when several plausible assets remain. -- For a public URL, confirm ownership or permission before creation. Call `media_import_inspect` when support is - uncertain or the user asks for a preview. +- Use the selected asset, `media_upload_file` for a ChatGPT attachment, `media_list` for workspace media, + or the user's supported URL. Use `media_import_inspect` to verify uncertain URL support and source metadata. +- Read `workspace_context_get` for the explicit workspace. Use `workspaces_list` only when selection is unresolved. +- Reuse reviewed audience, offer, purpose, language, protected and avoided terms, captions and Series; ask only for missing material choices. +- For a social URL with multiple audio tracks, use the language from `media_import_inspect` as selectedAudioLanguage. + Null preserves the default track; direct files and existing assets preserve source audio. +- State the source, duration when known, intended clip count, duration bounds, platform, purpose and export constraints. +- For a short recording the user wants preserved, route to edit-and-export-video; clipping selects excerpts. +- Treat each independent source as its own batch. Reuse approved settings and retain every source-to-batch mapping. + +Completion: identified sources, authorized workspace and resolved business outcome. + +## 2. Review moments and create + +- When the source has candidates, read `clips_candidates_list`; use `media_transcript_get` for needed context. +- Prefer complete explanations, examples, demonstrations, proof or relevant objections for the requested audience. +- Show candidate IDs, source ranges, factual hooks and a brief reason. Distinguish the spoken excerpt from draft copy. +- Apply topic instructions by selecting matching verified candidate IDs; show when no matching candidate exists. +- Call `clips_create` with one asset or URL, clipCount, durationBounds and the chosen captionThemeId. +- Use selection.includeIds for approved candidates; use selection.excludeIds for rejected candidates. +- Omitted captions inherit reviewed defaults. Preserve the chosen Series; use null for explicitly standalone clips. +- Keep createSharePage false unless public sharing is explicitly requested. +- Create once with a stable idempotencyKey. Retry identical inputs with the same key; inspect after ambiguous responses. + +Completion: one accepted batch per source with verified identifiers and requested settings. + +## 3. Follow and revise + +- Read batch.polling and follow `clips_status_get` within its delay and attempt/time limits. +- Show the batch with `clips_get` when playback is requested; status polling keeps the current review widget mounted. +- Deliver ready clips incrementally. Processing or QA warnings alone do not justify recreating accepted clips. +- Use `clips_list` and `clips_inspect` for bounded state; use `clips_reselect`, `clips_repair`, `clips_export` + or `captions_look_apply` for the identified clip and explicit requested change. +- Selected widget clip/time context identifies the target; route precise project edits to edit-and-export-video. +- Use `clips_recover` only for a terminal batch's missing count; retain accepted clips and rejected moments. + +Completion: every clip accounted for as ready, active, requiring review or failed. + +## 4. Deliver and reuse + +- Present inline playback and ready MP4s or the ZIP. Refresh `clips_status_get` when signed links expire. +- State the actual quality/watermark and any unresolved framing, caption or audio issues. +- Save user-requested ratings with `video_feedback_save` for the exact completed export; preserve accepted output. +- Draft titles, covers and platform copy from the verified source; keep invented statistics and claims out. +- For LinkedIn posts or carousels, reuse approved source excerpts; use the existing carousel tools to render/export. +- Organize repeat work with the existing Series and folder tools. A weekly request without configured recurrence + remains a manual task; describe the missing source, schedule and destination instead of claiming an automation. +- For a public review page, inspect `clip_share_get`, obtain explicit public/download choices, then call + `clip_share_publish`. Verify the returned link. `clip_share_visibility_set` changes only the selected clip. +- Publishing requires a supported live connection and explicit reviewed caption, destination and schedule. + Report scheduled and published states separately; never infer attributed sales from engagement. +- At a processing bound, return the batch ID, latest state and available continuation. -Completion: exactly one verified asset ID or supported URL. +Completion: usable files or explicit active/blocked state, with every requested delivery action verified. -## 2. Create or adjust +## Account access -- New batch: call `clips_create` once with exactly one of `assetId` or `url`. -- Public showcase: set `createSharePage` only when the user asks for one. -- Existing batch: use `clips_manage` to inspect, reselect, repair, caption, or export it. -- Selection: preserve an explicit range; use automatic best selection only when the user delegates the choice. -- Deletion: call `clip_batches_delete` for the identified batch only after the user confirms deletion. - -Completion: one valid batch ID whose latest state reflects the requested creation or adjustment. - -## 3. Follow the batch - -- Read `batch.polling` from each result. -- When `shouldPoll` is true, call `clips_get` after the suggested delay. -- Continue the existing batch until a terminal state or the returned polling limit. - -Completion: a terminal result or the latest bounded active state. - -## 4. Deliver the result - -- Report batch status plus rendered, review, and failed counts. -- List downloadable clips first, each with its verified title and URL. -- Include the studio URL when review or editing remains. -- Surface `lastErrorMessage` and per-clip errors from the latest tool result. -- At the polling limit, return the batch ID and studio URL and state that processing remains active. - -Completion: every clip is accounted for with verified status and available links. +Use existing entitlements. Explain missing credits or quota calmly, without checkout, pricing, subscriptions or upsells.
Full technical diff · 2 changed fields
changed /description
"Clipping: create, inspect, reselect, repair, caption, or export short clips from an uploaded file, BlitzReels asset, or permitted public video URL."
"Clipping: turn webinars, interviews, demos or uploaded recordings into captioned business clips; review moments, choose, repair or export clips with BlitzReels."
changed /skill_md_contents
"---\nname: create-short-clips\ndescription: \"Clipping: create, inspect, reselect, repair, caption, or export short clips from an uploaded file, BlitzReels asset, or permitted public video URL.\"\n---\n\n# Clipping\n\nCreate or adjust one clip batch, follow its bounded state, and return verified results.\n\n## 1. Resolve the source\n\n- Use the identified BlitzReels asset ID when the user already chose one.\n- For a ChatGPT attachment, call `media_upload_file` and use its returned asset ID.\n- For an unidentified workspace file, call `media_list`; ask the user only when several plausible assets remain.\n- For a public URL, confirm ownership or permission before creation. Call `media_import_inspect` when support is\n uncertain or the user asks for a preview.\n\nCompletion: exactly one verified asset ID or supported URL.\n\n## 2. Create or adjust\n\n- New batch: call `clips_create` once with exactly one of `assetId` or `url`.\n- Public showcase: set `createSharePage` only when the user asks for one.\n- Existing batch: use `clips_manage` to inspect, reselect, repair, caption, or export it.\n- Selection: preserve an explicit range; use automatic best selection only when the user delegates the choice.\n- Deletion: call `clip_batches_delete` for the identified batch only after the user confirms deletion.\n\nCompletion: one valid batch ID whose latest state reflects the requested creation or adjustment.\n\n## 3. Follow the batch\n\n- Read `batch.polling` from each result.\n- When `shouldPoll` is true, call `clips_get` after the suggested delay.\n- Continue the existing batch until a terminal state or the returned polling limit.\n\nCompletion: a terminal result or the latest bounded active state.\n\n## 4. Deliver the result\n\n- Report batch status plus rendered, review, and failed counts.\n- List downloadable clips first, each with its verified title and URL.\n- Include the studio URL when review or editing remains.\n- Surface `lastErrorMessage` and per-clip errors from the latest tool result.\n- At the polling limit, return the batch ID and studio URL and state that processing remains active.\n\nCompletion: every clip is accounted for with verified status and available links.\n"
"---\nname: create-short-clips\ndescription: \"Clipping: turn webinars, interviews, demos or uploaded recordings into captioned business clips; review moments, choose, repair or export clips with BlitzReels.\"\n---\n\n# Clipping\n\nRepurpose the identified recording into complete, source-grounded moments for the user's business.\n\n## 1. Resolve source and context\n\n- Use the selected asset, `media_upload_file` for a ChatGPT attachment, `media_list` for workspace media,\n or the user's supported URL. Use `media_import_inspect` to verify uncertain URL support and source metadata.\n- Read `workspace_context_get` for the explicit workspace. Use `workspaces_list` only when selection is unresolved.\n- Reuse reviewed audience, offer, purpose, language, protected and avoided terms, captions and Series; ask only for missing material choices.\n- For a social URL with multiple audio tracks, use the language from `media_import_inspect` as selectedAudioLanguage.\n Null preserves the default track; direct files and existing assets preserve source audio.\n- State the source, duration when known, intended clip count, duration bounds, platform, purpose and export constraints.\n- For a short recording the user wants preserved, route to edit-and-export-video; clipping selects excerpts.\n- Treat each independent source as its own batch. Reuse approved settings and retain every source-to-batch mapping.\n\nCompletion: identified sources, authorized workspace and resolved business outcome.\n\n## 2. Review moments and create\n\n- When the source has candidates, read `clips_candidates_list`; use `media_transcript_get` for needed context.\n- Prefer complete explanations, examples, demonstrations, proof or relevant objections for the requested audience.\n- Show candidate IDs, source ranges, factual hooks and a brief reason. Distinguish the spoken excerpt from draft copy.\n- Apply topic instructions by selecting matching verified candidate IDs; show when no matching candidate exists.\n- Call `clips_create` with one asset or URL, clipCount, durationBounds and the chosen captionThemeId.\n- Use selection.includeIds for approved candidates; use selection.excludeIds for rejected candidates.\n- Omitted captions inherit reviewed defaults. Preserve the chosen Series; use null for explicitly standalone clips.\n- Keep createSharePage false unless public sharing is explicitly requested.\n- Create once with a stable idempotencyKey. Retry identical inputs with the same key; inspect after ambiguous responses.\n\nCompletion: one accepted batch per source with verified identifiers and requested settings.\n\n## 3. Follow and revise\n\n- Read batch.polling and follow `clips_status_get` within its delay and attempt/time limits.\n- Show the batch with `clips_get` when playback is requested; status polling keeps the current review widget mounted.\n- Deliver ready clips incrementally. Processing or QA warnings alone do not justify recreating accepted clips.\n- Use `clips_list` and `clips_inspect` for bounded state; use `clips_reselect`, `clips_repair`, `clips_export`\n or `captions_look_apply` for the identified clip and explicit requested change.\n- Selected widget clip/time context identifies the target; route precise project edits to edit-and-export-video.\n- Use `clips_recover` only for a terminal batch's missing count; retain accepted clips and rejected moments.\n\nCompletion: every clip accounted for as ready, active, requiring review or failed.\n\n## 4. Deliver and reuse\n\n- Present inline playback and ready MP4s or the ZIP. Refresh `clips_status_get` when signed links expire.\n- State the actual quality/watermark and any unresolved framing, caption or audio issues.\n- Save user-requested ratings with `video_feedback_save` for the exact completed export; preserve accepted output.\n- Draft titles, covers and platform copy from the verified source; keep invented statistics and claims out.\n- For LinkedIn posts or carousels, reuse approved source excerpts; use the existing carousel tools to render/export.\n- Organize repeat work with the existing Series and folder tools. A weekly request without configured recurrence\n remains a manual task; describe the missing source, schedule and destination instead of claiming an automation.\n- For a public review page, inspect `clip_share_get`, obtain explicit public/download choices, then call\n `clip_share_publish`. Verify the returned link. `clip_share_visibility_set` changes only the selected clip.\n- Publishing requires a supported live connection and explicit reviewed caption, destination and schedule.\n Report scheduled and published states separately; never infer attributed sales from engagement.\n- At a processing bound, return the batch ID, latest state and available continuation.\n\nCompletion: usable files or explicit active/blocked state, with every requested delivery action verified.\n\n## Account access\n\nUse existing entitlements. Explain missing credits or quota calmly, without checkout, pricing, subscriptions or upsells.\n"
Full snapshot data
{
"description": "Clipping: turn webinars, interviews, demos or uploaded recordings into captioned business clips; review moments, choose, repair or export clips with BlitzReels.",
"included_files": [],
"name": "create-short-clips",
"skill_md_contents": "---\nname: create-short-clips\ndescription: \"Clipping: turn webinars, interviews, demos or uploaded recordings into captioned business clips; review moments, choose, repair or export clips with BlitzReels.\"\n---\n\n# Clipping\n\nRepurpose the identified recording into complete, source-grounded moments for the user's business.\n\n## 1. Resolve source and context\n\n- Use the selected asset, `media_upload_file` for a ChatGPT attachment, `media_list` for workspace media,\n or the user's supported URL. Use `media_import_inspect` to verify uncertain URL support and source metadata.\n- Read `workspace_context_get` for the explicit workspace. Use `workspaces_list` only when selection is unresolved.\n- Reuse reviewed audience, offer, purpose, language, protected and avoided terms, captions and Series; ask only for missing material choices.\n- For a social URL with multiple audio tracks, use the language from `media_import_inspect` as selectedAudioLanguage.\n Null preserves the default track; direct files and existing assets preserve source audio.\n- State the source, duration when known, intended clip count, duration bounds, platform, purpose and export constraints.\n- For a short recording the user wants preserved, route to edit-and-export-video; clipping selects excerpts.\n- Treat each independent source as its own batch. Reuse approved settings and retain every source-to-batch mapping.\n\nCompletion: identified sources, authorized workspace and resolved business outcome.\n\n## 2. Review moments and create\n\n- When the source has candidates, read `clips_candidates_list`; use `media_transcript_get` for needed context.\n- Prefer complete explanations, examples, demonstrations, proof or relevant objections for the requested audience.\n- Show candidate IDs, source ranges, factual hooks and a brief reason. Distinguish the spoken excerpt from draft copy.\n- Apply topic instructions by selecting matching verified candidate IDs; show when no matching candidate exists.\n- Call `clips_create` with one asset or URL, clipCount, durationBounds and the chosen captionThemeId.\n- Use selection.includeIds for approved candidates; use selection.excludeIds for rejected candidates.\n- Omitted captions inherit reviewed defaults. Preserve the chosen Series; use null for explicitly standalone clips.\n- Keep createSharePage false unless public sharing is explicitly requested.\n- Create once with a stable idempotencyKey. Retry identical inputs with the same key; inspect after ambiguous responses.\n\nCompletion: one accepted batch per source with verified identifiers and requested settings.\n\n## 3. Follow and revise\n\n- Read batch.polling and follow `clips_status_get` within its delay and attempt/time limits.\n- Show the batch with `clips_get` when playback is requested; status polling keeps the current review widget mounted.\n- Deliver ready clips incrementally. Processing or QA warnings alone do not justify recreating accepted clips.\n- Use `clips_list` and `clips_inspect` for bounded state; use `clips_reselect`, `clips_repair`, `clips_export`\n or `captions_look_apply` for the identified clip and explicit requested change.\n- Selected widget clip/time context identifies the target; route precise project edits to edit-and-export-video.\n- Use `clips_recover` only for a terminal batch's missing count; retain accepted clips and rejected moments.\n\nCompletion: every clip accounted for as ready, active, requiring review or failed.\n\n## 4. Deliver and reuse\n\n- Present inline playback and ready MP4s or the ZIP. Refresh `clips_status_get` when signed links expire.\n- State the actual quality/watermark and any unresolved framing, caption or audio issues.\n- Save user-requested ratings with `video_feedback_save` for the exact completed export; preserve accepted output.\n- Draft titles, covers and platform copy from the verified source; keep invented statistics and claims out.\n- For LinkedIn posts or carousels, reuse approved source excerpts; use the existing carousel tools to render/export.\n- Organize repeat work with the existing Series and folder tools. A weekly request without configured recurrence\n remains a manual task; describe the missing source, schedule and destination instead of claiming an automation.\n- For a public review page, inspect `clip_share_get`, obtain explicit public/download choices, then call\n `clip_share_publish`. Verify the returned link. `clip_share_visibility_set` changes only the selected clip.\n- Publishing requires a supported live connection and explicit reviewed caption, destination and schedule.\n Report scheduled and published states separately; never infer attributed sales from engagement.\n- At a processing bound, return the batch ID, latest state and available continuation.\n\nCompletion: usable files or explicit active/blocked state, with every requested delivery action verified.\n\n## Account access\n\nUse existing entitlements. Explain missing credits or quota calmly, without checkout, pricing, subscriptions or upsells.\n"
}SHA-256 of public snapshot: a28e53008c307532ff3f9ea773cee8ea4a7b0e6fa48d72b4f6fc2971cd396a3f