Update to Postey

{
  "description": "Create, schedule, and manage social media posts via Postey across X, LinkedIn, Instagram, TikTok, YouTube, Threads, Bluesky, Facebook, and Pinterest. The hub: accounts, platform truth, the post lifecycle, and the shared craft layer that decides how a post is written — plus the local-file and large-upload paths the MCP server cannot reach. Content flows ship as optional packs that require this one: install `postey-video` to transcribe a video and turn it into per-platform posts, `postey-ideas` to decide what to post.\n",
  "included_files": [
    {
      "relative_path": "CHANGELOG.md",
      "size_in_bytes": 34049
    },
    {
      "relative_path": "README.md",
      "size_in_bytes": 2543
    },
    {
      "relative_path": "bootstrap-prompt.md",
      "size_in_bytes": 3159
    },
    {
      "relative_path": "capability-snapshot.json",
      "size_in_bytes": 4741
    },
    {
      "relative_path": "command-reference.md",
      "size_in_bytes": 3911
    },
    {
      "relative_path": "pack.json",
      "size_in_bytes": 1539
    },
    {
      "relative_path": "prompts.md",
      "size_in_bytes": 6726
    },
    {
      "relative_path": "references/brand-profile-template.md",
      "size_in_bytes": 3378
    },
    {
      "relative_path": "references/caption-playbook.md",
      "size_in_bytes": 4635
    },
    {
      "relative_path": "references/hook-formulas.md",
      "size_in_bytes": 2396
    },
    {
      "relative_path": "references/mcp-authentication.md",
      "size_in_bytes": 8268
    },
    {
      "relative_path": "references/mcp-workflows.md",
      "size_in_bytes": 10409
    },
    {
      "relative_path": "references/platform-archetypes.md",
      "size_in_bytes": 6758
    },
    {
      "relative_path": "references/post-structures.md",
      "size_in_bytes": 11269
    },
    {
      "relative_path": "references/thread-and-video-formats.md",
      "size_in_bytes": 8887
    },
    {
      "relative_path": "references/x-algorithm.md",
      "size_in_bytes": 2461
    },
    {
      "relative_path": "routing-guide.md",
      "size_in_bytes": 6567
    },
    {
      "relative_path": "scripts/mediaValidator.js",
      "size_in_bytes": 8124
    },
    {
      "relative_path": "scripts/postey.js",
      "size_in_bytes": 78199
    },
    {
      "relative_path": "scripts/videoUtils.js",
      "size_in_bytes": 5148
    },
    {
      "relative_path": "video-workflow.md",
      "size_in_bytes": 3256
    }
  ],
  "name": "postey",
  "skill_md_contents": "---\nname: postey\nversion: 3.2.1\n# No `platforms:` list. The platform set lives on the server and is mirrored into\n# capability-snapshot.json by scripts/refresh-capability-snapshot.js. A copy here\n# would be a fourth hand-maintained list agreeing with the other three and with\n# nothing that ships (S9.5).\ndescription: >\n  Create, schedule, and manage social media posts via Postey across X, LinkedIn,\n  Instagram, TikTok, YouTube, Threads, Bluesky, Facebook, and Pinterest. The hub:\n  accounts, platform truth, the post lifecycle, and the shared craft layer that\n  decides how a post is written — plus the local-file and large-upload paths the\n  MCP server cannot reach. Content flows ship as optional packs that require this\n  one: install `postey-video` to transcribe a video and turn it into per-platform\n  posts, `postey-ideas` to decide what to post.\nwhen_to_use: >\n  Use when asked to: draft a tweet, post to LinkedIn, create a thread, schedule\n  content, publish a post, check scheduled or published posts, upload a video or\n  image from local disk to Instagram/TikTok/YouTube, cross-post to multiple\n  platforms, manage social drafts, or any social media publishing task. Transcribing\n  a video into captions belongs to `postey-video`; deciding what to post belongs to\n  `postey-ideas`; confirming something actually went out belongs to `postey-ops`.\nallowed-tools:\n  - Bash(${CLAUDE_SKILL_DIR}/scripts/postey.js:*)\nmcp-tools:\n  resources:\n    - postey://accounts\n    - postey://teams\n    - postey://posts/{post_id}/content/{platform}\n    - postey://platform-limits\n    - postey://platforms/{platform}/rules\n    - postey://platforms/{platform}/actions\n    - postey://posts/{post_id}/analytics\n    - postey://accounts/{account_id}\n    - postey://teams/{team_id}/members\n    - postey://skill-manifest\n  tools:\n    # GENERATED from capabilities: by scripts/gen-mcp-tools.js — do not hand-edit.\n    - add_tag\n    - connect_account\n    - convert_post_content\n    - create_post\n    - delete_draft\n    - file_manager\n    - get_posts\n    - get_review_status\n    - get_schedule\n    - link_cli\n    - list_files\n    - publish_draft\n    - read_file\n    - remove_tag\n    - review_post\n    - schedule_post\n    - transcribe_video\n    - unschedule_post\n    - update_post\n    - update_schedule\n    - upload_media\n    - validate_post_content\n    # Fallbacks only: each is superseded by a postey:// resource this skill\n    # declares. Use them when the client cannot read MCP resources.\n    - get_accounts\n    - get_post_content\n  prompts:\n    - compose-post\n    - review-for-virality\n    - repurpose-content\n    - improve-post\n    - analyze-engagement\n    - generate-captions-from-transcript\n    - generate-captions-batch\n# Capability-keyed ownership. Keys are `canonical` entries from\n# capability-snapshot.json — the server's vocabulary, never raw tool names, so this\n# cannot drift into a second hand-kept list (S9.5). `owns` is exclusive: exactly one\n# skill may own a key. `reads` is shared. Contract: docs/skills-mcp-contract.md.\n#\n# Every capability the server exposes now has an owner; the unclaimed allowlist is\n# empty and check-capability-contract keeps it that way. Claiming a key this skill\n# does not actually document would defeat the coverage check.\ncapabilities:\n  owns:\n    # Accounts, platform truth, setup — the hub's operations layer\n    - account.connect\n    - account.list\n    - account.read\n    - account.tags\n    - platform.limits\n    - platform.rules\n    - platform.actions\n    - server.manifest\n    - setup.read\n    - cli.link\n    # Authoring and the post lifecycle\n    - post.create\n    - post.read\n    - post.list\n    - post.update\n    - post.delete\n    - post.convert\n    - post.review\n    - post.review.status\n    - post.validate\n    - post.tag.add\n    - post.tag.remove\n    - publish.now\n    - schedule.create\n    - schedule.read\n    - schedule.update\n    - schedule.delete\n    # Media and local files (the only capability the CLI may hold)\n    - media.upload\n    - file.list\n    - file.read\n    - file.upload\n  reads:\n    - media.transcribe\n  prompts:\n    - compose-post\n    - review-for-virality\n\n# Machine-readable routing rules (mirrors routing-guide.md; used by CI and agents).\n# Values: a single path, or \"primary > fallback\" — use the fallback only when\n# your client lacks the primary capability (cannot read MCP resources, or has\n# no CLI/shell). Paths: mcp-resource | mcp-tool | cli\nrouting:\n  read-only-state:     mcp-resource > mcp-tool  # postey://... resources; resource-blind clients use get_* read tools\n  platform-limits:     mcp-resource  # postey://platform-limits / postey://platforms/{p}/rules\n  analytics:           mcp-resource  # postey://posts/{id}/analytics\n  validation:          mcp-tool      # validate_post_content (no CLI equivalent)\n  virality-review:     mcp-tool      # review_post\n  comment-read:        mcp-tool      # get_platform_comments / get_internal_comments\n  convert-content:     mcp-tool      # convert_post_content\n  write-post:          mcp-tool      # create/update/publish/schedule/delete → MCP tools, in EVERY environment\n  local-file:          cli           # any local path → unconditional CLI (video post); the write that follows is still mcp-tool\n  video-transcription: cli > mcp-tool  # postey.js video transcribe; connector-only clients use transcribe_video\n  fallback:            mcp-tool      # unknown operations → MCP; the CLI only holds local-machine commands\n---\n\n# Postey Skill\n\nCreate, schedule, and publish social media content across multiple platforms using [Postey](https://postey.ai).\n\n## Capability Comes From the Server, Not From This File\n\n`postey://skill-manifest` describes the live surface — every tool, resource, prompt and platform\nthe server actually serves. **When what you need is not obvious, read it rather than guessing from\nthis document.** Each tool entry carries three fields that settle routing on their own:\n\n| Field | Meaning |\n|-------|---------|\n| `capability` | What the tool is *for*, as `noun.verb` (`post.create`, `account.list`) |\n| `canonical` | `true` = the intended way to reach that capability |\n| `superseded_by` | On a non-canonical tool, the URI or tool you should call instead |\n\n**The rule: reach a capability through its canonical provider.** If `superseded_by` is set, follow\nit — that field is why you do not need to parse `[FALLBACK ONLY — READ … INSTEAD]` out of a\ndescription. Where a resource and a tool serve one capability, the resource is canonical.\n\nThe one exception is a client that cannot read MCP resources. Then the superseded tool is correct\nprecisely because the canonical provider is unreachable — that is what the fallbacks are for.\n\n`capability-snapshot.json` in this directory is the same data, captured offline for the CLI and CI.\nRead the live resource when you can; the snapshot is a mirror, and a mirror can be one deploy stale.\n\n## Tool Routing — Read Before Any Tool Call\n\nTwo surfaces exist — MCP tools/resources and the CLI (`postey.js`) — and they are layers, not\nalternatives. MCP owns every read and **every write**. The CLI owns only what needs the user's\nmachine, and it has no write command: its local-file commands upload and hand back the fields for\nan MCP write. A workflow uses whichever surface owns each step.\n\nAn installed skill is not a working setup. This file loads from disk whether or not the server is\nreachable. If the Postey tools are absent from your session, stop and say so. There is no command\nhere that reaches Postey state, so looking for one wastes the user's time.\n\nSay what to do next, rather than only that you are stuck. The server address is\n`https://mcp.postey.ai/mcp`, registered natively in your own client — never behind a local\nbridge. A client that can open a browser finishes OAuth. A browserless one (CI, container, cron)\ncannot: there is no `client_credentials` grant, so it needs an MCP key (`mk_…`) sent as\n`X-API-Key`, and you cannot create that key yourself. Per-client registration commands and config\npaths: <https://raw.githubusercontent.com/posteyai/skills/main/setup.md>. The key steps:\n[references/mcp-authentication.md](references/mcp-authentication.md).\n\n### Decision Tree\n\n1. **Local file path involved** (`~/video.mp4`, `./cover.jpg`)?\n   → **CLI only** — MCP cannot access the local filesystem.\n\n2. **Video transcription** (yt-dlp + Whisper)?\n   → **`node ${CLAUDE_SKILL_DIR}/scripts/postey.js video transcribe <url>`** — preferred wherever\n   the CLI runs. Connector-only clients (no CLI) use the `transcribe_video` MCP tool instead.\n\n3. **Read-only state** (accounts, teams, post content)?\n   → **MCP resource** — fast, cached, no subprocess:\n   - Accounts → `postey://accounts`\n   - Teams → `postey://teams`\n   - Post content → `postey://posts/{id}/content/{platform}`\n   - Prefer a resource URI over the equivalent read tool (e.g. `postey://accounts` over\n     `get_accounts`) whenever your client can read MCP resources; resource-blind clients (many\n     hosted connectors) use the tools. Reads with no resource equivalent (post listings →\n     `get_posts`) always use the tool.\n\n4. **Content validation or virality review** before publishing?\n   → **MCP tools** — `validate_post_content`, `review_post` — no CLI equivalent; do not skip these in any MCP-capable session. `review_post` returns a `job_id` and runs 60-120 seconds; collect the result with `get_review_status` (by `job_id`, or `post_id` if the handle was lost), repeating while `status` is `running`.\n\n5. **All other writes** (create, update, publish, schedule, delete, tag, upload by URL)?\n   → **MCP tools, in every environment** — `create_post`, `update_post`, `publish_draft`, `schedule_post`, `delete_draft`.\n   → There is no second path. Where no MCP server is reachable the write cannot be done at all —\n   say so and stop; do not reach for a CLI command that does not exist.\n\n### Routing Table\n\n| Trigger | Tool | Reason |\n|---------|------|--------|\n| `--file <local-path>` or `--video <local-path>` | CLI only (`video post`) | MCP has no filesystem access |\n| Video transcription workflow | CLI preferred; `transcribe_video` MCP tool for connector-only clients | Local pipeline needs yt-dlp, ffmpeg, Whisper |\n| Read accounts / teams / post content | MCP resource | Cached, no subprocess overhead |\n| Validate content before posting | MCP tool | No CLI equivalent |\n| Virality review | MCP tool | No CLI equivalent |\n| Create / update / publish / schedule / delete | MCP tool | `create_post`, `update_post`, `publish_draft`, `schedule_post`, `delete_draft` |\n| Get single draft content | MCP | `postey://posts/{id}/content/{platform}`, or `get_post_content` |\n| Cursor, SDK agent, CI/CD environment | Same as above — unchanged | The environment decides whether the CLI is *available*, never who owns the operation |\n\n### Anti-Patterns\n\n- **Never** call `get_accounts` when your client can read MCP resources — read `postey://accounts` instead. Resource-blind clients (many hosted connectors) may use the tool.\n- **Never** call `upload_media` for a local file — it accepts URLs only.\n- **Never** skip `validate_post_content` / `review_post` in any MCP-capable session.\n- **Never** use CLI `drafts:create` / `drafts:publish` / `drafts:schedule` — these commands are removed; use MCP tools. The same holds in CI/CD, Cursor, Windsurf and SDK agents: without an MCP server there is no write path, not a CLI one.\n- **Never** call REST endpoints directly (e.g. `GET /accounts`) — always use MCP resources or tools.\n- **Never** guess or invent an `account_id` — always read the accounts (`postey://accounts`, or `get_accounts` for resource-blind clients) and confirm with the user.\n- **Never** run `postey.js accounts:list` — that command does not exist; read `postey://accounts` (or call `get_accounts`).\n\n---\n\n## Setup\n\n1. **MCP key** — Ask the user to create one at\n   https://app.postey.ai?settings=agents&section=advanced — that is **AI & Agents → Advanced**,\n   and the key it mints never expires and works on every plan. `?settings=api` opens Integrations\n   instead, where the plan-gated general-purpose keys live. Then:\n   ```bash\n   ${CLAUDE_SKILL_DIR}/scripts/postey.js setup\n   ```\n   Or set env var: `export POSTEY_API_KEY=your_key`\n\n2. **Requirements** — Node.js 18+. No other dependencies for the core CLI.\n\n**Config priority** (highest to lowest):\n1. `POSTEY_API_KEY` environment variable\n2. `POSTEY_AUTH_TOKEN` environment variable — a bearer token the MCP server sets when it runs this\n   CLI for an OAuth-authenticated caller. Not something you set by hand.\n3. OAuth session from `postey.js auth:login`\n4. A linked credential from `postey.js auth:link` — the CLI copying the access this\n   connection already has. This is what `setup.md` Step 5 sets up.\n5. `./.postey/config.json` (project-local) — only honoured in the directory it was created for.\n   A config that arrived by clone or copy is ignored, because a repo that commits one would\n   otherwise supply the credential and the default account silently. Re-run\n   `setup --key <key> --location local` there, or set `POSTEY_TRUST_LOCAL_CONFIG=1`.\n6. `~/.config/postey/config.json` (user-global)\n\n### When \"API key not found\" appears\n\nIf your client is already connected to the MCP server, run `postey.js auth:link --begin` and call\nthe `link_cli` tool with the code it prints — that copies this connection's access to the CLI and\nneeds no second sign-in. Otherwise tell the user to run the setup command interactively; you cannot\nrun it on their behalf, so **stop and wait**. Never run bare `setup` unattended: it prompts on\nstdin. Do not look for credentials in keychains, `.env` files, or config directories.\n\n## Account Selection\n\nBefore any write operation, Claude **must** know which account to target. Follow this sequence every time:\n\n1. **Read `postey://accounts`** — call the `get_accounts` tool only if your client cannot read\n   MCP resources (many hosted connectors cannot).\n2. **One account** → use it silently without prompting the user.\n3. **Multiple accounts** → display them and ask the user which one to use.\n4. **Pass `account_id`** to `create_post`, `schedule_post`, `publish_draft`, etc.\n\n**Account fields returned by `postey://accounts`:**\n\n| Field | Type | Notes |\n|-------|------|-------|\n| `account_id` | int | Required by all write tools |\n| `account_name` | str \\| null | Human-readable label |\n| `teams` | list[int] \\| null | Team IDs this account belongs to |\n| *one key per platform* | object \\| null | Non-null = that platform is connected |\n\nThe per-platform keys are lowercase slugs (`twitter` for X; otherwise the platform's own name).\n**Read them from the payload — do not assume the set.** This table listed seven and the server\nserved nine, so two connected platforms were invisible to the skill.\n\n**Deriving a display handle** (for showing to the user): each connected platform object carries\nits own identifier field — usually `username`, sometimes a platform-specific one (`vanity_name`\non LinkedIn, `handle` on Bluesky). Read the object and use what is there rather than assuming a\nfield name; a missing key means that platform is not connected, not that the handle is blank.\n\n**Hard rules:**\n- ✗ Never call `get_accounts` when your client can read MCP resources —\n  read `postey://accounts` instead. Resource-blind clients may use the tool.\n- ✗ Never invent or assume an `account_id` — always read the accounts (resource or tool) and confirm.\n- ✗ Never call `GET /accounts` or any REST endpoint directly — use MCP only.\n- ✗ Never run `postey.js accounts:list` — that CLI command does not exist.\n\n## Accounts & Defaults\n\n- CLI commands that act on an account take a positional `account_id` (e.g. `video post 123 --video ...`). See [command-reference.md](command-reference.md) for the full argument list.\n\n## Common Actions\n\n| User says… | Action |\n|------------|--------|\n| \"Draft a tweet about X\" | MCP `create_post` |\n| \"Post this to LinkedIn\" | MCP `create_post` with `platform=LINKEDIN` |\n| \"Post to X and LinkedIn\" (same content) | MCP `create_post` with multiple platforms |\n| \"X thread + LinkedIn post\" (different content) | MCP `create_post` → MCP `update_post` per additional platform |\n| \"What's scheduled?\" | MCP `get_posts` with `status=SCHEDULED` |\n| \"Show my recent posts\" | MCP `get_posts` with `status=PUBLISHED` |\n| \"Schedule this for tomorrow\" | MCP `create_post` then MCP `schedule_post` |\n| \"Post this now\" | MCP `create_post` then MCP `publish_draft` |\n| \"Make captions from this reel: \\<url\\>\" | `postey.js video transcribe <url>` → apply Caption Generation Guide → MCP `create_post` |\n| \"Upload video to Instagram/TikTok/YouTube\" | `postey.js video post` (local file) or `postey.js video transcribe <url>` (remote URL) |\n| User provides a video but no caption | Run `video transcribe` first → refine `suggested_captions` → `video post --text` or `create_post` |\n\n## Workflow\n\n1. **Check config**: `${CLAUDE_SKILL_DIR}/scripts/postey.js config:show`\n2. **Find account**: MCP resource `postey://accounts`\n3. **Create draft**: MCP `create_post`\n4. **Schedule or publish**: MCP `schedule_post` or `publish_draft`\n\nThe full sequences — create/validate/tag/publish, partial draft updates, repurposing, media and\nvideo path selection, tagging, and the fields you must ask the user for rather than guess — are in\n[references/mcp-workflows.md](references/mcp-workflows.md). That guidance used to be sent by the\nMCP server on every single request; it lives here now, loaded when you need it.\n\n## Working with Tags\n\nPass tag IDs via the `tags` field on MCP `create_post`. Use MCP `add_tag` to attach tags to an already-created post.\n\n## Publishing to Multiple Platforms\n\n**One `post_id` per topic** — never create separate drafts for different platforms on the same content.\n\n### Same content across platforms\n```\nmcp create_post account_id=<id> platform=X additional_platforms=[LINKEDIN] contents=[{text: \"...\"}]\n```\n\n### Different content per platform\n```\n# Step 1 — Create initial draft\nmcp create_post account_id=<id> platform=INSTAGRAM contents=[{text: \"<instagram_caption>\"}]\n# Returns post_id, e.g. 1234\n\n# Steps 2–N — Attach each additional platform (same post_id)\nmcp update_post post_id=1234 platform=LINKEDIN contents=[{text: \"<linkedin_caption>\"}]\nmcp update_post post_id=1234 platform=X contents=[{text: \"<twitter_caption>\"}]\n```\n\n## Platform Names\n\n`--platform` takes the server's uppercase slug. **Do not work from a list in this file** — this\ntable used to exist and silently drifted to seven entries while the server served nine, so the\nskill told users Facebook and Pinterest did not exist.\n\nResolve the set instead:\n\n- **Which platforms exist** — `postey://platform-limits`, or `capability-snapshot.json` in this\n  skill directory (generated from the server; the CLI reads the same file).\n- **Per-platform rules** — `postey://platforms/{platform}/rules` for character limits, counting\n  rules, threading and banned words. Never hardcode a limit; they change per platform.\n- **Which platforms this account can actually post to** — read `postey://accounts` and use the\n  connection status. A platform existing on the server does not mean it is connected here.\n\n## Direct Video Posting\n\nUse `video post` when you have a caption ready and want the video (and its cover) uploaded in one\ncommand (no transcription). It returns `media_urls`, `cover_url` and the rest of the fields for MCP\n`create_post` — it does not create the draft itself, and it rejects `--publish-now` / `--schedule`\nbecause publishing and scheduling are MCP's.\n\n**No caption yet?** Run `video transcribe` first — it returns a transcript and `suggested_captions` per platform. Refine those captions (see [prompts.md](prompts.md)) then pass the result to `video post --text` or `create_post`. Never paste a raw transcript as a caption.\n\n**Requires:** `ffmpeg` on PATH for Instagram cover thumbnail extraction.\n\n```bash\n${CLAUDE_SKILL_DIR}/scripts/postey.js video post <account_id> \\\n  --video <local_path_or_https_url> \\\n  --text \"<caption>\" \\\n  --platforms INSTAGRAM,LINKEDIN,X \\\n  [--cover-time <seconds>]   # default: 3\n  [--title \"Draft title\"]\n```\n\n| Platform | Video attached | Cover thumbnail |\n|----------|---------------|-----------------|\n| `INSTAGRAM` | Yes (Reel) | Yes — ffmpeg frame extraction |\n| All others | No | No |\n\n## Video → Captions → Cross-Post\n\nTranscription is `postey-video`'s — install that pack for it. Uploading a video or image from local\ndisk is this skill's: see [video-workflow.md](video-workflow.md).\nFor platform-specific caption rules, see [prompts.md](prompts.md).\n\n## Content Flows\n\nThis skill includes four guided content workflows. Offer them when the user connects for the\nfirst time, asks what you can do, or gives an open-ended content request. Load the flow's\nreference file only when the user picks it; never install or load all of them up front.\n\nHouse rules for every flow (non-negotiable):\n\n1. Know the accounts first, every session: read `postey://accounts`, or call `get_accounts` if\n   your client cannot read MCP resources. Connected platforms are read, never assumed.\n2. Everything is created as a DRAFT. Publishing needs the user's explicit instruction, and\n   **scheduling counts as publishing** (a scheduled post publishes itself): propose times, call\n   `schedule_post` only after the user approves both content and times, with times at least\n   10 minutes in the future in UTC ISO-8601.\n3. Every platform gets its own hand-crafted caption. One idea, many voices. Use the documented\n   per-platform sequence (\"Publishing to Multiple Platforms\" above): `create_post` for the primary\n   platform with its caption, then one `update_post` per remaining platform with that platform's\n   caption — same `post_id` throughout.\n4. Verify each platform after creating — read `postey://posts/{id}/content/{platform}` (or call\n   `get_post_content` if your client cannot read resources) — and run\n   `validate_post_content` per platform, then fix before presenting.\n5. End every flow by giving the user the draft's share link.\n6. Tag agent-created posts: an agent tag (default `Agent`, ask the user once if they prefer\n   another name) plus 2 or 3 topic tags. `add_tag` is get-or-create by exact name, so reusing\n   the same spelling never creates a duplicate — keep tag names consistent across sessions and\n   reuse the tag names visible on recent posts (`get_posts` returns each post's tags) instead of\n   inventing near-duplicates. `remove_tag` undoes a mis-tag.\n\n**Ships in** names the skill that carries each flow. A flow whose pack is not installed is not\navailable — say so and offer the ones that are, rather than improvising the flow from memory. CI\n(`scripts/check-pack-discovery.js`) fails if this table advertises a pack that does not exist.\n\n| Flow | The user says something like | Ships in | Load |\n|------|------------------------------|----------|------|\n| Brand voice | \"Learn my voice\", \"write like me\", a handle or website | `postey-voice` | that pack's own flow file |\n| Video everywhere | a video URL, \"post this video everywhere\" | `postey-video` | that pack's own flow file |\n| Trends | \"what should I post today?\", \"find something trending\" | `postey-ideas` | that pack's own flow file |\n| Idea to posts | one rough idea, \"turn this into posts\" | `postey-ideas` | that pack's own flow file |\n\n**The craft layer always ships here**, in the hub, because every flow cites it — wherever the flow\nitself lives: [references/caption-playbook.md](references/caption-playbook.md) (universal rules and\npre-upload checklist), [references/platform-archetypes.md](references/platform-archetypes.md),\n[references/post-structures.md](references/post-structures.md) (the 18 structures, each with the\ncondition that selects it and the way it fails — read this when choosing a shape, before drafting),\n[references/hook-formulas.md](references/hook-formulas.md), [references/x-algorithm.md](references/x-algorithm.md),\n[references/thread-and-video-formats.md](references/thread-and-video-formats.md), and\n[references/brand-profile-template.md](references/brand-profile-template.md) (the schema for the\nper-brand profile every flow reads before drafting).\n\nFirst-run greeting: after verifying accounts, offer the flows this installation actually has in one\nshort list and run whichever the user picks. Two minutes to a share link is the goal.\n\n## Automation Guidelines\n\n- No duplicate content across multiple accounts\n- No unsolicited automated replies\n- No trending manipulation or fake engagement\n- Respect API rate limits\n- **Never publish or schedule without the user's explicit yes in the current turn.** Scheduling\n  counts as publishing, because a scheduled post publishes itself. \"Post this now\" asks for a\n  draft you then show them — it approves the intent, never text they have not seen. Show the\n  exact per-platform copy and wait. Publishing is irreversible and public; drafts are private.\n\n## Tips\n\n- Thread creation: use `---` on its own line to split into multiple posts\n- Scheduling: ISO 8601 UTC strings on MCP `schedule_post` — the CLI has no scheduling flag\n- Draft titles: `--title` on `video post` is for internal organization, not posted publicly\n\n## Reference\n\n- MCP workflow sequencing, media/video path choice, tagging, what to ask before you guess:\n  [references/mcp-workflows.md](references/mcp-workflows.md)\n- OAuth scopes, the MCP-key path and the agent-token mint endpoints:\n  [references/mcp-authentication.md](references/mcp-authentication.md)\n- Connecting the server itself — address, per-client registration, config paths:\n  <https://raw.githubusercontent.com/posteyai/skills/main/setup.md>\n- Full command reference: [command-reference.md](command-reference.md)\n- Video transcription workflow: [video-workflow.md](video-workflow.md)\n- Platform caption templates: [prompts.md](prompts.md)\n- Routing rules (extended): [routing-guide.md](routing-guide.md)\n- Content flows and playbooks: [references/](references/) (see Content Flows above)\n- Pack manifest for fetch-based install: [pack.json](pack.json)\n- One-paste agent setup: [bootstrap-prompt.md](bootstrap-prompt.md)\n"
}