[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6M9FV9M49465ERDXBNDJ5P9":3,"skill-same:01M6M9FV9M49465ERDXBNDJ5P9":69},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M6M9FV9M49465ERDXBNDJ5P9","autonomous-loop",null,"How Cavekit's autonomous execution loop works — state machine, stop hook,\ncompletion sentinel, lock, budgets, iteration cap. Read this skill any time\nyou are about to run \u002Fck:make, debug a stuck session, or write a new command\nthat needs the loop. Trigger phrases: \"how does the loop work\", \"stop hook\",\n\"autonomous\", \"completion sentinel\", \"why is the session looping\".","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1559,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJuliusBrussee\u002Fblueprint\u002Fskills\u002Fautonomous-loop\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"autonomous loop","loop","autonomous","stop","new","state machine","lock","you","hook","make","iteration","time","cap","run","write","read","command","work","why","how","sentinel","2026-11-10 10:12:30",false,"---\nname: autonomous-loop\ndescription: |\n  How Cavekit's autonomous execution loop works — state machine, stop hook,\n  completion sentinel, lock, budgets, iteration cap. Read this skill any time\n  you are about to run \u002Fck:make, debug a stuck session, or write a new command\n  that needs the loop. Trigger phrases: \"how does the loop work\", \"stop hook\",\n  \"autonomous\", \"completion sentinel\", \"why is the session looping\".\n---\n\n# Autonomous Loop\n\nThe loop lets a single `\u002Fck:make` invocation run dozens of agent iterations\nwithout user intervention, while still respecting per-task budgets, session\nbudgets, and explicit user-approval gates.\n\n## Architecture\n\n```\n┌─────────────────┐  Stop event   ┌────────────────────┐\n│  Claude Code    │──────────────▶│   stop-hook.sh     │\n│   session       │               │  (.cavekit\u002Floop    │\n└─────────────────┘               │   active?)         │\n        ▲                         └─────────┬──────────┘\n        │                                   │ route()\n        │ next prompt injected              ▼\n        │                         ┌────────────────────┐\n        │                         │ cavekit-tools.cjs  │\n        │                         │  routeDecision()   │\n        │                         │  + status-block    │\n        │                         │  + backprop-       │\n        │                         │    directive       │\n        │                         └─────────┬──────────┘\n        │                                   │\n        └───────── {decision:\"block\",       │\n                    reason:\u003Cnext prompt>} ◀─┘\n```\n\n## Files the loop touches\n\nAll under `\u003Cproject>\u002F.cavekit\u002F`:\n\n| File                            | Writer                | Purpose                                      |\n|---------------------------------|-----------------------|----------------------------------------------|\n| `.loop.json`                    | setup-loop            | Sentinel; stop-hook no-ops without it.       |\n| `.loop.lock`                    | stop-hook (heartbeat) | Single-writer lock. PID + hostname + ts.     |\n| `state.md`                      | cavekit-tools         | `phase`, `current_task`, `iteration`.        |\n| `token-ledger.json`             | token-monitor hook    | Session + per-task token tallies.            |\n| `task-status.json`              | commands              | Authoritative task registry.                 |\n| `.progress.json`                | progress-tracker      | Zero-context UI snapshot.                    |\n| `.auto-backprop-pending.json`   | auto-backprop hook    | Flag file from failed tests.                 |\n| `history\u002Fbackprop-log.md`       | backprop skill        | Append-only trace log.                       |\n| `capabilities.json`             | discover command      | MCP + CLI tool detection.                    |\n\n## Lifecycle\n\n1. **Setup** — `\u002Fck:make` calls:\n   ```\n   node \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcavekit-tools.cjs\" setup-loop\n   ```\n   This writes `.loop.json` (activating the stop hook) and resets `state.md`.\n\n2. **Work** — the agent does one wave of task execution per iteration.\n\n3. **Stop fires** — Claude Code's Stop event triggers `stop-hook.sh`. The hook:\n   - reads stdin for `session_id` and `transcript_path`\n   - acquires \u002F refreshes the lock\n   - scans the last 20 transcript lines for `\u003Cpromise>CAVEKIT COMPLETE\u003C\u002Fpromise>`\n   - if sentinel found → teardown + exit silently\n   - else → asks `routeDecision()` for the next prompt\n   - prepends the backprop directive if the flag file exists\n   - returns `{\"decision\":\"block\",\"reason\":\u003Cnext prompt>}`\n\n4. **Repeat** — Claude Code treats `decision:block` + `reason:...` as a new\n   user message, so the session continues.\n\n5. **Teardown** — one of:\n   - completion sentinel detected\n   - max-iterations reached (`CAVEKIT_MAX_ITERATIONS`)\n   - session budget exhausted (`CAVEKIT_BUDGET_EXHAUSTED`)\n   - lock stolen by another session (`CAVEKIT_LOCK_CONFLICT`)\n   - user interrupt (hook returns no output; session stops normally)\n\n## Completion sentinel\n\nTo end the loop cleanly, emit exactly:\n\n```\n\u003Cpromise>CAVEKIT COMPLETE\u003C\u002Fpromise>\n```\n\nThe hook searches for this literal in the last 20 transcript lines. Put it on\nits own line at the very end of the final message. Do not wrap it in code\nfences or paraphrase it — the search is a literal substring match.\n\n## Terminal sentinels\n\nWhen `routeDecision()` cannot safely continue, it returns one of these\nstrings instead of a prompt:\n\n| Sentinel                     | Meaning                               |\n|------------------------------|---------------------------------------|\n| `CAVEKIT_LOOP_DONE`          | All tasks complete. Hook exits silent.|\n| `CAVEKIT_MAX_ITERATIONS`     | Iteration cap hit. Loop halted.       |\n| `CAVEKIT_BUDGET_EXHAUSTED`   | Session budget exhausted.             |\n| `CAVEKIT_LOCK_CONFLICT`      | Another session owns the lock.        |\n\nThe hook translates each into a short user-facing message before returning.\n\n## Lock protocol\n\nThe lock is a JSON file (`.loop.lock`) with `{owner, pid, host, heartbeat_at}`.\n\n- **Owner tag**: `session:\u003Csession_id>`.\n- **Heartbeat**: every Stop invocation refreshes `heartbeat_at`.\n- **Stale**: > 5 minutes since last heartbeat. A new session may steal a stale\n  lock.\n- **Conflict**: non-owner with fresh lock → returns `CAVEKIT_LOCK_CONFLICT`.\n\nNever delete `.loop.lock` while a session might be active. Use\n`cavekit-tools release-lock --owner \u003Ctag>` instead.\n\n## Debugging a stuck loop\n\n```bash\n# Inspect current state\nnode \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcavekit-tools.cjs\" status\n\n# Who holds the lock?\ncat .cavekit\u002F.loop.lock\n\n# What would the router do right now?\nnode \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcavekit-tools.cjs\" route\n\n# Drop the loop entirely (safe after a crash)\nnode \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcavekit-tools.cjs\" teardown-loop\n```\n\nTurn on debug logging by exporting `CAVEKIT_DEBUG=1`. The hook will write to\n`.cavekit\u002F.debug.log`.\n\n## What not to do\n\n- Do **not** hand-edit `state.md`'s `phase` field while a loop is active. The\n  hook assumes single-writer semantics and will overwrite you.\n- Do **not** set your own stop hook that also blocks. Multiple blocking hooks\n  race, and Claude Code picks one arbitrarily.\n- Do **not** emit the completion sentinel unless every task in the registry is\n  truly `complete`. The hook trusts the sentinel and tears down immediately.\n","# Autonomous Loop\n\nThe loop lets a single `\u002Fck:make` invocation run dozens of agent iterations\nwithout user intervention, while still respecting per-task budgets, session\nbudgets, and explicit user-approval gates.\n\n## Architecture\n\n```\n┌─────────────────┐  Stop event   ┌────────────────────┐\n│  Claude Code    │──────────────▶│   stop-hook.sh     │\n│   session       │               │  (.cavekit\u002Floop    │\n└─────────────────┘               │   active?)         │\n        ▲                         └─────────┬──────────┘\n        │                                   │ route()\n        │ next prompt injected              ▼\n        │                         ┌────────────────────┐\n        │                         │ cavekit-tools.cjs  │\n        │                         │  routeDecision()   │\n        │                         │  + status-block    │\n        │                         │  + backprop-       │\n        │                         │    directive       │\n        │                         └─────────┬──────────┘\n        │                                   │\n        └───────── {decision:\"block\",       │\n                    reason:\u003Cnext prompt>} ◀─┘\n```\n\n## Files the loop touches\n\nAll under `\u003Cproject>\u002F.cavekit\u002F`:\n\n| File                            | Writer                | Purpose                                      |\n|---------------------------------|-----------------------|----------------------------------------------|\n| `.loop.json`                    | setup-loop            | Sentinel; stop-hook no-ops without it.       |\n| `.loop.lock`                    | stop-hook (heartbeat) | Single-writer lock. PID + hostname + ts.     |\n| `state.md`                      | cavekit-tools         | `phase`, `current_task`, `iteration`.        |\n| `token-ledger.json`             | token-monitor hook    | Session + per-task token tallies.            |\n| `task-status.json`              | commands              | Authoritative task registry.                 |\n| `.progress.json`                | progress-tracker      | Zero-context UI snapshot.                    |\n| `.auto-backprop-pending.json`   | auto-backprop hook    | Flag file from failed tests.                 |\n| `history\u002Fbackprop-log.md`       | backprop skill        | Append-only trace log.                       |\n| `capabilities.json`             | discover command      | MCP + CLI tool detection.                    |\n\n## Lifecycle\n\n1. **Setup** — `\u002Fck:make` calls:\n   ```\n   node \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcavekit-tools.cjs\" setup-loop\n   ```\n   This writes `.loop.json` (activating the stop hook) and resets `state.md`.\n\n2. **Work** — the agent does one wave of task execution per iteration.\n\n3. **Stop fires** — Claude Code's Stop event triggers `stop-hook.sh`. The hook:\n   - reads stdin for `session_id` and `transcript_path`\n   - acquires \u002F refreshes the lock\n   - scans the last 20 transcript lines for `\u003Cpromise>CAVEKIT COMPLETE\u003C\u002Fpromise>`\n   - if sentinel found → teardown + exit silently\n   - else → asks `routeDecision()` for the next prompt\n   - prepends the backprop directive if the flag file exists\n   - returns `{\"decision\":\"block\",\"reason\":\u003Cnext prompt>}`\n\n4. **Repeat** — Claude Code treats `decision:block` + `reason:...` as a new\n   user message, so the session continues.\n\n5. **Teardown** — one of:\n   - completion sentinel detected\n   - max-iterations reached (`CAVEKIT_MAX_ITERATIONS`)\n   - session budget exhausted (`CAVEKIT_BUDGET_EXHAUSTED`)\n   - lock stolen by another session (`CAVEKIT_LOCK_CONFLICT`)\n   - user interrupt (hook returns no output; session stops normally)\n\n## Completion sentinel\n\nTo end the loop cleanly, emit exactly:\n\n```\n\u003Cpromise>CAVEKIT COMPLETE\u003C\u002Fpromise>\n```\n\nThe hook searches for this literal in the last 20 transcript lines. Put it on\nits own line at the very end of the final message. Do not wrap it in code\nfences or paraphrase it — the search is a literal substring match.\n\n## Terminal sentinels\n\nWhen `routeDecision()` cannot safely continue, it returns one of these\nstrings instead of a prompt:\n\n| Sentinel                     | Meaning                               |\n|------------------------------|---------------------------------------|\n| `CAVEKIT_LOOP_DONE`          | All tasks complete. Hook exits silent.|\n| `CAVEKIT_MAX_ITERATIONS`     | Iteration cap hit. Loop halted.       |\n| `CAVEKIT_BUDGET_EXHAUSTED`   | Session budget exhausted.             |\n| `CAVEKIT_LOCK_CONFLICT`      | Another session owns the lock.        |\n\nThe hook translates each into a short user-facing message before returning.\n\n## Lock protocol\n\nThe lock is a JSON file (`.loop.lock`) with `{owner, pid, host, heartbeat_at}`.\n\n- **Owner tag**: `session:\u003Csession_id>`.\n- **Heartbeat**: every Stop invocation refreshes `heartbeat_at`.\n- **Stale**: > 5 minutes since last heartbeat. A new session may steal a stale\n  lock.\n- **Conflict**: non-owner with fresh lock → returns `CAVEKIT_LOCK_CONFLICT`.\n\nNever delete `.loop.lock` while a session might be active. Use\n`cavekit-tools release-lock --owner \u003Ctag>` instead.\n\n## Debugging a stuck loop\n\n```bash\n# Inspect current state\nnode \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcavekit-tools.cjs\" status\n\n# Who holds the lock?\ncat .cavekit\u002F.loop.lock\n\n# What would the router do right now?\nnode \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcavekit-tools.cjs\" route\n\n# Drop the loop entirely (safe after a crash)\nnode \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcavekit-tools.cjs\" teardown-loop\n```\n\nTurn on debug logging by exporting `CAVEKIT_DEBUG=1`. The hook will write to\n`.cavekit\u002F.debug.log`.\n\n## What not to do\n\n- Do **not** hand-edit `state.md`'s `phase` field while a loop is active. The\n  hook assumes single-writer semantics and will overwrite you.\n- Do **not** set your own stop hook that also blocks. Multiple blocking hooks\n  race, and Claude Code picks one arbitrarily.\n- Do **not** emit the completion sentinel unless every task in the registry is\n  truly `complete`. The hook trusts the sentinel and tears down immediately.\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002FJuliusBrussee\u002Fblueprint\u002Fskills\u002Fautonomous-loop",474,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-11 14:40:14",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill autonomous-loop",{"tool":61,"command":62},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill autonomous-loop",{"tool":64,"command":65},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill autonomous-loop","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJuliusBrussee\u002Fblueprint\u002Fskills\u002Fautonomous-loop\u002FSKILL.md",true,[],[70,78,85,92,118,143],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":77},"01M746ZWACVKMZ1BJXJZHYJSSX","migrate-to-e2e","Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for \u002Fmigrate-to-e2e, \"migrate our tests to e2e\", \"port these Maestro flows\", \"move our TesterArmy tests\", or when a project has an e2e config and an older suite still running.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fmigrate-to-e2e\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":77},"01M746ZPTAX1Q0FBKAB1CYND7E","e2e","Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fe2e\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":77},"01M746ZJN784HVHMDP9MQGCSGG","create-verification-skill","Generate a project-local verify-\u003Capp> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for \u002Fcreate-verification-skill, \"make a verification skill for this repo\", or when a project has no scripted way to prove UI behavior.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fcreate-verification-skill\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":40},"01M716A6ETNB9B1SQ3GXZC75VR","deja-search","deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-search\u002FSKILL.md",[],[99,100,101,102,103,104,105,106,107,108,109,110,26,111,112,113,114,115,116,117],"search","deja search","never","error","ready","memory","re","decide","fix","design","debugging","when","done","reviewer","io","change","cli","merge","past",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":40},"01M716A3J2W5SENSE9VGMXB375","deja-reflect","End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-reflect\u002FSKILL.md",[],[125,126,127,113,128,129,130,131,132,133,134,135,136,137,104,138,139,140,141,142],"deja reflect","reflect","review","with","record","github","next","https","node","Rules","decisions","brew","remember","project rules","project","session","end","reflection",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":160,"publishedAt":40},"01M715T3RR4BAYSR57HPPTJ0PF","revid","Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftmakersas\u002Frevid-skills\u002Fskills\u002Frevid\u002FSKILL.md",[149,154,157],{"categoryNo":150,"categoryName":151,"taxonomyType":152,"taxonomyTypeDesc":153},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":155,"categoryName":156,"taxonomyType":152,"taxonomyTypeDesc":153},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":158,"categoryName":159,"taxonomyType":152,"taxonomyTypeDesc":153},"01JBSEEDCAT000000000000010","后端与接口",[145,161,162,163,164,165,166,139,167,105,168,169,170,171,110,172,173,174,175,176],"URL","Video","short-form","standalone","PDF","viral","tiktok","short","social","MCP","song","image","mcp server","schedule","api","publish"]