[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MG4Y3JGSKCJ4S2SWFQ0TQW":3,"skill-same:01M6MG4Y3JGSKCJ4S2SWFQ0TQW":70},{"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":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":51,"ownerHtmlUrl":52,"ownerBlogUrl":53,"ownerDescription":54,"updatedAt":55,"install":56,"resources":69},"01M6MG4Y3JGSKCJ4S2SWFQ0TQW","book-edit",null,"Phase 4: Editing. Fact-check (nonfiction), assessment, developmental edit, line edit, copy edit, proofread, then a cold read by simulated readers that issues the readiness verdict. Rewrites the manuscript; does not only file reports.","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\u002Fepicsagas\u002FVelith\u002Fskills\u002Fbook-edit\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"book edit","book","edit","project","phase","manuscript","cold","verdict","line","readiness","developmental","stage","assessment","proofread","reports","only","read","check","editing","file","issues","2026-11-10 10:12:30",false,"---\nname: book-edit\ndescription: \"Phase 4: Editing. Fact-check (nonfiction), assessment, developmental edit, line edit, copy edit, proofread, then a cold read by simulated readers that issues the readiness verdict. Rewrites the manuscript; does not only file reports.\"\nargument-hint: \"[project-dir] [stage 0-6|all] [chapter-file]\"\n---\n\n# Phase 4: Editing\n\nGoal: a manuscript that passes a cold read by its target readers. Editing here means rewriting. Each stage snapshots the drafts, changes them, and files a report of what changed and why.\n\nRead `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Floom\u002Fquality-bar.md`. Every stage reads the whole manuscript, `STYLE.md` (voice lock passages), `bible.md`, and the genre skill.\n\nRefuse to run if any outlined chapter is missing. Editing an incomplete book fixes the wrong things.\n\n## Stages\n\n| # | Stage | Who | Rewrites? | Report |\n|---|-------|-----|-----------|--------|\n| 0 | Fact check (nonfiction, technical, academic, and fiction with real-world claims) | `fact-checker` | Yes, removes or corrects unverifiable claims | `edits\u002F00-fact-check.md` |\n| 1 | Editorial assessment | skill (you) | No | `edits\u002F01-assessment.md` |\n| 2 | Developmental edit | skill + `chapter-writer` for rewrites, `continuity-editor` after | Yes, chapter-level | `edits\u002F02-developmental.md` |\n| 3 | Line edit | `style-doctor` then skill | Yes, paragraph and sentence level | `edits\u002F03-line-edit.md` |\n| 4 | Copy edit | skill | Yes, mechanical | `edits\u002F04-copy-edit.md` |\n| 5 | Proofread | skill | Yes, final | `edits\u002F05-proofread.md` |\n| 6 | Readiness | `beta-reader` | No | `edits\u002F06-readiness-report.md` (also `edits\u002Freadiness-report.md`) |\n\nBefore every rewriting stage: `node ${CLAUDE_PLUGIN_ROOT}\u002Fvelith.mjs snapshot [project-dir] stage{N}`.\n\nAfter each stage: update chapter frontmatter `status: edited`, bump `revision`, run `scan`.\n\n### Stage 0 — Fact check\n\nInvoke `fact-checker`. It builds a claim ledger, verifies against `sources\u002F` and the web, and edits drafts to remove or correct what cannot be verified. It also reconciles every figure's labels and plotted values with the text and the data files in `sources\u002F`. A claim that would embarrass the author in a review is a Critical. Fiction runs this stage only if the bible flags real-world claims (real places, real history, real science). Stage 0 runs before anything else because a developmental edit built on a false claim is wasted.\n\n### Stage 1 — Editorial assessment\n\nRead the whole book once at reading speed (cold-read protocol). Produce the macro diagnosis:\n\n- Where the book delivers its promise and where it does not (against `PRD.md` reader promise)\n- Pacing map: per chapter, engagement 1-5 and why; identify the sag\n- Structural redundancies and gaps (two chapters doing one job; a job nobody does)\n- Proportion: is the setup too long, the ending too fast\n- Voice consistency across chapters (quote a line from chapter 2 and one from chapter 18 side by side)\n- Five-axis score for the whole manuscript\n- Ordered list of developmental interventions with expected impact\n\nNo rewriting in this stage. The report is the plan for stage 2.\n\n### Stage 2 — Developmental edit\n\nExecute the stage 1 plan. Interventions, in order of scale:\n\n- **Restructure** (reorder, merge, split, cut chapters): requires author approval. Present the proposal with rationale and the concrete new chapter list. Required stop.\n- **Rewrite chapter** (purpose unchanged, execution replaced): invoke `chapter-writer` with the assessment findings for that chapter as extra input and `--force`. It reads the whole book, so it will match the voice lock.\n- **Add or remove scenes\u002Fsections** within a chapter: do it directly, in the voice, then update the bible ledger.\n- **Deepen** (a character who acts without wanting; an argument missing its strongest objection): targeted rewrites of the passages, not the chapter.\n\nAfter all interventions, invoke `continuity-editor` on the full manuscript. Report: what changed per chapter, what was left as-is and why, and the new pacing map.\n\n### Stage 3 — Line edit\n\nInvoke `style-doctor`. It measures (`velith.mjs metrics`), reads, rewrites paragraphs and sentences in place, and reports before\u002Fafter with metrics. Then do your own line pass on anything it flagged as \"author decision\": sentences whose problem is meaning, not style.\n\nLine-edit priorities: rhythm uniformity, the structural tells, emotional tells, dialogue that answers, figurative density against the fingerprint, paragraphs that end on a punch, Korean 번역투 and ~것이다 endings, ~5% trim of every chapter by cutting what the reader already knows.\n\n### Stage 4 — Copy edit\n\nMechanical consistency against `bible.md` and `STYLE.md`: spelling of names and terms, hyphenation, number style, capitalization, quotation marks, 띄어쓰기, tense agreement, heading levels, code formatting (technical), citation format (academic), cross-references that point to the right chapter, figure numbering and caption format, every figure referenced in the text before it appears. Run `node ${CLAUDE_PLUGIN_ROOT}\u002Fvelith.mjs images check [project-dir]` and fix unresolved references and missing alt text. Fix directly. Report only counts by category plus anything ambiguous for the author.\n\n### Stage 5 — Proofread\n\nFinal pass on the revised text: typos, doubled words, orphaned formatting, markdown artifacts, missing scene breaks, dialogue punctuation, image references that resolve. Fix directly. Then set every chapter `status: final`.\n\n### Stage 6 — Readiness\n\nInvoke `beta-reader`. It cold-reads the whole manuscript as three target readers and one genre expert, writes `edits\u002F06-readiness-report.md` with per-chapter engagement, put-down points, confusion log, AI-feel log with quotes, comp comparison, five-axis scores, and a verdict.\n\n- `verdict: PASS` — write `edits\u002Feditorial-report.md` summarizing all stages and the scores. Phase complete.\n- `verdict: REVISE` — the report includes a prioritized fix list. Apply the fixes (stage 2 or 3 interventions as appropriate), then rerun stage 6. Maximum two loops, then present the report to the author with the remaining issues and ask whether to override or continue. Required stop.\n\nCopy the final report to `edits\u002Freadiness-report.md` (the router and dashboard read this path).\n\n## Running a single stage or chapter\n\n`\u002Fbook-edit 3` runs only the line edit. `\u002Fbook-edit 3 drafts\u002Fch07-x.md` line-edits one chapter (still with full-book context). Snapshots and reports are still written.\n\n## Gate\n\n`edits\u002Freadiness-report.md` has `verdict: PASS` (or an author override recorded in `edits\u002Feditorial-report.md`). All chapters `status: final`. Stage reports 01-06 exist (00 for nonfiction). No unresolved Critical issues in the last continuity or fact-check report.\n\n## Post-completion\n\n```bash\nnode ${CLAUDE_PLUGIN_ROOT}\u002Fvelith.mjs scan [project-dir]\n```\n","# Phase 4: Editing\n\nGoal: a manuscript that passes a cold read by its target readers. Editing here means rewriting. Each stage snapshots the drafts, changes them, and files a report of what changed and why.\n\nRead `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Floom\u002Fquality-bar.md`. Every stage reads the whole manuscript, `STYLE.md` (voice lock passages), `bible.md`, and the genre skill.\n\nRefuse to run if any outlined chapter is missing. Editing an incomplete book fixes the wrong things.\n\n## Stages\n\n| # | Stage | Who | Rewrites? | Report |\n|---|-------|-----|-----------|--------|\n| 0 | Fact check (nonfiction, technical, academic, and fiction with real-world claims) | `fact-checker` | Yes, removes or corrects unverifiable claims | `edits\u002F00-fact-check.md` |\n| 1 | Editorial assessment | skill (you) | No | `edits\u002F01-assessment.md` |\n| 2 | Developmental edit | skill + `chapter-writer` for rewrites, `continuity-editor` after | Yes, chapter-level | `edits\u002F02-developmental.md` |\n| 3 | Line edit | `style-doctor` then skill | Yes, paragraph and sentence level | `edits\u002F03-line-edit.md` |\n| 4 | Copy edit | skill | Yes, mechanical | `edits\u002F04-copy-edit.md` |\n| 5 | Proofread | skill | Yes, final | `edits\u002F05-proofread.md` |\n| 6 | Readiness | `beta-reader` | No | `edits\u002F06-readiness-report.md` (also `edits\u002Freadiness-report.md`) |\n\nBefore every rewriting stage: `node ${CLAUDE_PLUGIN_ROOT}\u002Fvelith.mjs snapshot [project-dir] stage{N}`.\n\nAfter each stage: update chapter frontmatter `status: edited`, bump `revision`, run `scan`.\n\n### Stage 0 — Fact check\n\nInvoke `fact-checker`. It builds a claim ledger, verifies against `sources\u002F` and the web, and edits drafts to remove or correct what cannot be verified. It also reconciles every figure's labels and plotted values with the text and the data files in `sources\u002F`. A claim that would embarrass the author in a review is a Critical. Fiction runs this stage only if the bible flags real-world claims (real places, real history, real science). Stage 0 runs before anything else because a developmental edit built on a false claim is wasted.\n\n### Stage 1 — Editorial assessment\n\nRead the whole book once at reading speed (cold-read protocol). Produce the macro diagnosis:\n\n- Where the book delivers its promise and where it does not (against `PRD.md` reader promise)\n- Pacing map: per chapter, engagement 1-5 and why; identify the sag\n- Structural redundancies and gaps (two chapters doing one job; a job nobody does)\n- Proportion: is the setup too long, the ending too fast\n- Voice consistency across chapters (quote a line from chapter 2 and one from chapter 18 side by side)\n- Five-axis score for the whole manuscript\n- Ordered list of developmental interventions with expected impact\n\nNo rewriting in this stage. The report is the plan for stage 2.\n\n### Stage 2 — Developmental edit\n\nExecute the stage 1 plan. Interventions, in order of scale:\n\n- **Restructure** (reorder, merge, split, cut chapters): requires author approval. Present the proposal with rationale and the concrete new chapter list. Required stop.\n- **Rewrite chapter** (purpose unchanged, execution replaced): invoke `chapter-writer` with the assessment findings for that chapter as extra input and `--force`. It reads the whole book, so it will match the voice lock.\n- **Add or remove scenes\u002Fsections** within a chapter: do it directly, in the voice, then update the bible ledger.\n- **Deepen** (a character who acts without wanting; an argument missing its strongest objection): targeted rewrites of the passages, not the chapter.\n\nAfter all interventions, invoke `continuity-editor` on the full manuscript. Report: what changed per chapter, what was left as-is and why, and the new pacing map.\n\n### Stage 3 — Line edit\n\nInvoke `style-doctor`. It measures (`velith.mjs metrics`), reads, rewrites paragraphs and sentences in place, and reports before\u002Fafter with metrics. Then do your own line pass on anything it flagged as \"author decision\": sentences whose problem is meaning, not style.\n\nLine-edit priorities: rhythm uniformity, the structural tells, emotional tells, dialogue that answers, figurative density against the fingerprint, paragraphs that end on a punch, Korean 번역투 and ~것이다 endings, ~5% trim of every chapter by cutting what the reader already knows.\n\n### Stage 4 — Copy edit\n\nMechanical consistency against `bible.md` and `STYLE.md`: spelling of names and terms, hyphenation, number style, capitalization, quotation marks, 띄어쓰기, tense agreement, heading levels, code formatting (technical), citation format (academic), cross-references that point to the right chapter, figure numbering and caption format, every figure referenced in the text before it appears. Run `node ${CLAUDE_PLUGIN_ROOT}\u002Fvelith.mjs images check [project-dir]` and fix unresolved references and missing alt text. Fix directly. Report only counts by category plus anything ambiguous for the author.\n\n### Stage 5 — Proofread\n\nFinal pass on the revised text: typos, doubled words, orphaned formatting, markdown artifacts, missing scene breaks, dialogue punctuation, image references that resolve. Fix directly. Then set every chapter `status: final`.\n\n### Stage 6 — Readiness\n\nInvoke `beta-reader`. It cold-reads the whole manuscript as three target readers and one genre expert, writes `edits\u002F06-readiness-report.md` with per-chapter engagement, put-down points, confusion log, AI-feel log with quotes, comp comparison, five-axis scores, and a verdict.\n\n- `verdict: PASS` — write `edits\u002Feditorial-report.md` summarizing all stages and the scores. Phase complete.\n- `verdict: REVISE` — the report includes a prioritized fix list. Apply the fixes (stage 2 or 3 interventions as appropriate), then rerun stage 6. Maximum two loops, then present the report to the author with the remaining issues and ask whether to override or continue. Required stop.\n\nCopy the final report to `edits\u002Freadiness-report.md` (the router and dashboard read this path).\n\n## Running a single stage or chapter\n\n`\u002Fbook-edit 3` runs only the line edit. `\u002Fbook-edit 3 drafts\u002Fch07-x.md` line-edits one chapter (still with full-book context). Snapshots and reports are still written.\n\n## Gate\n\n`edits\u002Freadiness-report.md` has `verdict: PASS` (or an author override recorded in `edits\u002Feditorial-report.md`). All chapters `status: final`. Stage reports 01-06 exist (00 for nonfiction). No unresolved Critical issues in the last continuity or fact-check report.\n\n## Post-completion\n\n```bash\nnode ${CLAUDE_PLUGIN_ROOT}\u002Fvelith.mjs scan [project-dir]\n```\n",{"name":5,"description":7,"argument-hint":45},"[project-dir] [stage 0-6|all] [chapter-file]","main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fepicsagas\u002FVelith\u002Fskills\u002Fbook-edit",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":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill book-edit",{"tool":62,"command":63},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill book-edit",{"tool":65,"command":66},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill book-edit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fepicsagas\u002FVelith\u002Fskills\u002Fbook-edit\u002FSKILL.md",true,[],[71,79,86,93,120,144],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":78},"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":78},"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":78},"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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",[],[100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119],"search","deja search","never","error","ready","memory","re","decide","fix","design","debugging","when","you","done","reviewer","io","change","cli","merge","past",{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"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",[],[127,128,129,115,130,131,132,133,134,135,136,137,138,139,105,140,22,141,142,143],"deja reflect","reflect","review","with","record","github","next","https","node","Rules","decisions","brew","remember","project rules","session","end","reflection",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":161,"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",[150,155,158],{"categoryNo":151,"categoryName":152,"taxonomyType":153,"taxonomyTypeDesc":154},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":156,"categoryName":157,"taxonomyType":153,"taxonomyTypeDesc":154},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":159,"categoryName":160,"taxonomyType":153,"taxonomyTypeDesc":154},"01JBSEEDCAT000000000000010","后端与接口",[146,162,163,164,165,166,167,22,168,106,169,170,171,172,111,173,174,175,176,177],"URL","Video","short-form","standalone","PDF","viral","tiktok","short","social","MCP","song","image","mcp server","schedule","api","publish"]