[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6M9GTYDCVM9N5RM79C0TN2H":3,"skill-same:01M6M9GTYDCVM9N5RM79C0TN2H":79},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M6M9GTYDCVM9N5RM79C0TN2H","caveman-internal",null,"Internal token-compression protocol for Cavekit agent artifacts — handoff\nnotes, artifact summaries, context bundles, review notes, status lines.\nNOT the user-facing \u002Fcaveman skill; that one compresses assistant replies to\nthe user. This skill compresses machine-to-machine prose so the next agent in\nthe loop reads fewer tokens. Three intensities (lite \u002F full \u002F ultra) with\nautomatic selection based on budget pressure. Used by task-builder, builder,\ninspector, verifier, convergence-monitor, and the stop-hook status block.","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\u002Fcaveman-internal\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"caveman internal","caveman","selection","automatic","convergence","ultra","hook","token","full","artifact","next","assistant","stop","builder","hook status","loop","Budget","notes","status","review","2026-11-10 10:12:30",false,"---\nname: caveman-internal\ndescription: |\n  Internal token-compression protocol for Cavekit agent artifacts — handoff\n  notes, artifact summaries, context bundles, review notes, status lines.\n  NOT the user-facing \u002Fcaveman skill; that one compresses assistant replies to\n  the user. This skill compresses machine-to-machine prose so the next agent in\n  the loop reads fewer tokens. Three intensities (lite \u002F full \u002F ultra) with\n  automatic selection based on budget pressure. Used by task-builder, builder,\n  inspector, verifier, convergence-monitor, and the stop-hook status block.\n---\n\n# Caveman Internal Protocol\n\n## Scope\n\n### IN-scope (compress)\n- Artifact summaries written to `.cavekit\u002Fartifacts\u002F`\n- Context bundles between tasks (`.cavekit\u002Fcontext-bundles\u002F`)\n- Review notes and gap lists (non-user-facing)\n- `state.md` `notes:` field and `loop-log.md` entries\n- Status-block body (dashboard injected by the stop hook)\n- Inter-agent handoff memos\n\n### OUT-of-scope (never compress)\n- Source code (any language, any file)\n- Git commit messages and PR descriptions\n- Kits (specs), build sites, DESIGN.md\n- Error messages that a human will act on\n- Security warnings and deprecation notices\n- Structured findings tables (P0\u002FP1\u002FP2\u002FP3, coverage matrices)\n- Regression test names and assertion messages\n\nCompressing out-of-scope content is a bug. If a reader cannot act on a\ncompressed artifact, regenerate it verbose and log a caveman fallback — see\n\"Fallback protocol\" below.\n\n## Intensity levels\n\n### Lite — trim the fat (~20% savings)\n\nProfessional tone. Grammar intact. Drop filler, pleasantries, hedging. Keep\narticles and full sentences.\n\n> Rate-limit middleware passes unit tests. Integration failed on 429 header\n> case sensitivity. Fix in progress.\n\n### Full — default (~40% savings)\n\nClassic caveman. Drop articles, filler, pleasantries. Fragments fine.\nTechnical terms stay exact. Pattern: `[thing] [action] [reason]. [next].`\n\n> Rate-limit mw pass unit. Integration fail on 429 header case. Fixing.\n\n### Ultra — maximum grunt (~65% savings)\n\nTelegraphic. Abbreviate common terms (DB, auth, config, req, res, fn, impl,\nmw, mcp). Arrow notation for causality. One-word answers when enough.\n\n> mw ok, int fail header case → fix\n\n## Automatic intensity selection\n\nConsult the session budget ledger before writing an internal artifact:\n\n| Budget remaining | Intensity |\n|------------------|-----------|\n| > 50 %           | lite      |\n| 20 – 50 %        | full      |\n| \u003C 20 %           | ultra     |\n\nOverride rules:\n- `depth = thorough` tasks clamp to **lite** regardless of pressure (accuracy\n  matters more than tokens when the stakes are high).\n- `phase = inspecting` clamps to **lite** for the gap-analysis output.\n- Security-sensitive artifacts clamp to **lite**.\n- If the caller sets `caveman_intensity` explicitly in the artifact envelope,\n  use that and skip auto-selection.\n\nSee `references\u002Fbudget-thresholds.md` for the detailed decision table.\n\n## Fallback protocol\n\nIf a downstream reader cannot reconstruct intent from a compressed artifact:\n\n1. Regenerate the artifact in **full prose** (no compression).\n2. Append a one-line entry to `state.md`'s \"Caveman fallbacks\" section:\n   ```\n   - 2026-04-17T12:34Z T-017 verifier fallback: artifact summary re-expanded\n   ```\n3. If the same artifact category fails 3+ times in one session, clamp that\n   category to `lite` for the rest of the session and log to `state.md`.\n\n## Envelope\n\nEvery compressed artifact carries a tiny header:\n\n```\n\u003C!-- caveman: intensity=full version=1 -->\n```\n\nReaders that see this header know the body is compressed and apply the\nreverse-expansion grammar (re-add articles, re-expand abbreviations) when\nrendering for a human.\n\n## Examples\n\n| Verbose                                                                 | Full                                        | Ultra                |\n|-------------------------------------------------------------------------|---------------------------------------------|----------------------|\n| \"The build completed successfully after three waves.\"                   | \"Build complete. 3 waves.\"                  | \"Build ok 3w\"        |\n| \"All tests pass, but one test was skipped due to a missing fixture.\"    | \"Tests pass. One skipped, missing fixture.\" | \"Tests ok 1 skip fx\" |\n| \"The reviewer flagged two critical issues in the auth middleware.\"     | \"Reviewer: 2 P0 in auth mw.\"                | \"Rev 2 P0 auth mw\"   |\n\n## Integration with the existing `caveman` skill\n\nThe user-facing `caveman` skill governs how the assistant **speaks to the user**\nduring a session (answers, explanations, replies). This `caveman-internal`\nskill governs how agents **write artifacts** for each other. Both must be on\nor both off for a coherent experience, so `caveman_mode = off` in config also\ndisables this skill.\n","# Caveman Internal Protocol\n\n## Scope\n\n### IN-scope (compress)\n- Artifact summaries written to `.cavekit\u002Fartifacts\u002F`\n- Context bundles between tasks (`.cavekit\u002Fcontext-bundles\u002F`)\n- Review notes and gap lists (non-user-facing)\n- `state.md` `notes:` field and `loop-log.md` entries\n- Status-block body (dashboard injected by the stop hook)\n- Inter-agent handoff memos\n\n### OUT-of-scope (never compress)\n- Source code (any language, any file)\n- Git commit messages and PR descriptions\n- Kits (specs), build sites, DESIGN.md\n- Error messages that a human will act on\n- Security warnings and deprecation notices\n- Structured findings tables (P0\u002FP1\u002FP2\u002FP3, coverage matrices)\n- Regression test names and assertion messages\n\nCompressing out-of-scope content is a bug. If a reader cannot act on a\ncompressed artifact, regenerate it verbose and log a caveman fallback — see\n\"Fallback protocol\" below.\n\n## Intensity levels\n\n### Lite — trim the fat (~20% savings)\n\nProfessional tone. Grammar intact. Drop filler, pleasantries, hedging. Keep\narticles and full sentences.\n\n> Rate-limit middleware passes unit tests. Integration failed on 429 header\n> case sensitivity. Fix in progress.\n\n### Full — default (~40% savings)\n\nClassic caveman. Drop articles, filler, pleasantries. Fragments fine.\nTechnical terms stay exact. Pattern: `[thing] [action] [reason]. [next].`\n\n> Rate-limit mw pass unit. Integration fail on 429 header case. Fixing.\n\n### Ultra — maximum grunt (~65% savings)\n\nTelegraphic. Abbreviate common terms (DB, auth, config, req, res, fn, impl,\nmw, mcp). Arrow notation for causality. One-word answers when enough.\n\n> mw ok, int fail header case → fix\n\n## Automatic intensity selection\n\nConsult the session budget ledger before writing an internal artifact:\n\n| Budget remaining | Intensity |\n|------------------|-----------|\n| > 50 %           | lite      |\n| 20 – 50 %        | full      |\n| \u003C 20 %           | ultra     |\n\nOverride rules:\n- `depth = thorough` tasks clamp to **lite** regardless of pressure (accuracy\n  matters more than tokens when the stakes are high).\n- `phase = inspecting` clamps to **lite** for the gap-analysis output.\n- Security-sensitive artifacts clamp to **lite**.\n- If the caller sets `caveman_intensity` explicitly in the artifact envelope,\n  use that and skip auto-selection.\n\nSee `references\u002Fbudget-thresholds.md` for the detailed decision table.\n\n## Fallback protocol\n\nIf a downstream reader cannot reconstruct intent from a compressed artifact:\n\n1. Regenerate the artifact in **full prose** (no compression).\n2. Append a one-line entry to `state.md`'s \"Caveman fallbacks\" section:\n   ```\n   - 2026-04-17T12:34Z T-017 verifier fallback: artifact summary re-expanded\n   ```\n3. If the same artifact category fails 3+ times in one session, clamp that\n   category to `lite` for the rest of the session and log to `state.md`.\n\n## Envelope\n\nEvery compressed artifact carries a tiny header:\n\n```\n\u003C!-- caveman: intensity=full version=1 -->\n```\n\nReaders that see this header know the body is compressed and apply the\nreverse-expansion grammar (re-add articles, re-expand abbreviations) when\nrendering for a human.\n\n## Examples\n\n| Verbose                                                                 | Full                                        | Ultra                |\n|-------------------------------------------------------------------------|---------------------------------------------|----------------------|\n| \"The build completed successfully after three waves.\"                   | \"Build complete. 3 waves.\"                  | \"Build ok 3w\"        |\n| \"All tests pass, but one test was skipped due to a missing fixture.\"    | \"Tests pass. One skipped, missing fixture.\" | \"Tests ok 1 skip fx\" |\n| \"The reviewer flagged two critical issues in the auth middleware.\"     | \"Reviewer: 2 P0 in auth mw.\"                | \"Rev 2 P0 auth mw\"   |\n\n## Integration with the existing `caveman` skill\n\nThe user-facing `caveman` skill governs how the assistant **speaks to the user**\nduring a session (answers, explanations, replies). This `caveman-internal`\nskill governs how agents **write artifacts** for each other. Both must be on\nor both off for a coherent experience, so `caveman_mode = off` in config also\ndisables this skill.\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002FJuliusBrussee\u002Fblueprint\u002Fskills\u002Fcaveman-internal",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":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill caveman-internal",{"tool":65,"command":66},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill caveman-internal",{"tool":68,"command":69},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill caveman-internal","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJuliusBrussee\u002Fblueprint\u002Fskills\u002Fcaveman-internal\u002FSKILL.md",true,[73],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fbudget-thresholds.md","REFERENCE","参考文档",1844,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJuliusBrussee\u002Fblueprint\u002Fskills\u002Fcaveman-internal\u002Freferences\u002Fbudget-thresholds.md",[80,88,95,102,129,152],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":87},"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":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":87},"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":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":87},"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":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":44},"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",[],[109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128],"search","deja search","never","error","ready","memory","re","decide","fix","design","debugging","when","you","done","reviewer","io","change","cli","merge","past",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":44},"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",[],[136,137,43,124,138,139,140,34,141,142,143,144,145,146,114,147,148,149,150,151],"deja reflect","reflect","with","record","github","https","node","Rules","decisions","brew","remember","project rules","project","session","end","reflection",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":165,"publishedAt":44},"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",[158,161,162],{"categoryNo":159,"categoryName":160,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":163,"categoryName":164,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",[154,166,167,168,169,170,171,148,172,115,173,174,175,176,120,177,178,179,180,181],"URL","Video","short-form","standalone","PDF","viral","tiktok","short","social","MCP","song","image","mcp server","schedule","api","publish"]