[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M790C4PF5M23YC744446GF7V":3,"skill-same:01M790C4PF5M23YC744446GF7V":71},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":15,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M790C4PF5M23YC744446GF7V","skill-creator",null,"Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.","ZDStudios\u002FAIOS","ZDStudios","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F121779558?v=4","01M788P61KMHSJ87R41BH4MSQM","01M788P627Y27KK5MQ1KG3TW5H",7,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FZDStudios\u002FAIOS\u002Fblob\u002Fmain\u002Fopenclaw-main\u002Fopenclaw-main\u002Fskills\u002Fskill-creator\u002Flicense.txt","https:\u002F\u002Fgithub.com\u002FZDStudios\u002FAIOS\u002Fblob\u002Fmain\u002Fopenclaw-main\u002Fopenclaw-main\u002Fskills\u002Fskill-creator\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: skill-creator\ndescription: \"Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.\"\n---\n\n# Skill Creator\n\nSkills are compact triggerable workflows. Metadata is always visible; body loads only after trigger; references\u002Fscripts\u002Fassets load only as needed.\n\n## Hard rules\n\n- For durable OpenClaw skill creation or updates in an agent session, use\n  `skill_workshop` to create or revise a pending proposal. Do not scaffold or\n  apply live `SKILL.md` files with shell commands or helper scripts.\n- Keep `SKILL.md` lean; Codex is already capable.\n- Put only trigger-critical facts in frontmatter `description`.\n- Quote frontmatter `description`.\n- Frontmatter needs `name` + `description`; local OpenClaw skills may also use `metadata`, `homepage`, `allowed-tools`, `user-invocable`, `license`.\n- Prefer noun-phrase descriptions; short generic trigger phrase, not full workflow.\n- Move long examples\u002Fdocs to `references\u002F`; scripts to `scripts\u002F`; templates\u002Fmedia to `assets\u002F`.\n- No extra README\u002Fchangelog\u002Fsetup docs inside a skill unless they are actual task references.\n- Validate YAML frontmatter after edits.\n\n## Shape\n\n```text\nskill-name\u002F\n  SKILL.md\n  scripts\u002F      optional deterministic helpers\n  references\u002F   optional docs loaded only when needed\n  assets\u002F       optional output resources\u002Ftemplates\n  agents\u002F       optional UI metadata\n```\n\n## Good SKILL.md\n\n```markdown\n---\nname: pdf-tools\ndescription: \"Inspect, split, merge, OCR, redact, or convert PDFs with local CLI tools.\"\n---\n\n# PDF tools\n\nUse for PDF manipulation. Prefer deterministic scripts for page edits.\n\n## Workflow\n\n1. Inspect file\u002Fpage count.\n2. Choose exact operation.\n3. Write output beside input unless user asked otherwise.\n4. Render\u002Fverify changed pages.\n```\n\n## Edit workflow\n\n1. Read existing skill and nearby resource names.\n2. Draft the proposed `SKILL.md` content.\n3. Create or revise the pending proposal through `skill_workshop` when the\n   change should persist as an OpenClaw skill.\n4. Remove generic advice the base model already knows.\n5. Keep brittle command syntax, auth caveats, safety rules, and validation.\n6. Replace tables with bullets unless a table is clearly needed.\n7. Relax prose; fragments ok.\n8. Validate frontmatter and run any script tests touched.\n\n## Validation\n\n```bash\npython skills\u002Fskill-creator\u002Fscripts\u002Fquick_validate.py skills\u002F\u003Cname>\npython - \u003C\u003C'PY'\nfrom pathlib import Path\nimport yaml\nfor p in Path(\"skills\").glob(\"*\u002FSKILL.md\"):\n    text=p.read_text()\n    if not text.startswith(\"---\\n\"):\n        raise SystemExit(f\"missing frontmatter: {p}\")\n    fm=text.split(\"---\",2)[1]\n    yaml.safe_load(fm)\nprint(\"ok\")\nPY\n```\n\n`quick_validate.py` is conservative; repo-local frontmatter may allow keys beyond public skill bundles.\n","# Skill Creator\n\nSkills are compact triggerable workflows. Metadata is always visible; body loads only after trigger; references\u002Fscripts\u002Fassets load only as needed.\n\n## Hard rules\n\n- For durable OpenClaw skill creation or updates in an agent session, use\n  `skill_workshop` to create or revise a pending proposal. Do not scaffold or\n  apply live `SKILL.md` files with shell commands or helper scripts.\n- Keep `SKILL.md` lean; Codex is already capable.\n- Put only trigger-critical facts in frontmatter `description`.\n- Quote frontmatter `description`.\n- Frontmatter needs `name` + `description`; local OpenClaw skills may also use `metadata`, `homepage`, `allowed-tools`, `user-invocable`, `license`.\n- Prefer noun-phrase descriptions; short generic trigger phrase, not full workflow.\n- Move long examples\u002Fdocs to `references\u002F`; scripts to `scripts\u002F`; templates\u002Fmedia to `assets\u002F`.\n- No extra README\u002Fchangelog\u002Fsetup docs inside a skill unless they are actual task references.\n- Validate YAML frontmatter after edits.\n\n## Shape\n\n```text\nskill-name\u002F\n  SKILL.md\n  scripts\u002F      optional deterministic helpers\n  references\u002F   optional docs loaded only when needed\n  assets\u002F       optional output resources\u002Ftemplates\n  agents\u002F       optional UI metadata\n```\n\n## Good SKILL.md\n\n```markdown\n---\nname: pdf-tools\ndescription: \"Inspect, split, merge, OCR, redact, or convert PDFs with local CLI tools.\"\n---\n\n# PDF tools\n\nUse for PDF manipulation. Prefer deterministic scripts for page edits.\n\n## Workflow\n\n1. Inspect file\u002Fpage count.\n2. Choose exact operation.\n3. Write output beside input unless user asked otherwise.\n4. Render\u002Fverify changed pages.\n```\n\n## Edit workflow\n\n1. Read existing skill and nearby resource names.\n2. Draft the proposed `SKILL.md` content.\n3. Create or revise the pending proposal through `skill_workshop` when the\n   change should persist as an OpenClaw skill.\n4. Remove generic advice the base model already knows.\n5. Keep brittle command syntax, auth caveats, safety rules, and validation.\n6. Replace tables with bullets unless a table is clearly needed.\n7. Relax prose; fragments ok.\n8. Validate frontmatter and run any script tests touched.\n\n## Validation\n\n```bash\npython skills\u002Fskill-creator\u002Fscripts\u002Fquick_validate.py skills\u002F\u003Cname>\npython - \u003C\u003C'PY'\nfrom pathlib import Path\nimport yaml\nfor p in Path(\"skills\").glob(\"*\u002FSKILL.md\"):\n    text=p.read_text()\n    if not text.startswith(\"---\\n\"):\n        raise SystemExit(f\"missing frontmatter: {p}\")\n    fm=text.split(\"---\",2)[1]\n    yaml.safe_load(fm)\nprint(\"ok\")\nPY\n```\n\n`quick_validate.py` is conservative; repo-local frontmatter may allow keys beyond public skill bundles.\n",{"name":5,"description":7},"main","4faa79f92720631ffd00755d9a1018f8c68d3619","openclaw-main\u002Fopenclaw-main\u002Fskills\u002Fskill-creator",1,"https:\u002F\u002Fgithub.com\u002FZDStudios\u002FAIOS","https:\u002F\u002Fzdstudios.github.io\u002FAIOS\u002F","https:\u002F\u002Fgithub.com\u002FZDStudios","zdstudios.network","Hacker, Coder and Machine Learning Engineer \r\n","2026-10-06 21:45:38",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add ZDStudios\u002FAIOS --skill skill-creator",{"tool":40,"command":41},"bunx","bunx skills add ZDStudios\u002FAIOS --skill skill-creator",{"tool":43,"command":44},"pnpm","pnpm dlx skills add ZDStudios\u002FAIOS --skill skill-creator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FZDStudios\u002FAIOS\u002Fblob\u002Fmain\u002Fopenclaw-main\u002Fopenclaw-main\u002Fskills\u002Fskill-creator\u002FSKILL.md",true,[48,53,59,63,67],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":15},"license.txt","LICENSE","许可证",11358,{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"scripts\u002Fpackage_skill.py","SCRIPT","脚本",4703,"https:\u002F\u002Fgithub.com\u002FZDStudios\u002FAIOS\u002Fblob\u002Fmain\u002Fopenclaw-main\u002Fopenclaw-main\u002Fskills\u002Fskill-creator\u002Fscripts\u002Fpackage_skill.py",{"path":60,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":61,"sourceHtmlUrl":62},"scripts\u002Fquick_validate.py",5303,"https:\u002F\u002Fgithub.com\u002FZDStudios\u002FAIOS\u002Fblob\u002Fmain\u002Fopenclaw-main\u002Fopenclaw-main\u002Fskills\u002Fskill-creator\u002Fscripts\u002Fquick_validate.py",{"path":64,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Ftest_package_skill.py",7771,"https:\u002F\u002Fgithub.com\u002FZDStudios\u002FAIOS\u002Fblob\u002Fmain\u002Fopenclaw-main\u002Fopenclaw-main\u002Fskills\u002Fskill-creator\u002Fscripts\u002Ftest_package_skill.py",{"path":68,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Ftest_quick_validate.py",3961,"https:\u002F\u002Fgithub.com\u002FZDStudios\u002FAIOS\u002Fblob\u002Fmain\u002Fopenclaw-main\u002Fopenclaw-main\u002Fskills\u002Fskill-creator\u002Fscripts\u002Ftest_quick_validate.py",[72,81,88,94,101,108],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":76,"licenseFileUrl":77,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7910QACPXVF8QY3ZMK6MD2M","ruflo","Ruflo is a multi-agent orchestration platform for AI coding agents (Claude Code, Cursor, Codex, Copilot, Gemini, Amp, +12 more). Use this skill when the user wants to (1) install\u002Finit ruflo in a project, (2) run multi-agent swarms with hierarchical coordination, (3) use ruflo's 314+ MCP tools for memory, routing, hooks, sub-agents, or workflows, (4) check ruflo status\u002Fversion\u002Fdoctor health, or (5) discover which of ruflo's 30+ plugins fits their task.","MIT","https:\u002F\u002Fgithub.com\u002FZDStudios\u002FAIOS\u002Fblob\u002Fmain\u002Fruflo-main\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FZDStudios\u002FAIOS\u002Fblob\u002Fmain\u002Fruflo-main\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":76,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M790G7AX480HX5959531CWBK","ponytail","Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says \"ponytail\", \"be lazy\", \"lazy mode\", \"simplest solution\", \"minimal solution\", \"yagni\", \"do less\", or \"shortest path\", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).","https:\u002F\u002Fgithub.com\u002FZDStudios\u002FAIOS\u002Fblob\u002Fmain\u002Fponytail-main\u002Fskills\u002Fponytail\u002FSKILL.md",[],[],{"skillNo":89,"name":83,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":76,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M790FD2BC49T1M774T6NND33","Lazy senior dev mode for any coding task (write, refactor, fix, review): YAGNI, stdlib first, no unrequested abstractions. Not for non-coding requests.","https:\u002F\u002Fgithub.com\u002FZDStudios\u002FAIOS\u002Fblob\u002Fmain\u002Fponytail-main\u002F.openclaw\u002Fskills\u002Fponytail\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":76,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M790FANKMMJJQK23GQEESEXP","ponytail-review","Review a diff for over-engineering. Finds what to delete: reinvented stdlib, needless deps, speculative abstractions. One line per finding.","https:\u002F\u002Fgithub.com\u002FZDStudios\u002FAIOS\u002Fblob\u002Fmain\u002Fponytail-main\u002F.openclaw\u002Fskills\u002Fponytail-review\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":76,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M790F7Q3SJZCR6BYQ97TVFEJ","ponytail-help","Quick reference for ponytail's modes, skills, and commands. One-shot display.","https:\u002F\u002Fgithub.com\u002FZDStudios\u002FAIOS\u002Fblob\u002Fmain\u002Fponytail-main\u002F.openclaw\u002Fskills\u002Fponytail-help\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":76,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":19},"01M790F3TX7VZG0J4VVXE9BSNT","ponytail-gain","Show ponytail measured impact as a scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display.","https:\u002F\u002Fgithub.com\u002FZDStudios\u002FAIOS\u002Fblob\u002Fmain\u002Fponytail-main\u002F.openclaw\u002Fskills\u002Fponytail-gain\u002FSKILL.md",[],[]]