[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75Y8K6109GPWX0Y054ED9WB":3,"skill-same:01M75Y8K6109GPWX0Y054ED9WB":58},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M75Y8K6109GPWX0Y054ED9WB","skillspec",null,"Multiplex SkillSpec post-install setup: inspect skill\u002Frepo shape with doctor, map multi-skill and plugin-shaped repositories before fanout import, assess a skill or plugin's security boundary — what it could reach if executed, ranked by risk (critical\u002Fhigh\u002Fmedium\u002Flow), with a clickable-evidence tree — and gate or install it safely before it lands on disk, import existing SKILL.md skills from local folders or public URIs, inspect installed status, install compiled workspaces with entry\u002Fsupport visibility planning, install\u002Fupdate\u002Fenable\u002Fdisable router mode, optionally install\u002Fupdate\u002Fenable\u002Fdisable\u002Fdelete durable-executor, create specs from observed durable execution workspaces, revise SkillSpec YAML, and prove value before install or release. Use for skillspec, \u002Fskillspec, skillspec setup, post install setup, assess skill security, is this skill safe, what can this skill reach, scan a skill or plugin, security analysis of a skill, boundary check, gate a skill or plugin install, check a skill before installing, install this skill safely, pull a skill or plugin, import SKILL.md, import existing skill, port skill, what is the shape of this skill, what is the shape of skill, shape of skill, skill shape and source shape. Use when the task needs to run SkillSpec post-install setup inside the harness prompt, inspect the shape of a skill, skill folder, assess what a skill could reach, or gate a skill or plugin before installing it","modiqo\u002Fskillspec","modiqo","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F172510440?v=4","01M75Y49PC2TMQY8FYFFYR2Y6A","Modiqo","01M75Y49Q47S75MS68C2Q8QVBM",668,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmodiqo\u002Fskillspec\u002Fblob\u002Fmain\u002Fskills\u002Fskillspec\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: skillspec\ndescription: \"Multiplex SkillSpec post-install setup: inspect skill\u002Frepo shape with doctor, map multi-skill and plugin-shaped repositories before fanout import, assess a skill or plugin's security boundary — what it could reach if executed, ranked by risk (critical\u002Fhigh\u002Fmedium\u002Flow), with a clickable-evidence tree — and gate or install it safely before it lands on disk, import existing SKILL.md skills from local folders or public URIs, inspect installed status, install compiled workspaces with entry\u002Fsupport visibility planning, install\u002Fupdate\u002Fenable\u002Fdisable router mode, optionally install\u002Fupdate\u002Fenable\u002Fdisable\u002Fdelete durable-executor, create specs from observed durable execution workspaces, revise SkillSpec YAML, and prove value before install or release. Use for skillspec, \u002Fskillspec, skillspec setup, post install setup, assess skill security, is this skill safe, what can this skill reach, scan a skill or plugin, security analysis of a skill, boundary check, gate a skill or plugin install, check a skill before installing, install this skill safely, pull a skill or plugin, import SKILL.md, import existing skill, port skill, what is the shape of this skill, what is the shape of skill, shape of skill, skill shape and source shape. Use when the task needs to run SkillSpec post-install setup inside the harness prompt, inspect the shape of a skill, skill folder, assess what a skill could reach, or gate a skill or plugin before installing it\"\n---\n\n# SkillSpec\n\nSkillSpec post-install setup and skill-authoring multiplexer for inspecting skill\u002Frepo shape with doctor, mapping multi-skill and plugin-shaped workspaces, importing existing prose skills, inspecting SkillSpec status, installing compiled workspaces with visibility planning, installing\u002Fupdating\u002Fenabling\u002Fdisabling router mode, installing\u002Fupdating\u002Fenabling\u002Fdisabling\u002Fdeleting durable-executor, creating specs from observed durable execution workspaces, revising SkillSpecs, compiling reviewed skills, optional install, and value reporting.\n\nUse the directory that contains this loaded `SKILL.md` as `\u003Cskill_dir>`.\nThe SkillSpec contract is `\u003Cskill_dir>\u002Fskill.spec.yml`; do not assume the user's current working directory contains the spec.\n\nStart the SkillSpec guide with the user's task:\n\n`skillspec run-loop \u003Cskill_dir>\u002Fskill.spec.yml --input '\u003Cuser task>' --trace-dir \"${PWD}\u002F.skillspec\u002Ftraces\" --guide agent --json`\n\nResume an existing guided run:\n\n`skillspec run-loop \u003Cskill_dir>\u002Fskill.spec.yml --resume \u003Crun_dir> --guide agent --json`\n\nUse the JSON current gate as internal control data. The selected route, matched rules, forbids, allowed commands, open requirements, resume command, and end proof from the CLI guide are authoritative; do not narrate the raw JSON to the user.\n\nKeep SkillSpec mechanics in the background. Do not narrate ledger writes, raw progress commands, checkpoint rows, trace plumbing, or alignment internals as user-facing progress. Show simple intent-level updates only, such as what was assessed, what changed, what passed, and what remains blocked.\n\nDo not run `skillspec act`, `skillspec query`, `skillspec refs`, or `skillspec --help` during normal execution. Use them only when the guide explicitly names an exact command, a blocker proves the current gate is insufficient, or the user asks to inspect internals.\n\nFor read-only diagnostic routes such as Doctor\u002Fsource-shape assessment, run the diagnostic command or `skillspec doctor checklist \u003Csource> --json` when available, answer directly, and stop. Do not create source maps, import drafts, progress ledgers, final-response proof, or alignment summaries unless the user explicitly asks for proof.\n\nFor security assessment — what a skill could reach if executed, and a least-privilege boundary for it — use the standalone `skillspec boundary` commands and answer directly. This is a separate read-only tool that needs no `skill.spec.yml` and installs\u002Fchanges nothing:\n- `skillspec boundary map \u003Cfolder-or-url>` — Structure: a tree of a skill collection (skills, resources, orphan files, cross-references). `--json` for the graph.\n- `skillspec boundary assess \u003Cfolder-or-url>` — Security analysis: what each skill can reach if executed, ranked by severity (critical\u002Fhigh\u002Fmedium\u002Flow), scope-aware (a skill confined to its own directory is low risk), with documentation examples qualified rather than counted as live effects. `--json` for structured findings.\n- `skillspec boundary \u003Cskill-or-url>` — the raw effect surface: what it reads, reaches, executes, plus concealment and directive findings.\n- `skillspec boundary gate \u003Cfolder-or-url> --then '\u003Cinstall command>'` — assess a skill\u002Fplugin before install, present tree and risk, and run the install only on approval.\n- `skillspec pull \u003Cfolder-or-url>` — assess then install across harnesses: proxy to the Claude\u002FCodex plugin CLI for a marketplace repo, or place skill folders for any AGENTS.md\u002FSKILL.md harness. `skillspec update \u003Csource>` re-pulls and shows capability drift before replacing an installed skill.\n- `skillspec boundary emit \u003Cskill>` — a deny-by-default policy compiled from that surface.\n- `skillspec boundary guard install|add|mode enforce` — enforce a reviewed policy against installed skills via a managed PreToolUse hook.\n\nBoth local paths and public git URLs (GitHub, GitLab, Bitbucket, self-hosted) are supported; nothing in the analyzed package is executed. See `docs\u002Fboundary-guide.md`.\n\nFor proof-bearing execution routes, prefer `skillspec run checklist \u003Crun_dir> --stage entry|loop|exit --json` when available for current-phase cues, proof requirements, repeat-until conditions, forbids, and final alignment directives. Otherwise use the run-loop guide's current gate. Record routine successful evidence with one quiet `skillspec progress checkpoint ... --quiet` command at natural phase boundaries. Use individual `skillspec progress record` only for failures, blockers, or debugging.\n\nFor imports, prefer `skillspec import checklist \u003Csource-or-workspace> --stage entry|loop|exit --json` when available. The generated checklist owns the shape-specific template for single `SKILL.md`, multi-skill folder, or plugin-shaped source; follow its package\u002Ffile\u002Fblock repeat loops, commands, directives, evidence requirements, activation policy, and forbids until complete or blocked. Do not review one representative package, bulk-promote scaffolds, or install generated drafts.\n\nMissing alignment proof is not a prompt-writing task. Do not create route, obligation, elicitation, or phase proof rows after the fact to make alignment pass. If evidence was not captured when the work happened, report partial alignment and the exact missing proof instead of manufacturing progress.\n\nIf the `skillspec` CLI is not installed, report that this skill requires SkillSpec and ask the user to install it before continuing:\n\n```bash\ncurl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fmodiqo\u002Fskillspec\u002Fmain\u002Finstall.sh | sh\n# or, with Rust installed:\ncargo install skillspec\n```\n\nIf the user declines or installation is impossible, read `\u003Cskill_dir>\u002Fskill.spec.yml` directly and manually follow the same route, rule, phase, dependency, forbid, proof, and completion contract. Report that CLI guidance was unavailable and alignment proof is partial.\n","# SkillSpec\n\nSkillSpec post-install setup and skill-authoring multiplexer for inspecting skill\u002Frepo shape with doctor, mapping multi-skill and plugin-shaped workspaces, importing existing prose skills, inspecting SkillSpec status, installing compiled workspaces with visibility planning, installing\u002Fupdating\u002Fenabling\u002Fdisabling router mode, installing\u002Fupdating\u002Fenabling\u002Fdisabling\u002Fdeleting durable-executor, creating specs from observed durable execution workspaces, revising SkillSpecs, compiling reviewed skills, optional install, and value reporting.\n\nUse the directory that contains this loaded `SKILL.md` as `\u003Cskill_dir>`.\nThe SkillSpec contract is `\u003Cskill_dir>\u002Fskill.spec.yml`; do not assume the user's current working directory contains the spec.\n\nStart the SkillSpec guide with the user's task:\n\n`skillspec run-loop \u003Cskill_dir>\u002Fskill.spec.yml --input '\u003Cuser task>' --trace-dir \"${PWD}\u002F.skillspec\u002Ftraces\" --guide agent --json`\n\nResume an existing guided run:\n\n`skillspec run-loop \u003Cskill_dir>\u002Fskill.spec.yml --resume \u003Crun_dir> --guide agent --json`\n\nUse the JSON current gate as internal control data. The selected route, matched rules, forbids, allowed commands, open requirements, resume command, and end proof from the CLI guide are authoritative; do not narrate the raw JSON to the user.\n\nKeep SkillSpec mechanics in the background. Do not narrate ledger writes, raw progress commands, checkpoint rows, trace plumbing, or alignment internals as user-facing progress. Show simple intent-level updates only, such as what was assessed, what changed, what passed, and what remains blocked.\n\nDo not run `skillspec act`, `skillspec query`, `skillspec refs`, or `skillspec --help` during normal execution. Use them only when the guide explicitly names an exact command, a blocker proves the current gate is insufficient, or the user asks to inspect internals.\n\nFor read-only diagnostic routes such as Doctor\u002Fsource-shape assessment, run the diagnostic command or `skillspec doctor checklist \u003Csource> --json` when available, answer directly, and stop. Do not create source maps, import drafts, progress ledgers, final-response proof, or alignment summaries unless the user explicitly asks for proof.\n\nFor security assessment — what a skill could reach if executed, and a least-privilege boundary for it — use the standalone `skillspec boundary` commands and answer directly. This is a separate read-only tool that needs no `skill.spec.yml` and installs\u002Fchanges nothing:\n- `skillspec boundary map \u003Cfolder-or-url>` — Structure: a tree of a skill collection (skills, resources, orphan files, cross-references). `--json` for the graph.\n- `skillspec boundary assess \u003Cfolder-or-url>` — Security analysis: what each skill can reach if executed, ranked by severity (critical\u002Fhigh\u002Fmedium\u002Flow), scope-aware (a skill confined to its own directory is low risk), with documentation examples qualified rather than counted as live effects. `--json` for structured findings.\n- `skillspec boundary \u003Cskill-or-url>` — the raw effect surface: what it reads, reaches, executes, plus concealment and directive findings.\n- `skillspec boundary gate \u003Cfolder-or-url> --then '\u003Cinstall command>'` — assess a skill\u002Fplugin before install, present tree and risk, and run the install only on approval.\n- `skillspec pull \u003Cfolder-or-url>` — assess then install across harnesses: proxy to the Claude\u002FCodex plugin CLI for a marketplace repo, or place skill folders for any AGENTS.md\u002FSKILL.md harness. `skillspec update \u003Csource>` re-pulls and shows capability drift before replacing an installed skill.\n- `skillspec boundary emit \u003Cskill>` — a deny-by-default policy compiled from that surface.\n- `skillspec boundary guard install|add|mode enforce` — enforce a reviewed policy against installed skills via a managed PreToolUse hook.\n\nBoth local paths and public git URLs (GitHub, GitLab, Bitbucket, self-hosted) are supported; nothing in the analyzed package is executed. See `docs\u002Fboundary-guide.md`.\n\nFor proof-bearing execution routes, prefer `skillspec run checklist \u003Crun_dir> --stage entry|loop|exit --json` when available for current-phase cues, proof requirements, repeat-until conditions, forbids, and final alignment directives. Otherwise use the run-loop guide's current gate. Record routine successful evidence with one quiet `skillspec progress checkpoint ... --quiet` command at natural phase boundaries. Use individual `skillspec progress record` only for failures, blockers, or debugging.\n\nFor imports, prefer `skillspec import checklist \u003Csource-or-workspace> --stage entry|loop|exit --json` when available. The generated checklist owns the shape-specific template for single `SKILL.md`, multi-skill folder, or plugin-shaped source; follow its package\u002Ffile\u002Fblock repeat loops, commands, directives, evidence requirements, activation policy, and forbids until complete or blocked. Do not review one representative package, bulk-promote scaffolds, or install generated drafts.\n\nMissing alignment proof is not a prompt-writing task. Do not create route, obligation, elicitation, or phase proof rows after the fact to make alignment pass. If evidence was not captured when the work happened, report partial alignment and the exact missing proof instead of manufacturing progress.\n\nIf the `skillspec` CLI is not installed, report that this skill requires SkillSpec and ask the user to install it before continuing:\n\n```bash\ncurl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fmodiqo\u002Fskillspec\u002Fmain\u002Finstall.sh | sh\n# or, with Rust installed:\ncargo install skillspec\n```\n\nIf the user declines or installation is impossible, read `\u003Cskill_dir>\u002Fskill.spec.yml` directly and manually follow the same route, rule, phase, dependency, forbid, proof, and completion contract. Report that CLI guidance was unavailable and alignment proof is partial.\n",{"name":5,"description":7},"main","f4d9ab57aa239829aee47b2f563b309067f2d43e","skills\u002Fskillspec",43,"https:\u002F\u002Fgithub.com\u002Fmodiqo\u002Fskillspec","https:\u002F\u002Fskillspec.sh","https:\u002F\u002Fgithub.com\u002Fmodiqo","2026-08-09 16:13:21",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add modiqo\u002Fskillspec --skill skillspec",{"tool":38,"command":39},"bunx","bunx skills add modiqo\u002Fskillspec --skill skillspec",{"tool":41,"command":42},"pnpm","pnpm dlx skills add modiqo\u002Fskillspec --skill skillspec","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmodiqo\u002Fskillspec\u002Fblob\u002Fmain\u002Fskills\u002Fskillspec\u002FSKILL.md",true,[46,52],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"skill.spec.yml","REFERENCE","参考文档",259067,"https:\u002F\u002Fgithub.com\u002Fmodiqo\u002Fskillspec\u002Fblob\u002Fmain\u002Fskills\u002Fskillspec\u002Fskill.spec.yml",{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"source\u002FSKILL_md.old","OTHER","其他",32044,"https:\u002F\u002Fgithub.com\u002Fmodiqo\u002Fskillspec\u002Fblob\u002Fmain\u002Fskills\u002Fskillspec\u002Fsource\u002FSKILL_md.old",[59,65,72,79,86,93],{"skillNo":60,"name":5,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M75Y8D56NV5SYNR5F5HYBEEG","Multiplex SkillSpec post-install setup: inspect skill\u002Frepo shape with doctor, map multi-skill and plugin-shaped repositories before fanout import, import existing SKILL.md skills from local folders or public URIs, inspect installed status, install compiled workspaces with entry\u002Fsupport visibility planning, install\u002Fupdate\u002Fenable\u002Fdisable router mode, optionally install\u002Fupdate\u002Fenable\u002Fdisable\u002Fdelete durable-executor, create specs from observed durable execution workspaces, revise SkillSpec YAML, and prove value before install or release. Use for skillspec, \u002Fskillspec, skillspec setup, post install setup, import SKILL.md, import existing skill, port skill, what is the shape of this skill, what is the shape of skill, shape of skill, skill shape and source shape. Use when the task needs to run SkillSpec post-install setup inside the harness prompt, inspect the shape of a skill, skill folder","https:\u002F\u002Fgithub.com\u002Fmodiqo\u002Fskillspec\u002Fblob\u002Fmain\u002Fplugins\u002Fskillspec\u002Fskills\u002Fskillspec\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M75Y8AX0V7NP36ES5Y4EJ1JJ","example-browser-skill","Use when the user asks to browse a page.","https:\u002F\u002Fgithub.com\u002Fmodiqo\u002Fskillspec\u002Fblob\u002Fmain\u002Ffixtures\u002Fskills\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M75Y88HBD7JCSB9HR4C9KXE4","wrapped-exec","Install the project toolchain before running the build.","https:\u002F\u002Fgithub.com\u002Fmodiqo\u002Fskillspec\u002Fblob\u002Fmain\u002Ffixtures\u002Feffects\u002Fwrapped-exec\u002FSKILL.md",[],[],{"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":19},"01M75Y86991J3KXNA6MD06JTHE","unmapped-payload","Generate a release checklist from the current milestone.","https:\u002F\u002Fgithub.com\u002Fmodiqo\u002Fskillspec\u002Fblob\u002Fmain\u002Ffixtures\u002Feffects\u002Funmapped-payload\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":19},"01M75Y83XPS0QBZND6A58V7G8P","secret-reader","Check that AWS credentials are present before running a deployment.","https:\u002F\u002Fgithub.com\u002Fmodiqo\u002Fskillspec\u002Fblob\u002Fmain\u002Ffixtures\u002Feffects\u002Fsecret-reader\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":19},"01M75Y82RHGQH046VG6EGT9ZCN","rce-curl-pipe","Install the formatting toolchain.","https:\u002F\u002Fgithub.com\u002Fmodiqo\u002Fskillspec\u002Fblob\u002Fmain\u002Ffixtures\u002Feffects\u002Frce-curl-pipe\u002FSKILL.md",[],[]]