[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7233P4A99FX4MCX15NRX01G":3,"skill-same:01M7233P4A99FX4MCX15NRX01G":89},{"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":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":34,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M7233P4A99FX4MCX15NRX01G","askit-build-skill",null,"Creates and improves agentskills.io skills to the Advanced Skill Library Standard. Use when you need to author a new SKILL.md, scaffold a skill directory, or raise an existing skill's conformance and description quality.","product-on-purpose\u002Fagent-skills-toolkit","product-on-purpose","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F253892650?v=4","01M7230Q4442AHBADCVFJCS277","Product on Purpose","01M7230Q4SFDBKY7586D5M7EFX",3,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Faskit-build-skill\u002FSKILL.md",[],[],"2026-11-10 18:39:20",false,"---\nname: askit-build-skill\ndescription: Creates and improves agentskills.io skills to the Advanced Skill Library Standard. Use when you need to author a new SKILL.md, scaffold a skill directory, or raise an existing skill's conformance and description quality.\nmetadata:\n  version: 0.1.3\n  tier: universal\n  audience: beginner\n  chain: askit-skill-author, askit-reviewer\n---\n\n# askit-build-skill\n\n## Purpose\nAuthor conformant skills. Two modes: `create` scaffolds a new skill that passes Bronze on first run; `improve` raises an existing skill toward the quality bar. Authoring depth is in [references\u002Fauthoring-guide.md](references\u002Fauthoring-guide.md).\n\n## When to use\nWhen the user asks to create, scaffold, write, or improve a skill.\n\n## create mode\n1. Brief interview: ask for the skill name (kebab-case), what it does, when to use it, and a few trigger keywords. Skip the interview if these inputs are already provided in context.\n2. Delegate the drafting to the `askit-skill-author` subagent (the declared chain) when running in a harness that can dispatch it; otherwise perform the steps below inline. Either way the procedure is the same: create `skills\u002F\u003Cname>\u002F` and copy `templates\u002FSKILL.md` into `skills\u002F\u003Cname>\u002FSKILL.md`. **A repository's own skill template governs over this toolkit's.** Before copying, look for one: a path the repository's authoring or contributing docs name, or a file such as `docs\u002Finternal\u002Fskill-template.md`. When one exists, copy it instead, and use `templates\u002FSKILL.md` only for what it leaves out. A house template usually encodes rules the repository's own gate enforces, so the generic template would produce a skill that gate rejects.\n3. Fill the frontmatter: `name` equal to the directory, and a `description` that states what AND when with concrete keywords (see [references\u002Fauthoring-guide.md](references\u002Fauthoring-guide.md) for the bar).\n4. Scaffold `references\u002F` if the skill needs depth. Samples in `examples\u002F` are optional at Bronze - add them only if useful. Do not assume the surrounding plugin anatomy exists - this skill works a la carte.\n5. Emit native manifests for the declared targets: set `agent-targets` in the plugin's `library.json` (for example `[\"claude\", \"codex\"]`), then run `node scripts\u002Fgenerators\u002Fgen-manifest.mjs \u003Cplugin-root> --write --target=all`. To emit for one agent only, pass `--target=claude` or `--target=codex`. The plugin's `library.json` `agent-targets` (not a CLI flag) declares which targets it requires; `gen-manifest` writes `.claude-plugin\u002Fplugin.json` and\u002For `.codex-plugin\u002Fplugin.json` from `library.json`.\n6. Assess the new skill with `node scripts\u002Fevaluate.mjs skills\u002F\u003Cname> --json` (this is what the `askit-evaluate` skill runs), report the result, and iterate until it passes with 0 errors.\n\n## improve mode\n1. Run `node scripts\u002Fevaluate.mjs \u003Cskill> --json` and read the report. As in create mode, the rewrite work itself may be delegated to `askit-skill-author` or done inline; the steps below are the procedure either way.\n2. For each finding: a samples warn -> add representative examples; a low description score (U5) -> rewrite the description to clear the bar; an over-budget warning (U7) -> move depth into `references\u002F`. For any other finding, read its message and apply the fix it states.\n3. Re-run evaluate to confirm the findings are resolved. That closes phase 1 (conformance).\n\n## improve mode, phase 2: the craft review (optional)\nPhase 1 proves the skill obeys the rules. Phase 2 asks whether it is any good as a teacher. It is OPTIONAL, it is OFFERED not assumed, and it never edits meaning. Decision and contract: ADR 0037 (the builder craft pass), `docs\u002Finternal\u002Fdecisions\u002F0037-builder-craft-pass-and-safe-judgment-partition.md`.\n\n1. **Check eligibility.** Phase 2 is offered only when the deterministic gate is already clean. Pass the phase-1 gate result (`{ exitCode, errors, warns }`) to `phaseTwoEligible()` from `scripts\u002Flib\u002Fcraft-review.mjs`. If it returns ineligible, say why and go back to phase 1; the craft pass is never a way around a conformance failure.\n2. **Offer it, and stop.** Tell the user what the craft review costs (one advisory subagent run, see `docs\u002Freference\u002Ftoken-usage-estimates.md`) and what it produces. Run it only on an explicit yes.\n3. **Dispatch the reviewer.** Delegate to the `askit-reviewer` subagent (the declared chain), briefed with [references\u002Fskill-craft-rubric.md](references\u002Fskill-craft-rubric.md). It scores five dimensions - description and trigger quality, instruction clarity, example depth including golden and anti-example presence, reference structure, token economy - and returns findings in the rubric's contract. **If the session has no `askit-reviewer` agent type**, as in fallback mode, where the toolkit is a sibling checkout rather than an installed plugin, brief any capable general-purpose agent instead. Give it `agents\u002Faskit-reviewer.md` and the rubric, and run its output through `toReviewAdvisory()` as usual.\n4. **Render a durable report.** Write the findings through `toReviewAdvisory()` to a JSON file, then render: `node scripts\u002Fevaluate.mjs \u003Cskill> --report=review --advisory \u003Cfile.json> --format=md --out \u003Creport.md>` (use `--format=html` for the shareable page). The craft review is an artifact, not chat output. It renders BESIDE the verdict and cannot change it.\n5. **Partition.** Call `partitionCraftFindings()`. SAFE is a closed allowlist of three mechanical categories (broken link, formatting, missing bookkeeping frontmatter field), each needing a bounded single-line fix. Everything else, including any category the allowlist does not name, is JUDGMENT.\n6. **Offer the SAFE subset only, item by item.** Show each SAFE fix as the exact before and after. On explicit consent, call `applySafeFixes(\u003Cskill>, safe, { consent: true })`. Without `consent: true` it writes nothing, and it refuses any finding that is not SAFE even if it is handed one.\n7. **Report the JUDGMENT findings, do not act on them.** Present each with its recommended change and leave the files untouched. If the user asks for one, that is ordinary improve-mode work (step 2), consciously chosen.\n8. **Re-run the gate** (`node scripts\u002Fevaluate.mjs \u003Cskill> --json`) to confirm it is still clean after the apply, and say so.\n\n## Scope\nEmits for Claude and Codex: `library.json.agent-targets` declares which targets the plugin requires, and `gen-manifest.mjs --target=all|claude|codex` generates the matching native manifests. This skill delegates authoring to the `askit-skill-author` subagent (permitted in `agents\u002F_chain-permitted.yaml`), which in turn delegates assessment to `askit-evaluator`, and delegates the optional phase-2 craft review to `askit-reviewer` (the same subagent `askit-evaluate` uses for its advisory review layer).\n","# askit-build-skill\n\n## Purpose\nAuthor conformant skills. Two modes: `create` scaffolds a new skill that passes Bronze on first run; `improve` raises an existing skill toward the quality bar. Authoring depth is in [references\u002Fauthoring-guide.md](references\u002Fauthoring-guide.md).\n\n## When to use\nWhen the user asks to create, scaffold, write, or improve a skill.\n\n## create mode\n1. Brief interview: ask for the skill name (kebab-case), what it does, when to use it, and a few trigger keywords. Skip the interview if these inputs are already provided in context.\n2. Delegate the drafting to the `askit-skill-author` subagent (the declared chain) when running in a harness that can dispatch it; otherwise perform the steps below inline. Either way the procedure is the same: create `skills\u002F\u003Cname>\u002F` and copy `templates\u002FSKILL.md` into `skills\u002F\u003Cname>\u002FSKILL.md`. **A repository's own skill template governs over this toolkit's.** Before copying, look for one: a path the repository's authoring or contributing docs name, or a file such as `docs\u002Finternal\u002Fskill-template.md`. When one exists, copy it instead, and use `templates\u002FSKILL.md` only for what it leaves out. A house template usually encodes rules the repository's own gate enforces, so the generic template would produce a skill that gate rejects.\n3. Fill the frontmatter: `name` equal to the directory, and a `description` that states what AND when with concrete keywords (see [references\u002Fauthoring-guide.md](references\u002Fauthoring-guide.md) for the bar).\n4. Scaffold `references\u002F` if the skill needs depth. Samples in `examples\u002F` are optional at Bronze - add them only if useful. Do not assume the surrounding plugin anatomy exists - this skill works a la carte.\n5. Emit native manifests for the declared targets: set `agent-targets` in the plugin's `library.json` (for example `[\"claude\", \"codex\"]`), then run `node scripts\u002Fgenerators\u002Fgen-manifest.mjs \u003Cplugin-root> --write --target=all`. To emit for one agent only, pass `--target=claude` or `--target=codex`. The plugin's `library.json` `agent-targets` (not a CLI flag) declares which targets it requires; `gen-manifest` writes `.claude-plugin\u002Fplugin.json` and\u002For `.codex-plugin\u002Fplugin.json` from `library.json`.\n6. Assess the new skill with `node scripts\u002Fevaluate.mjs skills\u002F\u003Cname> --json` (this is what the `askit-evaluate` skill runs), report the result, and iterate until it passes with 0 errors.\n\n## improve mode\n1. Run `node scripts\u002Fevaluate.mjs \u003Cskill> --json` and read the report. As in create mode, the rewrite work itself may be delegated to `askit-skill-author` or done inline; the steps below are the procedure either way.\n2. For each finding: a samples warn -> add representative examples; a low description score (U5) -> rewrite the description to clear the bar; an over-budget warning (U7) -> move depth into `references\u002F`. For any other finding, read its message and apply the fix it states.\n3. Re-run evaluate to confirm the findings are resolved. That closes phase 1 (conformance).\n\n## improve mode, phase 2: the craft review (optional)\nPhase 1 proves the skill obeys the rules. Phase 2 asks whether it is any good as a teacher. It is OPTIONAL, it is OFFERED not assumed, and it never edits meaning. Decision and contract: ADR 0037 (the builder craft pass), `docs\u002Finternal\u002Fdecisions\u002F0037-builder-craft-pass-and-safe-judgment-partition.md`.\n\n1. **Check eligibility.** Phase 2 is offered only when the deterministic gate is already clean. Pass the phase-1 gate result (`{ exitCode, errors, warns }`) to `phaseTwoEligible()` from `scripts\u002Flib\u002Fcraft-review.mjs`. If it returns ineligible, say why and go back to phase 1; the craft pass is never a way around a conformance failure.\n2. **Offer it, and stop.** Tell the user what the craft review costs (one advisory subagent run, see `docs\u002Freference\u002Ftoken-usage-estimates.md`) and what it produces. Run it only on an explicit yes.\n3. **Dispatch the reviewer.** Delegate to the `askit-reviewer` subagent (the declared chain), briefed with [references\u002Fskill-craft-rubric.md](references\u002Fskill-craft-rubric.md). It scores five dimensions - description and trigger quality, instruction clarity, example depth including golden and anti-example presence, reference structure, token economy - and returns findings in the rubric's contract. **If the session has no `askit-reviewer` agent type**, as in fallback mode, where the toolkit is a sibling checkout rather than an installed plugin, brief any capable general-purpose agent instead. Give it `agents\u002Faskit-reviewer.md` and the rubric, and run its output through `toReviewAdvisory()` as usual.\n4. **Render a durable report.** Write the findings through `toReviewAdvisory()` to a JSON file, then render: `node scripts\u002Fevaluate.mjs \u003Cskill> --report=review --advisory \u003Cfile.json> --format=md --out \u003Creport.md>` (use `--format=html` for the shareable page). The craft review is an artifact, not chat output. It renders BESIDE the verdict and cannot change it.\n5. **Partition.** Call `partitionCraftFindings()`. SAFE is a closed allowlist of three mechanical categories (broken link, formatting, missing bookkeeping frontmatter field), each needing a bounded single-line fix. Everything else, including any category the allowlist does not name, is JUDGMENT.\n6. **Offer the SAFE subset only, item by item.** Show each SAFE fix as the exact before and after. On explicit consent, call `applySafeFixes(\u003Cskill>, safe, { consent: true })`. Without `consent: true` it writes nothing, and it refuses any finding that is not SAFE even if it is handed one.\n7. **Report the JUDGMENT findings, do not act on them.** Present each with its recommended change and leave the files untouched. If the user asks for one, that is ordinary improve-mode work (step 2), consciously chosen.\n8. **Re-run the gate** (`node scripts\u002Fevaluate.mjs \u003Cskill> --json`) to confirm it is still clean after the apply, and say so.\n\n## Scope\nEmits for Claude and Codex: `library.json.agent-targets` declares which targets the plugin requires, and `gen-manifest.mjs --target=all|claude|codex` generates the matching native manifests. This skill delegates authoring to the `askit-skill-author` subagent (permitted in `agents\u002F_chain-permitted.yaml`), which in turn delegates assessment to `askit-evaluator`, and delegates the optional phase-2 craft review to `askit-reviewer` (the same subagent `askit-evaluate` uses for its advisory review layer).\n",{"name":5,"metadata":24,"description":7},{"tier":25,"chain":26,"version":27,"audience":28},"universal","askit-skill-author, askit-reviewer","0.1.3","beginner","main","b0a696723b1155d08503a8441c981998f9d13c34","skills\u002Faskit-build-skill",0,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit","https:\u002F\u002Fproduct-on-purpose.github.io\u002Fagent-skills-toolkit","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose","2026-11-14 15:02:57",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add product-on-purpose\u002Fagent-skills-toolkit --skill askit-build-skill",{"tool":43,"command":44},"bunx","bunx skills add product-on-purpose\u002Fagent-skills-toolkit --skill askit-build-skill",{"tool":46,"command":47},"pnpm","pnpm dlx skills add product-on-purpose\u002Fagent-skills-toolkit --skill askit-build-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Faskit-build-skill\u002FSKILL.md",true,[51,57,61,65,69,73,77,81,85],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"evals\u002Faskit-build-skill-triggering.eval.json","REFERENCE","参考文档",2599,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Faskit-build-skill\u002Fevals\u002Faskit-build-skill-triggering.eval.json",{"path":58,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":59,"sourceHtmlUrl":60},"evals\u002FREADME.md",361,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Faskit-build-skill\u002Fevals\u002FREADME.md",{"path":62,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":63,"sourceHtmlUrl":64},"examples\u002Fanti-vague-description.md",9759,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Faskit-build-skill\u002Fexamples\u002Fanti-vague-description.md",{"path":66,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":67,"sourceHtmlUrl":68},"examples\u002Fgolden-1-conventional-commit.md",6347,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Faskit-build-skill\u002Fexamples\u002Fgolden-1-conventional-commit.md",{"path":70,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":71,"sourceHtmlUrl":72},"examples\u002Fgolden-2-incident-postmortem.md",12087,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Faskit-build-skill\u002Fexamples\u002Fgolden-2-incident-postmortem.md",{"path":74,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":75,"sourceHtmlUrl":76},"examples\u002Fgolden-3-dependency-audit.md",12528,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Faskit-build-skill\u002Fexamples\u002Fgolden-3-dependency-audit.md",{"path":78,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":79,"sourceHtmlUrl":80},"README.md",669,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Faskit-build-skill\u002FREADME.md",{"path":82,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fauthoring-guide.md",13273,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Faskit-build-skill\u002Freferences\u002Fauthoring-guide.md",{"path":86,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Fskill-craft-rubric.md",8261,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Faskit-build-skill\u002Freferences\u002Fskill-craft-rubric.md",[90,97,102,107,114,121],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M723BRSVFQ2KRQ8KKY42R6XB","fx-demo","A fixture skill that exists so the re-derived manifest has a component list to compare. Use only from tests\u002Funit\u002Fself-consistency.test.mjs.","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fself-consistency\u002Frepaired\u002Fskills\u002Ffx-demo\u002FSKILL.md",[],[],{"skillNo":98,"name":92,"nameZh":6,"description":93,"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":19},"01M723BPZ1NQDZSEF21D3YP2VF","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fself-consistency\u002Fpre-fix\u002Fskills\u002Ffx-demo\u002FSKILL.md",[],[],{"skillNo":103,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M723BNCZXT3BM577HJYESV08","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fself-consistency\u002Fbody-drift\u002Fskills\u002Ffx-demo\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M723BKWKX9JG10YQ6NK79ZB6","sf-caller","Calls the worker subagent to do a thing. Use when delegating work to sf-worker.","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fgolden\u002Fsubagent-fixture\u002Fskills\u002Fsf-caller\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":19},"01M723BJNDZHEJTNBJP6ZJA8WM","sf-do-thing","Converts CSV input into a formatted summary. Use when the user asks to summarize or tabulate spreadsheet data.","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fgolden\u002Fsilver-fixture\u002Fskills\u002Fsf-do-thing\u002FSKILL.md",[],[],{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":19},"01M723BH7BYXT0A05PG6QH6B98","root-skill-plugin","Summarizes a changelog section into one release-note sentence. Use when the user asks to condense a list of changelog bullets into a single announcement line.","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fgolden\u002Froot-skill-plugin\u002FSKILL.md",[],[]]