[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79AHPRH3YYZ3F3VNK7QDSKJ":3,"skill-same:01M79AHPRH3YYZ3F3VNK7QDSKJ":47},{"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":31,"updatedAt":32,"install":33,"resources":46},"01M79AHPRH3YYZ3F3VNK7QDSKJ","zirkel-optimize-instruction",null,"Optimizes the exact wording of an instruction\u002Fprompt for a recurring task using APE — generates one candidate per framing, scores them against real test cases, and critiques the winner. Use when a prompt will be reused and its wording matters: \"tune this prompt\", \"find the best wording for this instruction\", \"optimize this system prompt\", \"which phrasing works best\", with representative test cases available. Not for one-off prompts with no test cases.","Anselmoo\u002Fwerkstoff","Anselmoo","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F13209783?v=4","01M799YTB3D7RZ4P3B8CSR2X85","Anselm Hahn","01M799YTBRAM6719D9V0NRGB4R",1,"MIT","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Fplugins\u002Fzirkel\u002Fskills\u002Fzirkel-optimize-instruction\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: zirkel-optimize-instruction\ndescription: >-\n  Optimizes the exact wording of an instruction\u002Fprompt for a recurring task using\n  APE — generates one candidate per framing, scores them against real test cases,\n  and critiques the winner. Use when a prompt will be reused and its wording\n  matters: \"tune this prompt\", \"find the best wording for this instruction\",\n  \"optimize this system prompt\", \"which phrasing works best\", with representative\n  test cases available. Not for one-off prompts with no test cases.\n---\n\n# zirkel-optimize-instruction\n\nGenerate 5 framings, score on fixed test cases, select, critique the winner. The\nguard enforces the candidate count, the framing set, the tie-break, and the\nchecklist size in code.\n\nThe guard is `python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzirkel.py\"`, typed in full in each command below.\n\n## Preferred path: the workflow\nWhen the Workflow tool is available, run\n`${CLAUDE_PLUGIN_ROOT}\u002Fworkflows\u002Foptimize-instruction.js`\n(args `{ taskDescription, testCases:[{input, expectedOutcome}] }`). It dispatches\none `instruction-candidate` agent per framing in parallel, scores each against the\nexact test cases, selects with the framing tie-break, and critiques the winner.\n\n## Inputs\n- a recurring task description\n- **3-5 representative real test cases** `{input, expectedOutcome}`. **Source them\n  from real prior inputs first; only construct if none exist. MUST NOT fabricate\n  test cases or adjust expected outcomes.**\n\n## Process\n\n1. **Generate exactly 5 candidates — one per APE framing:** rule-based,\n   example-based, definition-based, question-based, chain-of-thought-based. Each\n   commits fully to its framing (no blending).\n2. **Score each candidate against the exact provided test cases** (pass count).\n3. **Select the highest score.** Validate the count, framings, and tie-break:\n\n```\necho '{\"candidates\":[\n  {\"framing\":\"rule-based\",\"score\":4},\n  {\"framing\":\"example-based\",\"score\":4},\n  {\"framing\":\"definition-based\",\"score\":3},\n  {\"framing\":\"question-based\",\"score\":2},\n  {\"framing\":\"chain-of-thought-based\",\"score\":4}\n]}' | python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzirkel.py\" candidates -\n```\nThe guard requires exactly 5 candidates covering all 5 framings and **breaks ties\nby framing precedence: rule → example → definition → question → CoT.** Use its\n`winner`. If the guard rejects the set (wrong count, missing\u002Fduplicate framing,\nor malformed JSON), regenerate only the missing\u002Fduplicate framing(s) and\nre-validate. If the guard still rejects after 2 attempts, stop and report which\nframing(s) could not be produced rather than looping indefinitely.\n\n4. **Critique the winner only** with meta-prompting's 4-item checklist, revising\n   only failing items:\n```\necho '{\"checklist\":[\n  {\"criterion\":\"rules unambiguous\",\"pass\":true},\n  {\"criterion\":\"handles out-of-scope\",\"pass\":false},\n  {\"criterion\":\"format rules compatible\",\"pass\":true},\n  {\"criterion\":\"no two-way readings\",\"pass\":true}\n]}' | python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzirkel.py\" critique -\n```\n\n## Output\n- candidates table: framing, score (n\u002Ftotal)\n- winner + why\n- critique checklist: pass\u002Ffail per criterion\n- the final prompt, ready to use\n\nExample (task: \"triage inbound support tickets by urgency\"):\n\n```\n| framing              | score |\n|----------------------|-------|\n| rule-based           | 4\u002F5   |\n| example-based        | 4\u002F5   |\n| definition-based     | 3\u002F5   |\n| question-based       | 2\u002F5   |\n| chain-of-thought-based | 4\u002F5 |\n\nWinner: rule-based (tie with example-based and chain-of-thought-based at 4\u002F5;\nframing precedence picks rule-based)\n\nCritique:\n- [x] rules unambiguous\n- [ ] handles out-of-scope -> revised: added an explicit \"no urgency signal\n      found\" fallback clause\n- [x] format rules compatible\n- [x] no two-way readings\n\nFinal prompt:\n\"\"\"\nClassify this support ticket's urgency as high, medium, or low.\n\n- high: mentions data loss, outage, or a billing failure blocking checkout\n- medium: a broken feature with a workaround, or a repeat complaint\n- low: a question, a feature request, or cosmetic issue\n- if no urgency signal is present, classify as low and note \"no signal found\"\n\nTicket: {ticket_text}\n\"\"\"\n```\n","# zirkel-optimize-instruction\n\nGenerate 5 framings, score on fixed test cases, select, critique the winner. The\nguard enforces the candidate count, the framing set, the tie-break, and the\nchecklist size in code.\n\nThe guard is `python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzirkel.py\"`, typed in full in each command below.\n\n## Preferred path: the workflow\nWhen the Workflow tool is available, run\n`${CLAUDE_PLUGIN_ROOT}\u002Fworkflows\u002Foptimize-instruction.js`\n(args `{ taskDescription, testCases:[{input, expectedOutcome}] }`). It dispatches\none `instruction-candidate` agent per framing in parallel, scores each against the\nexact test cases, selects with the framing tie-break, and critiques the winner.\n\n## Inputs\n- a recurring task description\n- **3-5 representative real test cases** `{input, expectedOutcome}`. **Source them\n  from real prior inputs first; only construct if none exist. MUST NOT fabricate\n  test cases or adjust expected outcomes.**\n\n## Process\n\n1. **Generate exactly 5 candidates — one per APE framing:** rule-based,\n   example-based, definition-based, question-based, chain-of-thought-based. Each\n   commits fully to its framing (no blending).\n2. **Score each candidate against the exact provided test cases** (pass count).\n3. **Select the highest score.** Validate the count, framings, and tie-break:\n\n```\necho '{\"candidates\":[\n  {\"framing\":\"rule-based\",\"score\":4},\n  {\"framing\":\"example-based\",\"score\":4},\n  {\"framing\":\"definition-based\",\"score\":3},\n  {\"framing\":\"question-based\",\"score\":2},\n  {\"framing\":\"chain-of-thought-based\",\"score\":4}\n]}' | python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzirkel.py\" candidates -\n```\nThe guard requires exactly 5 candidates covering all 5 framings and **breaks ties\nby framing precedence: rule → example → definition → question → CoT.** Use its\n`winner`. If the guard rejects the set (wrong count, missing\u002Fduplicate framing,\nor malformed JSON), regenerate only the missing\u002Fduplicate framing(s) and\nre-validate. If the guard still rejects after 2 attempts, stop and report which\nframing(s) could not be produced rather than looping indefinitely.\n\n4. **Critique the winner only** with meta-prompting's 4-item checklist, revising\n   only failing items:\n```\necho '{\"checklist\":[\n  {\"criterion\":\"rules unambiguous\",\"pass\":true},\n  {\"criterion\":\"handles out-of-scope\",\"pass\":false},\n  {\"criterion\":\"format rules compatible\",\"pass\":true},\n  {\"criterion\":\"no two-way readings\",\"pass\":true}\n]}' | python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzirkel.py\" critique -\n```\n\n## Output\n- candidates table: framing, score (n\u002Ftotal)\n- winner + why\n- critique checklist: pass\u002Ffail per criterion\n- the final prompt, ready to use\n\nExample (task: \"triage inbound support tickets by urgency\"):\n\n```\n| framing              | score |\n|----------------------|-------|\n| rule-based           | 4\u002F5   |\n| example-based        | 4\u002F5   |\n| definition-based     | 3\u002F5   |\n| question-based       | 2\u002F5   |\n| chain-of-thought-based | 4\u002F5 |\n\nWinner: rule-based (tie with example-based and chain-of-thought-based at 4\u002F5;\nframing precedence picks rule-based)\n\nCritique:\n- [x] rules unambiguous\n- [ ] handles out-of-scope -> revised: added an explicit \"no urgency signal\n      found\" fallback clause\n- [x] format rules compatible\n- [x] no two-way readings\n\nFinal prompt:\n\"\"\"\nClassify this support ticket's urgency as high, medium, or low.\n\n- high: mentions data loss, outage, or a billing failure blocking checkout\n- medium: a broken feature with a workaround, or a repeat complaint\n- low: a question, a feature request, or cosmetic issue\n- if no urgency signal is present, classify as low and note \"no signal found\"\n\nTicket: {ticket_text}\n\"\"\"\n```\n",{"name":5,"description":7},"main","6158c1e4e112c06af2c7ac01b13b2ed7214c0fcf","plugins\u002Fzirkel\u002Fskills\u002Fzirkel-optimize-instruction",0,"https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff","https:\u002F\u002Fanselmoo.github.io\u002Fwerkstoff\u002F","https:\u002F\u002Fgithub.com\u002FAnselmoo","Likes to Develop","2026-11-02 04:20:59",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Anselmoo\u002Fwerkstoff --skill zirkel-optimize-instruction",{"tool":39,"command":40},"bunx","bunx skills add Anselmoo\u002Fwerkstoff --skill zirkel-optimize-instruction",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Anselmoo\u002Fwerkstoff --skill zirkel-optimize-instruction","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Fplugins\u002Fzirkel\u002Fskills\u002Fzirkel-optimize-instruction\u002FSKILL.md",true,[],[48,55,62,67,72,77],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M79AJTRBNBX03WWKYJ8ENM45","toy-check","A skill that checks things in the repository and reports what it finds.","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Ftest\u002Fworkflows\u002Ffixtures\u002Ftoy-plugin\u002Fskills\u002Ftoy-check\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M79AJS292F3HTDRXWZVRSN5B","demo-check","Reports which generated files changed since the last generation run. Use when the user asks what drifted. Read-only; never edits a file.","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Ftest\u002Fplugins\u002Ffixtures\u002Fnacharbeit-uncompleted-run\u002Fplugins\u002Fdemo\u002Fskills\u002Fdemo-check\u002FSKILL.md",[],[],{"skillNo":63,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M79AJP4TFQXKT1AAK1WC1JYK","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Ftest\u002Fplugins\u002Ffixtures\u002Fnacharbeit-stale-lock\u002Fplugins\u002Fdemo\u002Fskills\u002Fdemo-check\u002FSKILL.md",[],[],{"skillNo":68,"name":57,"nameZh":6,"description":58,"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},"01M79AJM6Y50WP3G2BR4H0M60Z","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Ftest\u002Fplugins\u002Ffixtures\u002Fnacharbeit-preflight-mixed\u002Fplugins\u002Fdemo\u002Fskills\u002Fdemo-check\u002FSKILL.md",[],[],{"skillNo":73,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M79AJGR6DMT8KCCK071V78XM","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Ftest\u002Fplugins\u002Ffixtures\u002Fnacharbeit-hooks-shape\u002Fplugins\u002Fdemo\u002Fskills\u002Fdemo-check\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M79AJBJ4CHC4PZVWKERWF3HF","zirkel-verify-assumptions","Checks exactly ONE named assumption against real evidence in at most 3 steps and reports one outcome: confidence raised (>=90), reading changed, or still unresolved. Use to resolve a single load-bearing uncertainty — typically a blocking entry surfaced by zirkel-clarify-scope: \"verify this one assumption\", \"is it actually true that X\", \"check this before we rely on it\". For multiple uncertainties, invoke once per uncertainty — the step budget is never shared.","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Fplugins\u002Fzirkel\u002Fskills\u002Fzirkel-verify-assumptions\u002FSKILL.md",[],[]]