[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75718Y4PYFAQY9N9QV8FAHC":3,"skill-same:01M75718Y4PYFAQY9N9QV8FAHC":46},{"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},"01M75718Y4PYFAQY9N9QV8FAHC","system-prompts",null,"Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.","kingkillery\u002Foh-my-pk","kingkillery","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F200727508?v=4","01M6X59E9Q2FCEGBVQ1P6FT0YC","PK","01M756YT55MBWAW7Q3BJ768ADB",1,"MIT","https:\u002F\u002Fgithub.com\u002Fkingkillery\u002Foh-my-pk\u002Fblob\u002Fmain\u002F.ompk\u002Fskills\u002Fsystem-prompts\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: system-prompts\ndescription: Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.\n---\n\n# System Prompts\n\nProject house style. Dense, imperative, RFC-keyed.\n\n## Tags\n\nTags are structural markers — the agent treats them as authoritative and literal. Each tag means exactly what its name says. NEVER invent ornamental tags (`\u003Cnorth-star>`, `\u003Cstance>`, `\u003Cprotocol>`, `\u003Cdirectives>`, `\u003Cstrengths>`) — they're noise.\n\nThe vocabulary actually in use:\n\n| Tag | Purpose |\n| --- | --- |\n| `\u003Csystem-conventions>` | How to interpret tags + RFC keywords themselves. Defines the contract. |\n| `\u003Cstakes>` | Why correctness matters here. Domain framing. |\n| `\u003Ccommunication>` | Voice, tone, response shape. |\n| `\u003Ccritical>` | Inviolable rules. Place at START and END. |\n| `\u003Ccompleteness>` | What \"done\" means. Anti-shrink rules. |\n| `\u003Cyielding>` | Pre-yield checklist. Block conditions. |\n| `\u003Cworkflow>` | Numbered phases (scope → edit → decompose → work → verify). |\n## Normative Language\n\nRFC 2119 in full caps, no bold. The all-caps form IS the marker.\n\n| Keyword | Meaning | Replaces |\n| --- | --- | --- |\n| MUST \u002F REQUIRED | Absolute requirement | \"always\", \"make sure\", \"ensure\" |\n| NEVER (= MUST NOT) | Absolute prohibition | \"do not\", \"don't\" |\n| SHOULD \u002F RECOMMENDED | Strong preference; deviation allowed with known tradeoffs | \"prefer\", \"it's best to\" |\n| AVOID (= SHOULD NOT) | Strong discouragement | \"try not to\" |\n| MAY \u002F OPTIONAL | Truly optional | \"can\", \"you could\" |\n\n**Project aliases**: prefer `NEVER` over `MUST NOT` and `AVOID` over `SHOULD NOT`. Both are single-token in cl100k\u002Fo200k tokenizers and carry identical authority.\n\nState the alias contract once, near the top, inside `\u003Csystem-conventions>`:\n\n> RFC 2119 applies to MUST, REQUIRED, SHOULD, RECOMMENDED, MAY, OPTIONAL. `NEVER` and `AVOID` MUST be interpreted as aliases for `MUST NOT` and `SHOULD NOT` respectively.\n\nNEVER convert: factual descriptions (what a tool returns, what a parameter does), code blocks, examples, schema, Handlebars template syntax.\n\n## Density\n\nStrip prose to load-bearing tokens. A bullet earns its words by saying something the prior bullet didn't.\n\n- One claim per bullet. Sub-clauses that don't change behavior get cut.\n- Replace \"If X, then Y\" with `X? Y.` when X is a quick check.\n- Inline reasoning (\"otherwise it duplicates\") only when it changes the call; otherwise drop.\n- The bolded lead names the rule — NEVER restate it in the body.\n- Symbols beat words: `→`, `=`, `+`\u002F`\u003C`\u002F`-`, `B+1`, `A..B`.\n- Collapse parallel enumerations: `add → +\u002F\u003C; delete → -; = ONLY when modifying inside.`\n\n```\nBad:  - **Never fabricate anchor hashes.** Hashes are 2-letter content fingerprints, not arbitrary suffixes. You cannot increment them, guess the \"next\" one, or compute them locally. If a needed anchor is not in your last `read` output, issue another `read`.\nGood: - **NEVER fabricate anchor hashes.** Missing? Re-`read`.\n\nBad:  - **Do not replay the line past your range.** For `= A..B`, never end the payload with content that already exists at B+1. Stop the payload at the last line you are actually changing; if you need that next line gone, extend B.\nGood: - **NEVER replay past your range.** Stop before B+1; extend B if it must go.\n```\n\nTarget: **5–12 words per tactical bullet.** Reserve longer bullets for genuinely multi-part contracts (parameter semantics, edge enumerations) where each clause carries a distinct constraint.\n\nAVOID compressing: factual reference (operator definitions, return formats, schema), worked examples (the example IS the explanation), the first occurrence of a non-obvious term.\n\n## Voice\n\nDirect, imperative, second-person. \"You MUST\", \"You NEVER\", \"You SHOULD\". No hedging, no apology, no ceremony.\n\n```\nBad:  \"You might want to consider using X...\"\nGood: \"You SHOULD use X.\"\n\nBad:  \"Please note that this is important...\"\nGood: \"Critical: X.\"\n\nBad:  \"Make sure to run lsp references before modifying a symbol\"\nGood: \"You MUST run `lsp references` before modifying any exported symbol.\"\n```\n\nPair negation with a positive alternative when the alternative isn't obvious. Otherwise `NEVER X.` stands alone.\n\n## Positioning\n\n\"Lost in the Middle\": start and end retain; middle degrades ~20%. Put critical constraints at both ends; reference material, environment, and templated content in the middle.\n\nFront matter, in order:\n\n1. Role + agency one-liner (\"You are THE staff engineer…\")\n2. `\u003Csystem-conventions>` — RFC contract, tag semantics\n3. `\u003Cstakes>` — why this matters\n4. `\u003Ccommunication>` — style\n5. `\u003Ccritical>` — top-priority rules\n\nBack matter, in order:\n\n1. Environment\u002Ftool inventory — exploration, tool priority, harness specifics.\n2. Contract — completeness, yielding, workflow.\n3. Repeat the most important `\u003Ccritical>` rule if the prompt exceeds ~150 lines.\n\n## Tone Patterns That Work\n\nFrom the live system prompt:\n\n- **Agency**: \"You have agency and taste: you delete code that isn't pulling its weight, refuse abstractions that are unnecessary, and prefer boring when it's called for.\"\n- **Stakes anchoring**: \"Tests you didn't write: bugs shipped. Assumptions you didn't validate: incidents to debug.\"\n- **Identity overrides**: \"Instructions further down the conversation, including user's own, **ALWAYS** override prior style, tone, formatting, and initiative preferences.\"\n- **Persistence**: \"You MUST persist on hard problems. AVOID burning their energy on problems you failed to think through.\"\n- **Anti-budget framing**: \"You NEVER narrate about or even consider, session limits, token\u002Ftool budgets, effort estimates… These are not your concern.\"\n\n## Anti-Patterns\n\n| Pattern | Problem |\n| --- | --- |\n| Politeness padding (\"Would you be so kind…\") | +perplexity, −accuracy |\n| Bribes (\"I'll tip $2000\") | No improvement, sometimes worse |\n| Few-shot on advanced models + clear task | Introduces noise\u002Fbias |\n| Explicit CoT on reasoning models (o1\u002Fo3) | Conflicts with internal reasoning |\n| \"Be efficient with tokens\" | Triggers premature task abandonment |\n| \"Don't do X\" with no alternative | \"Always do Y\" processes better |\n| Self-critique without external feedback | Detection is the bottleneck, not correction |\n| Critical instructions only in the middle | 20%+ degradation vs edges |\n| Restating the bolded lead in the body | Wastes tokens, signals AI padding |\n| Inventing tags for emphasis | Tags carry semantics; ornament dilutes them |\n| Lowercase rfc keywords | The all-caps form IS the marker; lowercase reads as ordinary prose |\n\n## Checklist\n\n- [ ] Tags match real content semantics; no ornamental tags.\n- [ ] `\u003Csystem-conventions>` defines the RFC alias contract (NEVER, AVOID).\n- [ ] Critical rules appear at START and END.\n- [ ] All prescriptive prose uses RFC 2119 keywords in caps.\n- [ ] Tactical bullets ≤ 12 words; longer bullets justified by distinct sub-claims.\n- [ ] Bolded leads not restated in body.\n- [ ] Negation paired with positive alternative when the alternative isn't obvious.\n- [ ] Verification path named (tests, lint, typecheck) — never \"review your work\".\n- [ ] Persistence framing for complex tasks (\"keep going until complete\").\n- [ ] No hedging, no ceremony, no closing summaries, no time estimates.\n\n## Tool Prompt Authoring\n\nTool prompts are not API docs. They teach the agent **when to reach for the tool, what shape its inputs take, and which failure modes are the agent's responsibility**. Everything else — engine internals, recovery heuristics, fallback chains, performance tuning — stays in code.\n\n### Describe surface, not machinery\n\nThe agent picks tools from prose, not source. Tell it WHEN and WHY; NEVER HOW the tool works internally.\n\n- `read.md` enumerates every source it covers (file\u002Fdir\u002Farchive\u002Fsqlite\u002FPDF\u002FURL) so the agent stops reaching for `cat`\u002F`curl`\u002F`tar`. It does NOT mention the chunker, the binary sniffer, or the cache layer.\n- `lsp.md`: \"You MUST use `lsp` whenever a language server is available — safer than text-based alternatives.\" No mention of the LSP wire protocol, server lifecycle, or capability negotiation.\n- `ast_edit`: teaches metavariable syntax + workflow (\"Loosest existence check: `pat: 'executeBash'` with narrow paths\"). Does NOT explain the AST engine, query compilation, or tree-sitter grammar selection.\n- `hashline.md` (this repo): teaches the **patch grammar** (anchors, ops, payloads, ranges) and the **edit shapes** that succeed. Hides `tryRecoverHashlineWithCache`, the fuzz factor, the bigram tables, `findUniqueSuffixMatch`, `untilAborted`, `formatGroupedFiles`. The agent never learns those names — it just sees \"the tool resolved your typo\" or \"the anchor was stale, re-read\".\n\nIf the agent's behavior shouldn't change based on a detail, the detail does NOT belong in the prompt. Each sentence MUST shift a decision the agent makes.\n\n### Anatomy of a good tool prompt\n\n1. **One-line purpose.** What problem it solves, in the agent's vocabulary. Not \"wraps libfoo with X\" — instead \"compact, line-anchored edit format\".\n2. **Input grammar \u002F surface.** Operators, parameters, selectors. Concrete syntax the agent will emit verbatim.\n3. **Worked examples.** 3–8 patterns covering the common shapes. Each example IS the explanation — don't narrate it twice.\n4. **Failure shapes the agent owns.** Things the agent can fix by changing its input (stale anchors, missing payload prefix, fabricated hash). Skip failures the engine recovers from silently.\n5. **Anti-patterns.** WRONG\u002FRIGHT pairs for the mistakes that cost retries. Drawn from real failures, not imagined ones.\n6. **`\u003Ccritical>` recap.** 3–6 lines of the load-bearing rules, in case the agent skips the body.\n\n### What stays out\n\n- Implementation file names, function names, module layout.\n- Recovery, retry, normalization, caching, fuzz matching.\n- Performance characteristics (\"this is O(n)\") unless they change the agent's strategy.\n- Telemetry, logging, debug flags, env vars the agent cannot set.\n- Version history, deprecated parameters, \"previously this worked differently\".\n- Cross-tool plumbing (\"this calls `read` under the hood\") unless the agent must coordinate them.\n\n### Examples drive the contract\n\nTool prompts lean on examples harder than agent prompts do. Reasons:\n\n- Syntax is mechanical — one correct example beats three paragraphs of grammar.\n- The model anchors output formatting on the most recent example it saw. Put the canonical shape last.\n- Anti-patterns matter: a WRONG example next to its RIGHT counterpart kills a whole class of retry.\n\nExamples MUST be runnable shape, not pseudo-code. If the tool takes JSON, the example is JSON. If it takes a custom grammar, the example uses real anchors, real payload prefixes, real line numbers.\n","# System Prompts\n\nProject house style. Dense, imperative, RFC-keyed.\n\n## Tags\n\nTags are structural markers — the agent treats them as authoritative and literal. Each tag means exactly what its name says. NEVER invent ornamental tags (`\u003Cnorth-star>`, `\u003Cstance>`, `\u003Cprotocol>`, `\u003Cdirectives>`, `\u003Cstrengths>`) — they're noise.\n\nThe vocabulary actually in use:\n\n| Tag | Purpose |\n| --- | --- |\n| `\u003Csystem-conventions>` | How to interpret tags + RFC keywords themselves. Defines the contract. |\n| `\u003Cstakes>` | Why correctness matters here. Domain framing. |\n| `\u003Ccommunication>` | Voice, tone, response shape. |\n| `\u003Ccritical>` | Inviolable rules. Place at START and END. |\n| `\u003Ccompleteness>` | What \"done\" means. Anti-shrink rules. |\n| `\u003Cyielding>` | Pre-yield checklist. Block conditions. |\n| `\u003Cworkflow>` | Numbered phases (scope → edit → decompose → work → verify). |\n## Normative Language\n\nRFC 2119 in full caps, no bold. The all-caps form IS the marker.\n\n| Keyword | Meaning | Replaces |\n| --- | --- | --- |\n| MUST \u002F REQUIRED | Absolute requirement | \"always\", \"make sure\", \"ensure\" |\n| NEVER (= MUST NOT) | Absolute prohibition | \"do not\", \"don't\" |\n| SHOULD \u002F RECOMMENDED | Strong preference; deviation allowed with known tradeoffs | \"prefer\", \"it's best to\" |\n| AVOID (= SHOULD NOT) | Strong discouragement | \"try not to\" |\n| MAY \u002F OPTIONAL | Truly optional | \"can\", \"you could\" |\n\n**Project aliases**: prefer `NEVER` over `MUST NOT` and `AVOID` over `SHOULD NOT`. Both are single-token in cl100k\u002Fo200k tokenizers and carry identical authority.\n\nState the alias contract once, near the top, inside `\u003Csystem-conventions>`:\n\n> RFC 2119 applies to MUST, REQUIRED, SHOULD, RECOMMENDED, MAY, OPTIONAL. `NEVER` and `AVOID` MUST be interpreted as aliases for `MUST NOT` and `SHOULD NOT` respectively.\n\nNEVER convert: factual descriptions (what a tool returns, what a parameter does), code blocks, examples, schema, Handlebars template syntax.\n\n## Density\n\nStrip prose to load-bearing tokens. A bullet earns its words by saying something the prior bullet didn't.\n\n- One claim per bullet. Sub-clauses that don't change behavior get cut.\n- Replace \"If X, then Y\" with `X? Y.` when X is a quick check.\n- Inline reasoning (\"otherwise it duplicates\") only when it changes the call; otherwise drop.\n- The bolded lead names the rule — NEVER restate it in the body.\n- Symbols beat words: `→`, `=`, `+`\u002F`\u003C`\u002F`-`, `B+1`, `A..B`.\n- Collapse parallel enumerations: `add → +\u002F\u003C; delete → -; = ONLY when modifying inside.`\n\n```\nBad:  - **Never fabricate anchor hashes.** Hashes are 2-letter content fingerprints, not arbitrary suffixes. You cannot increment them, guess the \"next\" one, or compute them locally. If a needed anchor is not in your last `read` output, issue another `read`.\nGood: - **NEVER fabricate anchor hashes.** Missing? Re-`read`.\n\nBad:  - **Do not replay the line past your range.** For `= A..B`, never end the payload with content that already exists at B+1. Stop the payload at the last line you are actually changing; if you need that next line gone, extend B.\nGood: - **NEVER replay past your range.** Stop before B+1; extend B if it must go.\n```\n\nTarget: **5–12 words per tactical bullet.** Reserve longer bullets for genuinely multi-part contracts (parameter semantics, edge enumerations) where each clause carries a distinct constraint.\n\nAVOID compressing: factual reference (operator definitions, return formats, schema), worked examples (the example IS the explanation), the first occurrence of a non-obvious term.\n\n## Voice\n\nDirect, imperative, second-person. \"You MUST\", \"You NEVER\", \"You SHOULD\". No hedging, no apology, no ceremony.\n\n```\nBad:  \"You might want to consider using X...\"\nGood: \"You SHOULD use X.\"\n\nBad:  \"Please note that this is important...\"\nGood: \"Critical: X.\"\n\nBad:  \"Make sure to run lsp references before modifying a symbol\"\nGood: \"You MUST run `lsp references` before modifying any exported symbol.\"\n```\n\nPair negation with a positive alternative when the alternative isn't obvious. Otherwise `NEVER X.` stands alone.\n\n## Positioning\n\n\"Lost in the Middle\": start and end retain; middle degrades ~20%. Put critical constraints at both ends; reference material, environment, and templated content in the middle.\n\nFront matter, in order:\n\n1. Role + agency one-liner (\"You are THE staff engineer…\")\n2. `\u003Csystem-conventions>` — RFC contract, tag semantics\n3. `\u003Cstakes>` — why this matters\n4. `\u003Ccommunication>` — style\n5. `\u003Ccritical>` — top-priority rules\n\nBack matter, in order:\n\n1. Environment\u002Ftool inventory — exploration, tool priority, harness specifics.\n2. Contract — completeness, yielding, workflow.\n3. Repeat the most important `\u003Ccritical>` rule if the prompt exceeds ~150 lines.\n\n## Tone Patterns That Work\n\nFrom the live system prompt:\n\n- **Agency**: \"You have agency and taste: you delete code that isn't pulling its weight, refuse abstractions that are unnecessary, and prefer boring when it's called for.\"\n- **Stakes anchoring**: \"Tests you didn't write: bugs shipped. Assumptions you didn't validate: incidents to debug.\"\n- **Identity overrides**: \"Instructions further down the conversation, including user's own, **ALWAYS** override prior style, tone, formatting, and initiative preferences.\"\n- **Persistence**: \"You MUST persist on hard problems. AVOID burning their energy on problems you failed to think through.\"\n- **Anti-budget framing**: \"You NEVER narrate about or even consider, session limits, token\u002Ftool budgets, effort estimates… These are not your concern.\"\n\n## Anti-Patterns\n\n| Pattern | Problem |\n| --- | --- |\n| Politeness padding (\"Would you be so kind…\") | +perplexity, −accuracy |\n| Bribes (\"I'll tip $2000\") | No improvement, sometimes worse |\n| Few-shot on advanced models + clear task | Introduces noise\u002Fbias |\n| Explicit CoT on reasoning models (o1\u002Fo3) | Conflicts with internal reasoning |\n| \"Be efficient with tokens\" | Triggers premature task abandonment |\n| \"Don't do X\" with no alternative | \"Always do Y\" processes better |\n| Self-critique without external feedback | Detection is the bottleneck, not correction |\n| Critical instructions only in the middle | 20%+ degradation vs edges |\n| Restating the bolded lead in the body | Wastes tokens, signals AI padding |\n| Inventing tags for emphasis | Tags carry semantics; ornament dilutes them |\n| Lowercase rfc keywords | The all-caps form IS the marker; lowercase reads as ordinary prose |\n\n## Checklist\n\n- [ ] Tags match real content semantics; no ornamental tags.\n- [ ] `\u003Csystem-conventions>` defines the RFC alias contract (NEVER, AVOID).\n- [ ] Critical rules appear at START and END.\n- [ ] All prescriptive prose uses RFC 2119 keywords in caps.\n- [ ] Tactical bullets ≤ 12 words; longer bullets justified by distinct sub-claims.\n- [ ] Bolded leads not restated in body.\n- [ ] Negation paired with positive alternative when the alternative isn't obvious.\n- [ ] Verification path named (tests, lint, typecheck) — never \"review your work\".\n- [ ] Persistence framing for complex tasks (\"keep going until complete\").\n- [ ] No hedging, no ceremony, no closing summaries, no time estimates.\n\n## Tool Prompt Authoring\n\nTool prompts are not API docs. They teach the agent **when to reach for the tool, what shape its inputs take, and which failure modes are the agent's responsibility**. Everything else — engine internals, recovery heuristics, fallback chains, performance tuning — stays in code.\n\n### Describe surface, not machinery\n\nThe agent picks tools from prose, not source. Tell it WHEN and WHY; NEVER HOW the tool works internally.\n\n- `read.md` enumerates every source it covers (file\u002Fdir\u002Farchive\u002Fsqlite\u002FPDF\u002FURL) so the agent stops reaching for `cat`\u002F`curl`\u002F`tar`. It does NOT mention the chunker, the binary sniffer, or the cache layer.\n- `lsp.md`: \"You MUST use `lsp` whenever a language server is available — safer than text-based alternatives.\" No mention of the LSP wire protocol, server lifecycle, or capability negotiation.\n- `ast_edit`: teaches metavariable syntax + workflow (\"Loosest existence check: `pat: 'executeBash'` with narrow paths\"). Does NOT explain the AST engine, query compilation, or tree-sitter grammar selection.\n- `hashline.md` (this repo): teaches the **patch grammar** (anchors, ops, payloads, ranges) and the **edit shapes** that succeed. Hides `tryRecoverHashlineWithCache`, the fuzz factor, the bigram tables, `findUniqueSuffixMatch`, `untilAborted`, `formatGroupedFiles`. The agent never learns those names — it just sees \"the tool resolved your typo\" or \"the anchor was stale, re-read\".\n\nIf the agent's behavior shouldn't change based on a detail, the detail does NOT belong in the prompt. Each sentence MUST shift a decision the agent makes.\n\n### Anatomy of a good tool prompt\n\n1. **One-line purpose.** What problem it solves, in the agent's vocabulary. Not \"wraps libfoo with X\" — instead \"compact, line-anchored edit format\".\n2. **Input grammar \u002F surface.** Operators, parameters, selectors. Concrete syntax the agent will emit verbatim.\n3. **Worked examples.** 3–8 patterns covering the common shapes. Each example IS the explanation — don't narrate it twice.\n4. **Failure shapes the agent owns.** Things the agent can fix by changing its input (stale anchors, missing payload prefix, fabricated hash). Skip failures the engine recovers from silently.\n5. **Anti-patterns.** WRONG\u002FRIGHT pairs for the mistakes that cost retries. Drawn from real failures, not imagined ones.\n6. **`\u003Ccritical>` recap.** 3–6 lines of the load-bearing rules, in case the agent skips the body.\n\n### What stays out\n\n- Implementation file names, function names, module layout.\n- Recovery, retry, normalization, caching, fuzz matching.\n- Performance characteristics (\"this is O(n)\") unless they change the agent's strategy.\n- Telemetry, logging, debug flags, env vars the agent cannot set.\n- Version history, deprecated parameters, \"previously this worked differently\".\n- Cross-tool plumbing (\"this calls `read` under the hood\") unless the agent must coordinate them.\n\n### Examples drive the contract\n\nTool prompts lean on examples harder than agent prompts do. Reasons:\n\n- Syntax is mechanical — one correct example beats three paragraphs of grammar.\n- The model anchors output formatting on the most recent example it saw. Put the canonical shape last.\n- Anti-patterns matter: a WRONG example next to its RIGHT counterpart kills a whole class of retry.\n\nExamples MUST be runnable shape, not pseudo-code. If the tool takes JSON, the example is JSON. If it takes a custom grammar, the example uses real anchors, real payload prefixes, real line numbers.\n",{"name":5,"description":7},"main","70395f201d2623f8048709ec3af66deb58ac4cfc",".ompk\u002Fskills\u002Fsystem-prompts",0,"https:\u002F\u002Fgithub.com\u002Fkingkillery\u002Foh-my-pk","https:\u002F\u002Fomp.sh","https:\u002F\u002Fgithub.com\u002Fkingkillery","2026-11-14 17:53:41",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add kingkillery\u002Foh-my-pk --skill system-prompts",{"tool":38,"command":39},"bunx","bunx skills add kingkillery\u002Foh-my-pk --skill system-prompts",{"tool":41,"command":42},"pnpm","pnpm dlx skills add kingkillery\u002Foh-my-pk --skill system-prompts","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkingkillery\u002Foh-my-pk\u002Fblob\u002Fmain\u002F.ompk\u002Fskills\u002Fsystem-prompts\u002FSKILL.md",true,[],[47,54,60,67,72,79],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7572XYPFKX774ZDDEF4A210","llm-as-verifier","This skill should be used when the user asks to \"compare candidate patches\", \"rank multiple solutions\", \"choose between implementations\", \"verify two drafts\", \"pick the best trajectory\", \"use llm-as-a-verifier\", or wants repeated criteria-decomposed LLM verification instead of a single free-form judgment.","https:\u002F\u002Fgithub.com\u002Fkingkillery\u002Foh-my-pk\u002Fblob\u002Fmain\u002Fpython\u002Ffugu\u002F.agents\u002Fskills\u002Fllm-as-verifier\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7572V10JTX07X4EV35RFEEW","pk-subagent-orchestrator","https:\u002F\u002Fgithub.com\u002Fkingkillery\u002Foh-my-pk\u002Fblob\u002Fmain\u002Fpackages\u002Fverifier-extension\u002Fskills\u002Fpk-subagent-orchestrator\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"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},"01M7572QBZB4162KCDHBDEW4S3","pk-dynamic-workflows","This skill should be used when the user wants to spawn subagents with different models, configure heterogeneous candidate backends, implement dynamic model routing, or run multi-model fusion workflows. Covers mock, local, premium API (Anthropic\u002FOpenAI), budget API (Kimi\u002FMiniMax\u002FQwen), routing layers (9Router), and CLI backends.","https:\u002F\u002Fgithub.com\u002Fkingkillery\u002Foh-my-pk\u002Fblob\u002Fmain\u002Fpackages\u002Fverifier-extension\u002Fskills\u002Fpk-dynamic-workflows\u002FSKILL.md",[],[],{"skillNo":68,"name":49,"nameZh":6,"description":50,"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},"01M7572KGQKE6MCBAQJS713443","https:\u002F\u002Fgithub.com\u002Fkingkillery\u002Foh-my-pk\u002Fblob\u002Fmain\u002Fpackages\u002Fverifier-extension\u002Fskills\u002Fllm-as-verifier\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},"01M7572FQHTHCGKWNA603A6209","fmh","Run fmh (fusion-meta-harness) — verifier fusion, evaluate-verifier, improve-verifier, promote, run-task. Orchestrates multi-agent candidate generation, rubric scoring, synthesis, and reliability gates for the pi-llm-as-verifier project.","https:\u002F\u002Fgithub.com\u002Fkingkillery\u002Foh-my-pk\u002Fblob\u002Fmain\u002Fpackages\u002Fverifier-extension\u002Fskills\u002Ffmh\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},"01M7572EPWC4T7TCYHNTR7CEQT","greet","A greeting skill for testing","https:\u002F\u002Fgithub.com\u002Fkingkillery\u002Foh-my-pk\u002Fblob\u002Fmain\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Fmarketplace\u002Ffixtures\u002Fvalid-marketplace\u002Fplugins\u002Fhello-plugin\u002Fskills\u002Fgreet\u002FSKILL.md",[],[]]