[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7571NP3H19FMBWW7EY9CQ77":3,"skill-same:01M7571NP3H19FMBWW7EY9CQ77":55},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7571NP3H19FMBWW7EY9CQ77","tool-prompt-optimization",null,"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\u002Ftool-prompt-optimization\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: tool-prompt-optimization\ndescription: Optimize the description prompts an AI agent reads to learn its built-in tools (the `.md` files under prompts\u002Ftools\u002F). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool prompt vs what stays in code. Use when auditing, trimming, writing, or reviewing tool prompts, deciding what schema field descriptions already cover, or testing schema-vs-prompt overlap before deleting prompt lines.\n---\n\n# Tool Prompt Optimization\n\nA tool's description prompt and its parameter schema overlap. Whatever a model can reconstruct from the **schema + tool name + a blank outline** is a *prune candidate* — the schema may already teach it. This skill measures that overlap so you prune with evidence, not vibes. A candidate is never an automatic delete (see caveats — history first).\n\nCore move: give a model only `(name, JSON schema, outline)` and have it predict the prompt body. Lines it predicts reliably are *prune candidates*. Lines it never recovers are *load-bearing* — keep them.\n\n## Run the probe\n\n`scripts\u002Fprobe.ts` routes through `@pk-nerdsaver-ai\u002Fpi-ai` (`completeSimple`) so model\u002Fauth\u002Fprovider behavior matches production.\n\n```bash\nbun .ompk\u002Fskills\u002Ftool-prompt-optimization\u002Fscripts\u002Fprobe.ts \\\n  --schema \u003Cfile|json> --template \u003Cfile|text> --name \u003Ctool_name>\n```\n\n- `--schema` and `--template` are the only required inputs (file path or inline value).\n- No `--model` → 3-model panel (`fireworks\u002Fkimi-k2.7-code`, `anthropic\u002Fclaude-opus-4-8`, `openai\u002Fgpt-5.5`) × `--samples` (default 3). Needs `FIREWORKS_API_KEY` \u002F `ANTHROPIC_API_KEY` \u002F `OPENAI_API_KEY`.\n- `--model p\u002Fid,p\u002Fid` overrides the panel; `--samples N`, `--max-tokens`, `--json` tune it.\n- Programmatic: `import { probe } from \".\u002Fscripts\u002Fprobe.ts\"` → `{ prompt, results: [{ model, samples: [{ text, stopReason, usage, error }] }] }`.\n\n### Builtin shortcut (preferred for this repo's tools)\n\nSkip building the two inputs by hand — `scripts\u002Fprobe-builtin.ts` instantiates the live tool, pulls the EXACT wire schema (`toolWireSchema`) and rendered prompt (`tool.description`), and derives the outline for you:\n\n```bash\nbun .ompk\u002Fskills\u002Ftool-prompt-optimization\u002Fscripts\u002Fprobe-builtin.ts --tool \u003Cname> [--no-summary] [--show]\n```\n\n- `--show` prints the resolved schema + derived outline + real prompt and exits (no API calls) — use it to eyeball inputs before spending tokens.\n- `--no-summary` runs the ablation (blank the summary line) directly.\n- `--samples` \u002F `--model` \u002F `--max-tokens` \u002F `--json` forward to the panel; output ends with the REAL prompt so you can diff in place.\n- It bypasses the settings allowlist via the factory map, so gated tools (`irc`, `github`, …) resolve. If a tool refuses to construct (an availability gate like a missing `gh` CLI), fall back to the manual inputs below.\n\n## Build the two inputs\n\n**Schema** — use the *wire* schema the model actually sees, not a hand-sketch. For this repo's arktype tool schemas:\n\n```ts\nimport { arkToWireSchema } from \"@pk-nerdsaver-ai\u002Fpi-ai\"; \u002F\u002F or toolWireSchema(tool)\nJSON.stringify(arkToWireSchema(toolSchema), null, 2);\n```\n\nInclude `required` and `additionalProperties: false` — omitting them makes the model infer looser usage than the real tool.\n\n**Template (outline)** — the real `.md`'s structure with bodies blanked: the one-line summary, then each section tag with `...` inside.\n\n```\nStructural code search via native ast-grep AST matching.\n\n\u003Cinstruction>\n...\n\u003C\u002Finstruction>\n\n\u003Coutput>\n...\n\u003C\u002Foutput>\n\n\u003Ccritical>\n...\n\u003C\u002Fcritical>\n```\n\n## Interpret results\n\nBucket every line of the real prompt against the predictions:\n\n- **Prune candidate** — content that is STABLE across samples AND agrees across models AND restates the schema (param names, types, \"required\", value examples already in a field `description`, clamp ranges already stated). The schema teaches it; the prompt repeats it.\n- **Keep** — content no model recovers: defaults and their direction (`gitignore` default true), cross-tool routing\u002Fescalation (\"NEVER shell out to `find`\u002F`fd` → use this tool\", \"broad exploration → Task subagent\"), exact output format (mtime sort, grouping, `artifact:\u002F\u002F` truncation), worked anti-patterns, and hard constraints invisible to a type (the AST metavariable grammar, C++ trailing `;`).\n\nA single sample is noise. Only treat overlap that is **stable across samples and models** as a prune *candidate* — and a candidate is not a verdict until its history clears (see caveats). You MUST NOT delete a line on inferability alone.\n\n## Caveats — read before deleting anything\n\n- **`git blame` before cutting — MUST, not SHOULD.** Many prompt lines were added on purpose after a real failure: a model that hallucinated a flag, shelled out, scanned the repo root, fabricated an anchor. They look redundant precisely because they now prevent the mistake. You MUST `git blame` (and read the commit\u002Fissue) every line you intend to cut; the history tells you whether it restates the schema or is scar tissue from an incident. Keep scar tissue. Inferability is necessary for pruning, NEVER sufficient.\n- **Memorization ≠ inference.** Public repos (this one included) may be in training data, so a model can *recite* `ast-grep.md` it never *inferred*. Tell: predictions naming repo-specific details absent from the schema (exact tool names, internal URI schemes, the `Task` subagent) are memorized, not derived — discount them.\n- **The outline leaks.** The summary line and section names are themselves hints. To isolate *schema-alone* inferability, run an ablation: a second pass with no summary line and generic section tags. Content that survives only with the summary present is \"summary-inferable\", not \"schema-inferable\".\n\n## Verdict pattern\n\nPer tool: predictions reproduce parameter mechanics and generic usage (already in the schema) but miss defaults, output shape, cross-tool routing, anti-patterns, and domain grammar. Prune the first set (after `git blame` clears each line); keep the second. Self-documenting flag tools (e.g. `find`) prune heavily; DSL\u002Fcapability tools (e.g. `read`, `ast_grep`) barely at all.\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","# Tool Prompt Optimization\n\nA tool's description prompt and its parameter schema overlap. Whatever a model can reconstruct from the **schema + tool name + a blank outline** is a *prune candidate* — the schema may already teach it. This skill measures that overlap so you prune with evidence, not vibes. A candidate is never an automatic delete (see caveats — history first).\n\nCore move: give a model only `(name, JSON schema, outline)` and have it predict the prompt body. Lines it predicts reliably are *prune candidates*. Lines it never recovers are *load-bearing* — keep them.\n\n## Run the probe\n\n`scripts\u002Fprobe.ts` routes through `@pk-nerdsaver-ai\u002Fpi-ai` (`completeSimple`) so model\u002Fauth\u002Fprovider behavior matches production.\n\n```bash\nbun .ompk\u002Fskills\u002Ftool-prompt-optimization\u002Fscripts\u002Fprobe.ts \\\n  --schema \u003Cfile|json> --template \u003Cfile|text> --name \u003Ctool_name>\n```\n\n- `--schema` and `--template` are the only required inputs (file path or inline value).\n- No `--model` → 3-model panel (`fireworks\u002Fkimi-k2.7-code`, `anthropic\u002Fclaude-opus-4-8`, `openai\u002Fgpt-5.5`) × `--samples` (default 3). Needs `FIREWORKS_API_KEY` \u002F `ANTHROPIC_API_KEY` \u002F `OPENAI_API_KEY`.\n- `--model p\u002Fid,p\u002Fid` overrides the panel; `--samples N`, `--max-tokens`, `--json` tune it.\n- Programmatic: `import { probe } from \".\u002Fscripts\u002Fprobe.ts\"` → `{ prompt, results: [{ model, samples: [{ text, stopReason, usage, error }] }] }`.\n\n### Builtin shortcut (preferred for this repo's tools)\n\nSkip building the two inputs by hand — `scripts\u002Fprobe-builtin.ts` instantiates the live tool, pulls the EXACT wire schema (`toolWireSchema`) and rendered prompt (`tool.description`), and derives the outline for you:\n\n```bash\nbun .ompk\u002Fskills\u002Ftool-prompt-optimization\u002Fscripts\u002Fprobe-builtin.ts --tool \u003Cname> [--no-summary] [--show]\n```\n\n- `--show` prints the resolved schema + derived outline + real prompt and exits (no API calls) — use it to eyeball inputs before spending tokens.\n- `--no-summary` runs the ablation (blank the summary line) directly.\n- `--samples` \u002F `--model` \u002F `--max-tokens` \u002F `--json` forward to the panel; output ends with the REAL prompt so you can diff in place.\n- It bypasses the settings allowlist via the factory map, so gated tools (`irc`, `github`, …) resolve. If a tool refuses to construct (an availability gate like a missing `gh` CLI), fall back to the manual inputs below.\n\n## Build the two inputs\n\n**Schema** — use the *wire* schema the model actually sees, not a hand-sketch. For this repo's arktype tool schemas:\n\n```ts\nimport { arkToWireSchema } from \"@pk-nerdsaver-ai\u002Fpi-ai\"; \u002F\u002F or toolWireSchema(tool)\nJSON.stringify(arkToWireSchema(toolSchema), null, 2);\n```\n\nInclude `required` and `additionalProperties: false` — omitting them makes the model infer looser usage than the real tool.\n\n**Template (outline)** — the real `.md`'s structure with bodies blanked: the one-line summary, then each section tag with `...` inside.\n\n```\nStructural code search via native ast-grep AST matching.\n\n\u003Cinstruction>\n...\n\u003C\u002Finstruction>\n\n\u003Coutput>\n...\n\u003C\u002Foutput>\n\n\u003Ccritical>\n...\n\u003C\u002Fcritical>\n```\n\n## Interpret results\n\nBucket every line of the real prompt against the predictions:\n\n- **Prune candidate** — content that is STABLE across samples AND agrees across models AND restates the schema (param names, types, \"required\", value examples already in a field `description`, clamp ranges already stated). The schema teaches it; the prompt repeats it.\n- **Keep** — content no model recovers: defaults and their direction (`gitignore` default true), cross-tool routing\u002Fescalation (\"NEVER shell out to `find`\u002F`fd` → use this tool\", \"broad exploration → Task subagent\"), exact output format (mtime sort, grouping, `artifact:\u002F\u002F` truncation), worked anti-patterns, and hard constraints invisible to a type (the AST metavariable grammar, C++ trailing `;`).\n\nA single sample is noise. Only treat overlap that is **stable across samples and models** as a prune *candidate* — and a candidate is not a verdict until its history clears (see caveats). You MUST NOT delete a line on inferability alone.\n\n## Caveats — read before deleting anything\n\n- **`git blame` before cutting — MUST, not SHOULD.** Many prompt lines were added on purpose after a real failure: a model that hallucinated a flag, shelled out, scanned the repo root, fabricated an anchor. They look redundant precisely because they now prevent the mistake. You MUST `git blame` (and read the commit\u002Fissue) every line you intend to cut; the history tells you whether it restates the schema or is scar tissue from an incident. Keep scar tissue. Inferability is necessary for pruning, NEVER sufficient.\n- **Memorization ≠ inference.** Public repos (this one included) may be in training data, so a model can *recite* `ast-grep.md` it never *inferred*. Tell: predictions naming repo-specific details absent from the schema (exact tool names, internal URI schemes, the `Task` subagent) are memorized, not derived — discount them.\n- **The outline leaks.** The summary line and section names are themselves hints. To isolate *schema-alone* inferability, run an ablation: a second pass with no summary line and generic section tags. Content that survives only with the summary present is \"summary-inferable\", not \"schema-inferable\".\n\n## Verdict pattern\n\nPer tool: predictions reproduce parameter mechanics and generic usage (already in the schema) but miss defaults, output shape, cross-tool routing, anti-patterns, and domain grammar. Prune the first set (after `git blame` clears each line); keep the second. Self-documenting flag tools (e.g. `find`) prune heavily; DSL\u002Fcapability tools (e.g. `read`, `ast_grep`) barely at all.\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",{},"main","70395f201d2623f8048709ec3af66deb58ac4cfc",".ompk\u002Fskills\u002Ftool-prompt-optimization",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":7,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add kingkillery\u002Foh-my-pk --skill tool-prompt-optimization",{"tool":37,"command":38},"bunx","bunx skills add kingkillery\u002Foh-my-pk --skill tool-prompt-optimization",{"tool":40,"command":41},"pnpm","pnpm dlx skills add kingkillery\u002Foh-my-pk --skill tool-prompt-optimization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkingkillery\u002Foh-my-pk\u002Fblob\u002Fmain\u002F.ompk\u002Fskills\u002Ftool-prompt-optimization\u002FSKILL.md",true,[45,51],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"scripts\u002Fprobe-builtin.ts","SCRIPT","脚本",6282,"https:\u002F\u002Fgithub.com\u002Fkingkillery\u002Foh-my-pk\u002Fblob\u002Fmain\u002F.ompk\u002Fskills\u002Ftool-prompt-optimization\u002Fscripts\u002Fprobe-builtin.ts",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"scripts\u002Fprobe.ts",8671,"https:\u002F\u002Fgithub.com\u002Fkingkillery\u002Foh-my-pk\u002Fblob\u002Fmain\u002F.ompk\u002Fskills\u002Ftool-prompt-optimization\u002Fscripts\u002Fprobe.ts",[56,63,69,76,81,88],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":18},"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":64,"name":65,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":18},"01M7572V10JTX07X4EV35RFEEW","pk-subagent-orchestrator","https:\u002F\u002Fgithub.com\u002Fkingkillery\u002Foh-my-pk\u002Fblob\u002Fmain\u002Fpackages\u002Fverifier-extension\u002Fskills\u002Fpk-subagent-orchestrator\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":18},"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":77,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M7572KGQKE6MCBAQJS713443","https:\u002F\u002Fgithub.com\u002Fkingkillery\u002Foh-my-pk\u002Fblob\u002Fmain\u002Fpackages\u002Fverifier-extension\u002Fskills\u002Fllm-as-verifier\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"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":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":18},"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",[],[]]