[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AP97151H1T1CV40VR9MJ2Q":3,"skill-same:01M7AP97151H1T1CV40VR9MJ2Q":51},{"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":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7AP97151H1T1CV40VR9MJ2Q","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.","Vinayak-RZ\u002FImproveness","Vinayak-RZ","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F179278780?v=4","01M7ANW079C0NQMM13ZJ9AFNNB","Vinayak Raizada","01M7ANW07W35RJP6KJQ6448V08",1,"MIT","https:\u002F\u002Fgithub.com\u002FVinayak-RZ\u002FImproveness\u002Fblob\u002Fmain\u002Foh-my-pi\u002F.omp\u002Fskills\u002Fsystem-prompts\u002FSKILL.md",[],[],"2026-11-15 14:19:17",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\nHouse style: dense, imperative, RFC-keyed.\n\nSmall models (≤2B; tiny\u002Fon-device, e.g. LFM2): MUST read [small-models.md](small-models.md). Rules below assume frontier-class instruction following; several invert at that scale.\n\n## Tags\n\nTags: authoritative, literal structural markers; meaning exactly matches name. NEVER invent ornamental tags: `\u003Cnorth-star>`, `\u003Cstance>`, `\u003Cprotocol>`, `\u003Cdirectives>`, `\u003Cstrengths>` — noise.\n\n|Tag|Purpose|\n|---|---|\n|`\u003Csystem-conventions>`|Tag\u002FRFC-keyword interpretation; contract.|\n|`\u003Cstakes>`|Correctness importance; domain framing.|\n|`\u003Ccommunication>`|Voice, tone, response shape.|\n|`\u003Ccritical>`|Inviolable rules; place at START and END.|\n|`\u003Ccompleteness>`|Done definition; anti-shrink rules.|\n|`\u003Cyielding>`|Pre-yield checklist; block conditions.|\n|`\u003Cworkflow>`|Numbered phases: scope → edit → decompose → work → verify.|\n\n## Normative Language\n\nRFC 2119: full caps, no bold; 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; known-tradeoff deviation allowed|\"prefer\", \"it's best to\"|\n|AVOID (= SHOULD NOT)|Strong discouragement|\"try not to\"|\n|MAY \u002F OPTIONAL|Truly optional|\"can\", \"you could\"|\n\nAliases: prefer `NEVER` to `MUST NOT`; `AVOID` to `SHOULD NOT`. Both: single-token in cl100k\u002Fo200k; identical authority.\n\nNear top, inside `\u003Csystem-conventions>`, state once:\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 (tool returns, parameter behavior), code blocks, examples, schema, or Handlebars template syntax.\n\n## Density\n\nLoad-bearing tokens only; every bullet adds a claim.\n\n- One claim\u002Fbullet; cut behavior-neutral subclauses.\n- Quick check `X? Y.` replaces “If X, then Y.”\n- Reasoning ONLY when it changes the call.\n- Bold lead names rule; NEVER restate in body.\n- Prefer `→`, `=`, `+`\u002F`\u003C`\u002F`-`, `B+1`, `A..B`.\n- Parallel edits: `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\nTactical bullets: 5–12 words. Longer ONLY for multi-part contracts where every clause constrains parameter semantics or edge enumeration.\n\nAVOID compressing factual reference (operator definitions, return formats, schema), worked examples, or first use of a non-obvious term.\n\n## Voice\n\nDirect, imperative, second-person: “You MUST\u002FNEVER\u002FSHOULD.” No hedging, apology, ceremony, closing summaries, or time estimates.\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\nNegation: pair positive alternative when non-obvious; otherwise `NEVER X.` alone.\n\n## Positioning\n\n“Lost in the Middle”: start\u002Fend retain; middle degrades ~20%. Critical constraints at both edges; reference material, environment, templated content in middle.\n\nFront matter:\n1. Role + agency one-liner (`You are THE staff engineer…`).\n2. `\u003Csystem-conventions>` — RFC contract, tag semantics.\n3. `\u003Cstakes>` — importance.\n4. `\u003Ccommunication>` — style.\n5. `\u003Ccritical>` — top-priority rules.\n\nBack matter:\n1. Environment\u002Ftool inventory — exploration, tool priority, harness specifics.\n2. Contract — completeness, yielding, workflow.\n3. Prompt >~150 lines: repeat most important `\u003Ccritical>` rule.\n\n## Tone Patterns That Work\n\nLive-system-prompt patterns:\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|Noise\u002Fbias|\n|Explicit CoT on reasoning models (o1\u002Fo3)|Conflicts with internal reasoning|\n|`\"Be efficient with tokens\"`|Premature task abandonment|\n|`\"Don't do X\"` without alternative|`\"Always do Y\"` processes better|\n|Self-critique without external feedback|Detection bottleneck, not correction|\n|Critical instructions only in middle|20%+ degradation vs edges|\n|Restating bold lead in body|Token waste; AI-padding signal|\n|Inventing emphasis tags|Tags have semantics; ornament dilutes|\n|Lowercase RFC keywords|All-caps is marker; lowercase ordinary prose|\n\n## Checklist\n\n- Tags match content; no ornamental tags.\n- `\u003Csystem-conventions>` defines `NEVER`\u002F`AVOID` aliases.\n- Critical rules at START and END.\n- Prescriptive prose: uppercase RFC 2119 keywords.\n- Tactical bullets ≤12 words unless distinct subclaims justify more.\n- NEVER restate bold lead in body.\n- Non-obvious negation gets positive alternative.\n- Name verification path (tests, lint, typecheck); NEVER “review your work”.\n- Complex tasks: persist until complete.\n- No hedging, ceremony, closing summaries, time estimates.\n\n## Tool Prompt Authoring\n\nTool prompts teach when to use the tool, input shape, and agent-owned failures — not API docs. Engine internals, recovery heuristics, fallback chains, performance tuning: code.\n\n### Surface, not machinery\n\nAgents choose tools from prose: state WHEN\u002FWHY; NEVER internal HOW.\n\n- `read.md`: enumerate every covered source — file\u002Fdir\u002Farchive\u002Fsqlite\u002FPDF\u002FURL — so agent avoids `cat`\u002F`curl`\u002F`tar`; omit chunker, binary sniffer, cache layer.\n- `lsp.md`: \"You MUST use `lsp` whenever a language server is available — safer than text-based alternatives.\" Omit LSP wire protocol, server lifecycle, capability negotiation.\n- `ast_edit`: teach metavariable syntax + workflow: \"Loosest existence check: `pat: 'executeBash'` with narrow paths\"; omit AST engine, query compilation, tree-sitter grammar selection.\n- `hashline.md` (this repo): teach **patch grammar** — anchors, ops, payloads, ranges — and successful **edit shapes**. NEVER expose `tryRecoverHashlineWithCache`, fuzz factor, bigram tables, `findUniqueSuffixMatch`, `untilAborted`, `formatGroupedFiles`; agent sees only \"the tool resolved your typo\" or \"the anchor was stale, re-read\".\n\nBehavior-invariant detail: exclude. Every sentence MUST shift an agent decision.\n\n### Good tool-prompt anatomy\n\n1. **One-line purpose** — agent-vocabulary problem; e.g. “compact, line-anchored edit format”, not “wraps libfoo with X”.\n2. **Input grammar \u002F surface** — operators, parameters, selectors; verbatim emitted syntax.\n3. **Worked examples** — 3–8 common shapes; each explains itself, no duplicate narration.\n4. **Agent-owned failure shapes** — input-fixable stale anchors, missing payload prefix, fabricated hash; skip silently recovered failures.\n5. **Anti-patterns** — real-failure WRONG\u002FRIGHT pairs that cost retries; not imagined failures.\n6. **`\u003Ccritical>` recap** — 3–6 load-bearing lines, for body-skipping agents.\n\n### Exclude\n\n- Implementation file\u002Ffunction names; module layout.\n- Recovery, retry, normalization, caching, fuzz matching.\n- Performance (`O(n)`) unless strategy-changing.\n- Telemetry, logging, debug flags, unsettable env vars.\n- Version history, deprecated parameters, “previously this worked differently”.\n- Cross-tool plumbing (`this calls \\`read\\` under the hood`) unless coordination required.\n\n### Examples drive the contract\n\nTool prompts rely on examples more than agent prompts:\n\n- Mechanical syntax: one correct example beats three grammar paragraphs.\n- Model anchors output format on latest example: canonical shape last.\n- Adjacent WRONG\u002FRIGHT eliminates a retry class.\n\nExamples MUST be runnable, not pseudo-code. JSON tool → JSON example; custom grammar → real anchors, payload prefixes, line numbers.\n","# System Prompts\n\nHouse style: dense, imperative, RFC-keyed.\n\nSmall models (≤2B; tiny\u002Fon-device, e.g. LFM2): MUST read [small-models.md](small-models.md). Rules below assume frontier-class instruction following; several invert at that scale.\n\n## Tags\n\nTags: authoritative, literal structural markers; meaning exactly matches name. NEVER invent ornamental tags: `\u003Cnorth-star>`, `\u003Cstance>`, `\u003Cprotocol>`, `\u003Cdirectives>`, `\u003Cstrengths>` — noise.\n\n|Tag|Purpose|\n|---|---|\n|`\u003Csystem-conventions>`|Tag\u002FRFC-keyword interpretation; contract.|\n|`\u003Cstakes>`|Correctness importance; domain framing.|\n|`\u003Ccommunication>`|Voice, tone, response shape.|\n|`\u003Ccritical>`|Inviolable rules; place at START and END.|\n|`\u003Ccompleteness>`|Done definition; anti-shrink rules.|\n|`\u003Cyielding>`|Pre-yield checklist; block conditions.|\n|`\u003Cworkflow>`|Numbered phases: scope → edit → decompose → work → verify.|\n\n## Normative Language\n\nRFC 2119: full caps, no bold; 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; known-tradeoff deviation allowed|\"prefer\", \"it's best to\"|\n|AVOID (= SHOULD NOT)|Strong discouragement|\"try not to\"|\n|MAY \u002F OPTIONAL|Truly optional|\"can\", \"you could\"|\n\nAliases: prefer `NEVER` to `MUST NOT`; `AVOID` to `SHOULD NOT`. Both: single-token in cl100k\u002Fo200k; identical authority.\n\nNear top, inside `\u003Csystem-conventions>`, state once:\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 (tool returns, parameter behavior), code blocks, examples, schema, or Handlebars template syntax.\n\n## Density\n\nLoad-bearing tokens only; every bullet adds a claim.\n\n- One claim\u002Fbullet; cut behavior-neutral subclauses.\n- Quick check `X? Y.` replaces “If X, then Y.”\n- Reasoning ONLY when it changes the call.\n- Bold lead names rule; NEVER restate in body.\n- Prefer `→`, `=`, `+`\u002F`\u003C`\u002F`-`, `B+1`, `A..B`.\n- Parallel edits: `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\nTactical bullets: 5–12 words. Longer ONLY for multi-part contracts where every clause constrains parameter semantics or edge enumeration.\n\nAVOID compressing factual reference (operator definitions, return formats, schema), worked examples, or first use of a non-obvious term.\n\n## Voice\n\nDirect, imperative, second-person: “You MUST\u002FNEVER\u002FSHOULD.” No hedging, apology, ceremony, closing summaries, or time estimates.\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\nNegation: pair positive alternative when non-obvious; otherwise `NEVER X.` alone.\n\n## Positioning\n\n“Lost in the Middle”: start\u002Fend retain; middle degrades ~20%. Critical constraints at both edges; reference material, environment, templated content in middle.\n\nFront matter:\n1. Role + agency one-liner (`You are THE staff engineer…`).\n2. `\u003Csystem-conventions>` — RFC contract, tag semantics.\n3. `\u003Cstakes>` — importance.\n4. `\u003Ccommunication>` — style.\n5. `\u003Ccritical>` — top-priority rules.\n\nBack matter:\n1. Environment\u002Ftool inventory — exploration, tool priority, harness specifics.\n2. Contract — completeness, yielding, workflow.\n3. Prompt >~150 lines: repeat most important `\u003Ccritical>` rule.\n\n## Tone Patterns That Work\n\nLive-system-prompt patterns:\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|Noise\u002Fbias|\n|Explicit CoT on reasoning models (o1\u002Fo3)|Conflicts with internal reasoning|\n|`\"Be efficient with tokens\"`|Premature task abandonment|\n|`\"Don't do X\"` without alternative|`\"Always do Y\"` processes better|\n|Self-critique without external feedback|Detection bottleneck, not correction|\n|Critical instructions only in middle|20%+ degradation vs edges|\n|Restating bold lead in body|Token waste; AI-padding signal|\n|Inventing emphasis tags|Tags have semantics; ornament dilutes|\n|Lowercase RFC keywords|All-caps is marker; lowercase ordinary prose|\n\n## Checklist\n\n- Tags match content; no ornamental tags.\n- `\u003Csystem-conventions>` defines `NEVER`\u002F`AVOID` aliases.\n- Critical rules at START and END.\n- Prescriptive prose: uppercase RFC 2119 keywords.\n- Tactical bullets ≤12 words unless distinct subclaims justify more.\n- NEVER restate bold lead in body.\n- Non-obvious negation gets positive alternative.\n- Name verification path (tests, lint, typecheck); NEVER “review your work”.\n- Complex tasks: persist until complete.\n- No hedging, ceremony, closing summaries, time estimates.\n\n## Tool Prompt Authoring\n\nTool prompts teach when to use the tool, input shape, and agent-owned failures — not API docs. Engine internals, recovery heuristics, fallback chains, performance tuning: code.\n\n### Surface, not machinery\n\nAgents choose tools from prose: state WHEN\u002FWHY; NEVER internal HOW.\n\n- `read.md`: enumerate every covered source — file\u002Fdir\u002Farchive\u002Fsqlite\u002FPDF\u002FURL — so agent avoids `cat`\u002F`curl`\u002F`tar`; omit chunker, binary sniffer, cache layer.\n- `lsp.md`: \"You MUST use `lsp` whenever a language server is available — safer than text-based alternatives.\" Omit LSP wire protocol, server lifecycle, capability negotiation.\n- `ast_edit`: teach metavariable syntax + workflow: \"Loosest existence check: `pat: 'executeBash'` with narrow paths\"; omit AST engine, query compilation, tree-sitter grammar selection.\n- `hashline.md` (this repo): teach **patch grammar** — anchors, ops, payloads, ranges — and successful **edit shapes**. NEVER expose `tryRecoverHashlineWithCache`, fuzz factor, bigram tables, `findUniqueSuffixMatch`, `untilAborted`, `formatGroupedFiles`; agent sees only \"the tool resolved your typo\" or \"the anchor was stale, re-read\".\n\nBehavior-invariant detail: exclude. Every sentence MUST shift an agent decision.\n\n### Good tool-prompt anatomy\n\n1. **One-line purpose** — agent-vocabulary problem; e.g. “compact, line-anchored edit format”, not “wraps libfoo with X”.\n2. **Input grammar \u002F surface** — operators, parameters, selectors; verbatim emitted syntax.\n3. **Worked examples** — 3–8 common shapes; each explains itself, no duplicate narration.\n4. **Agent-owned failure shapes** — input-fixable stale anchors, missing payload prefix, fabricated hash; skip silently recovered failures.\n5. **Anti-patterns** — real-failure WRONG\u002FRIGHT pairs that cost retries; not imagined failures.\n6. **`\u003Ccritical>` recap** — 3–6 load-bearing lines, for body-skipping agents.\n\n### Exclude\n\n- Implementation file\u002Ffunction names; module layout.\n- Recovery, retry, normalization, caching, fuzz matching.\n- Performance (`O(n)`) unless strategy-changing.\n- Telemetry, logging, debug flags, unsettable env vars.\n- Version history, deprecated parameters, “previously this worked differently”.\n- Cross-tool plumbing (`this calls \\`read\\` under the hood`) unless coordination required.\n\n### Examples drive the contract\n\nTool prompts rely on examples more than agent prompts:\n\n- Mechanical syntax: one correct example beats three grammar paragraphs.\n- Model anchors output format on latest example: canonical shape last.\n- Adjacent WRONG\u002FRIGHT eliminates a retry class.\n\nExamples MUST be runnable, not pseudo-code. JSON tool → JSON example; custom grammar → real anchors, payload prefixes, line numbers.\n",{"name":5,"description":7},"main","9fb685c39f4231d1c854d8d1b95935d2e1a2e709","oh-my-pi\u002F.omp\u002Fskills\u002Fsystem-prompts",0,"https:\u002F\u002Fgithub.com\u002FVinayak-RZ\u002FImproveness","https:\u002F\u002Fgithub.com\u002FVinayak-RZ","2026-09-15 15:09:50",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add Vinayak-RZ\u002FImproveness --skill system-prompts",{"tool":37,"command":38},"bunx","bunx skills add Vinayak-RZ\u002FImproveness --skill system-prompts",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Vinayak-RZ\u002FImproveness --skill system-prompts","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVinayak-RZ\u002FImproveness\u002Fblob\u002Fmain\u002Foh-my-pi\u002F.omp\u002Fskills\u002Fsystem-prompts\u002FSKILL.md",true,[45],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"small-models.md","REFERENCE","参考文档",3442,"https:\u002F\u002Fgithub.com\u002FVinayak-RZ\u002FImproveness\u002Fblob\u002Fmain\u002Foh-my-pi\u002F.omp\u002Fskills\u002Fsystem-prompts\u002Fsmall-models.md",[52,59,66,73,79,86],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7APA22BN6W9SVF4SCEAP3B1","greet","A greeting skill for testing","https:\u002F\u002Fgithub.com\u002FVinayak-RZ\u002FImproveness\u002Fblob\u002Fmain\u002Foh-my-pi\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Fmarketplace\u002Ffixtures\u002Fvalid-marketplace\u002Fplugins\u002Fhello-plugin\u002Fskills\u002Fgreet\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7AP9ZV2PZ7EZAVMP021GT88","valid-skill","A valid skill for testing purposes.","https:\u002F\u002Fgithub.com\u002FVinayak-RZ\u002FImproveness\u002Fblob\u002Fmain\u002Foh-my-pi\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Ffixtures\u002Fskills\u002Fvalid-skill\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7AP9YRRCH92DRVN61AQTNAZ","unknown-field","A skill with an unknown frontmatter field.","https:\u002F\u002Fgithub.com\u002FVinayak-RZ\u002FImproveness\u002Fblob\u002Fmain\u002Foh-my-pi\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Ffixtures\u002Fskills\u002Funknown-field\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"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":76,"categories":77,"keywords":78,"publishedAt":19},"01M7AP9XDBJJSP9XRNGP6JQ2BX","no-frontmatter","https:\u002F\u002Fgithub.com\u002FVinayak-RZ\u002FImproveness\u002Fblob\u002Fmain\u002Foh-my-pi\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Ffixtures\u002Fskills\u002Fno-frontmatter\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},"01M7AP9WAGKGA2C3FN9B92RKAD","child-skill","A nested skill in a subdirectory.","https:\u002F\u002Fgithub.com\u002FVinayak-RZ\u002FImproveness\u002Fblob\u002Fmain\u002Foh-my-pi\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Ffixtures\u002Fskills\u002Fnested\u002Fchild-skill\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},"01M7AP9SRFAAYTQ44GWGXG5ERX","different-name","A skill with a name that doesn't match the directory.","https:\u002F\u002Fgithub.com\u002FVinayak-RZ\u002FImproveness\u002Fblob\u002Fmain\u002Foh-my-pi\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Ffixtures\u002Fskills\u002Fname-mismatch\u002FSKILL.md",[],[]]