[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F370YJCDB2R8XB2KYMYF34":3,"skill-same:01M7F370YJCDB2R8XB2KYMYF34":58},{"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":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":6,"ownerDescription":42,"updatedAt":43,"install":44,"resources":57},"01M7F370YJCDB2R8XB2KYMYF34","prism-maintain",null,"Maintain the Prism codebase: measure cyclomatic complexity, refactor hotspots, and enforce the anti-slop type discipline. Use when the user asks about \"complexity\", \"refactor\", \"hotspot\", \"maintainability\", \"code health\", \"anti-slop\", \"lint rules\", or \"clean up\" the Prism repo.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fprism-maintain\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: prism-maintain\nversion: \"0.1.0\"\ndescription: >\n  Maintain the Prism codebase: measure cyclomatic complexity, refactor\n  hotspots, and enforce the anti-slop type discipline. Use when the user asks\n  about \"complexity\", \"refactor\", \"hotspot\", \"maintainability\", \"code health\",\n  \"anti-slop\", \"lint rules\", or \"clean up\" the Prism repo.\nlicense: MIT\nauthor: irfndi\nhomepage: https:\u002F\u002Fgithub.com\u002Firfndi\u002Fprism-liquidity-agent\ntags: [typescript, effect-ts, refactoring, complexity, lint, maintainability]\ncompatibility: Requires Bun 1.4+ and oxlint with the vendored anti-slop plugin.\n---\n\n# Prism Code Maintenance\n\nMeasure complexity, refactor hotspots, keep the code human-maintainable.\nMethodology adapted from\n[saurabhkumar8112\u002Fcyclomatic-complexity-skill](https:\u002F\u002Fgithub.com\u002Fsaurabhkumar8112\u002Fcyclomatic-complexity-skill)\n(Apache-2.0); type discipline enforced by the vendored\n[dmmulroy\u002Fanti-slop](https:\u002F\u002Fgithub.com\u002Fdmmulroy\u002Fanti-slop) v0.1.2 plugin in\n`tools\u002Foxlint\u002Fanti-slop\u002F`.\n\n## Complexity gates (project config wins)\n\n`bun run lint` enforces `complexity: max 10` as an error via oxlint\n(type-aware — it is the authoritative measure for this Effect-TS codebase;\nline-counters like lizard mis-parse `Effect.gen` chains and report phantom\nCCN 50+ on 15-line functions, so never act on lizard numbers here).\n\nBands: 1–6 fine · 7–10 watch (refactor only if touching the function anyway) ·\n11+ must split before merge (lint fails).\n\nWatch-band probe (never commit this config):\n\n```bash\nsed '\"'\"'s\u002F\"max\": 10\u002F\"max\": 6\u002F'\"'\"' .oxlintrc.json > .oxlint-cc6.json\nbunx oxlint --config .oxlint-cc6.json engine ops bench cli\nrm .oxlint-cc6.json\n```\n\n## Workflow (mandatory)\n\n1. Measure the touched functions, rank by CCN descending.\n2. Report hotspots with numbers BEFORE touching anything.\n3. Refactor worst first, one function at a time.\n4. Re-measure; close with the report table below.\n5. Verify: `bun run lint`, `bun run format`, full `bun run test` green with\n   ZERO test edits (unchanged tests passing is the behavior proof).\n\n```md\n## Complexity report\n| Function | Before | After |\n|----------|--------|-------|\n| runPoolEntryGates | 11 | 9 |\nExtracted: isSafetyBinsSkippable, snapshotPriceDrift\nBehavior verified: full suite green, no test edits\n```\n\n## Refactor tactics (preference order)\n\n1. Guard clauses — invert, return early, kill nesting.\n2. Extract function — name for WHAT, not how.\n3. Lookup table \u002F map over if-else chains.\n4. Named predicates — `isPositiveFiniteApr(x)` beats boolean soup.\n5. Lookup before polymorphism: Effect code dispatches via Layers and\n   tagged unions, not class hierarchies.\n6. `continue` over nested `if` in loops.\n\nHard rules: preserve behavior · never game the metric (a dense one-liner\nhiding 6 branches is worse than the honest chain) · never break exported\nsignatures without asking · one responsibility per function.\n\n## When NOT to split\n\n- Numbered risk-gate chains (`engine\u002Frisk-service.ts`): sequential\n  early-return blocks are the documented convention (AGENTS.md) — splitting\n  scatters the gate narrative.\n- Single decision-loop `Effect.gen` blocks (`engine\u002Fprogram.ts`): splitting\n  obscures per-cycle sequencing; extract pure predicates instead.\n- Agent-overlay handlers and network retry logic in untouched domains.\n\n## Anti-slop plugin (vendored v0.1.2 parity)\n\nSource: `tools\u002Foxlint\u002Fanti-slop\u002F` (`.ts` sources + `index.mjs` bundles +\nupstream `*.test.ts` contracts, which need `oxlint\u002Fplugins-dev` to execute).\nRebuild bundles after any source change — never hand-edit `.mjs`:\n\n```bash\nbun build tools\u002Foxlint\u002Fanti-slop\u002Findex.ts --outfile tools\u002Foxlint\u002Fanti-slop\u002Findex.mjs\nbun build tools\u002Foxlint\u002Fanti-slop\u002Feffect\u002Findex.ts --outfile tools\u002Foxlint\u002Fanti-slop\u002Feffect\u002Findex.mjs\n```\n\nRules that most often bite: `no-known-value-widening` (open-dict\nannotations — prefer finite `type` contracts, `satisfies`, accumulators, or\n`Map`), `require-safety-comment-for-type-assertion` (every `as` needs a\n`SAFETY:` justification with non-empty text), `no-unknown-parameters` \u002F\n`no-unknown-returns` (parse at the boundary, return named domain types).\nNever suppress or weaken a rule — fix the code.\n","# Prism Code Maintenance\n\nMeasure complexity, refactor hotspots, keep the code human-maintainable.\nMethodology adapted from\n[saurabhkumar8112\u002Fcyclomatic-complexity-skill](https:\u002F\u002Fgithub.com\u002Fsaurabhkumar8112\u002Fcyclomatic-complexity-skill)\n(Apache-2.0); type discipline enforced by the vendored\n[dmmulroy\u002Fanti-slop](https:\u002F\u002Fgithub.com\u002Fdmmulroy\u002Fanti-slop) v0.1.2 plugin in\n`tools\u002Foxlint\u002Fanti-slop\u002F`.\n\n## Complexity gates (project config wins)\n\n`bun run lint` enforces `complexity: max 10` as an error via oxlint\n(type-aware — it is the authoritative measure for this Effect-TS codebase;\nline-counters like lizard mis-parse `Effect.gen` chains and report phantom\nCCN 50+ on 15-line functions, so never act on lizard numbers here).\n\nBands: 1–6 fine · 7–10 watch (refactor only if touching the function anyway) ·\n11+ must split before merge (lint fails).\n\nWatch-band probe (never commit this config):\n\n```bash\nsed '\"'\"'s\u002F\"max\": 10\u002F\"max\": 6\u002F'\"'\"' .oxlintrc.json > .oxlint-cc6.json\nbunx oxlint --config .oxlint-cc6.json engine ops bench cli\nrm .oxlint-cc6.json\n```\n\n## Workflow (mandatory)\n\n1. Measure the touched functions, rank by CCN descending.\n2. Report hotspots with numbers BEFORE touching anything.\n3. Refactor worst first, one function at a time.\n4. Re-measure; close with the report table below.\n5. Verify: `bun run lint`, `bun run format`, full `bun run test` green with\n   ZERO test edits (unchanged tests passing is the behavior proof).\n\n```md\n## Complexity report\n| Function | Before | After |\n|----------|--------|-------|\n| runPoolEntryGates | 11 | 9 |\nExtracted: isSafetyBinsSkippable, snapshotPriceDrift\nBehavior verified: full suite green, no test edits\n```\n\n## Refactor tactics (preference order)\n\n1. Guard clauses — invert, return early, kill nesting.\n2. Extract function — name for WHAT, not how.\n3. Lookup table \u002F map over if-else chains.\n4. Named predicates — `isPositiveFiniteApr(x)` beats boolean soup.\n5. Lookup before polymorphism: Effect code dispatches via Layers and\n   tagged unions, not class hierarchies.\n6. `continue` over nested `if` in loops.\n\nHard rules: preserve behavior · never game the metric (a dense one-liner\nhiding 6 branches is worse than the honest chain) · never break exported\nsignatures without asking · one responsibility per function.\n\n## When NOT to split\n\n- Numbered risk-gate chains (`engine\u002Frisk-service.ts`): sequential\n  early-return blocks are the documented convention (AGENTS.md) — splitting\n  scatters the gate narrative.\n- Single decision-loop `Effect.gen` blocks (`engine\u002Fprogram.ts`): splitting\n  obscures per-cycle sequencing; extract pure predicates instead.\n- Agent-overlay handlers and network retry logic in untouched domains.\n\n## Anti-slop plugin (vendored v0.1.2 parity)\n\nSource: `tools\u002Foxlint\u002Fanti-slop\u002F` (`.ts` sources + `index.mjs` bundles +\nupstream `*.test.ts` contracts, which need `oxlint\u002Fplugins-dev` to execute).\nRebuild bundles after any source change — never hand-edit `.mjs`:\n\n```bash\nbun build tools\u002Foxlint\u002Fanti-slop\u002Findex.ts --outfile tools\u002Foxlint\u002Fanti-slop\u002Findex.mjs\nbun build tools\u002Foxlint\u002Fanti-slop\u002Feffect\u002Findex.ts --outfile tools\u002Foxlint\u002Fanti-slop\u002Feffect\u002Findex.mjs\n```\n\nRules that most often bite: `no-known-value-widening` (open-dict\nannotations — prefer finite `type` contracts, `satisfies`, accumulators, or\n`Map`), `require-safety-comment-for-type-assertion` (every `as` needs a\n`SAFETY:` justification with non-empty text), `no-unknown-parameters` \u002F\n`no-unknown-returns` (parse at the boundary, return named domain types).\nNever suppress or weaken a rule — fix the code.\n",{"name":5,"tags":24,"author":31,"license":15,"version":32,"homepage":33,"description":34,"compatibility":35},[25,26,27,28,29,30],"typescript","effect-ts","refactoring","complexity","lint","maintainability","irfndi","0.1.0","https:\u002F\u002Fgithub.com\u002Firfndi\u002Fprism-liquidity-agent","Maintain the Prism codebase: measure cyclomatic complexity, refactor hotspots, and enforce the anti-slop type discipline. Use when the user asks about \"complexity\", \"refactor\", \"hotspot\", \"maintainability\", \"code health\", \"anti-slop\", \"lint rules\", or \"clean up\" the Prism repo.\n","Requires Bun 1.4+ and oxlint with the vendored anti-slop plugin.","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fprism-maintain",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill prism-maintain",{"tool":50,"command":51},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill prism-maintain",{"tool":53,"command":54},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill prism-maintain","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fprism-maintain\u002FSKILL.md",true,[],[59,66,71,78,85,92],{"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},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":67,"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":68,"categories":69,"keywords":70,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]