[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ETF3B16N1P09S5M68D7MJG":3,"skill-same:01M7ETF3B16N1P09S5M68D7MJG":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":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7ETF3B16N1P09S5M68D7MJG","test-audit",null,"Invoke whenever writing, changing, reviewing, or sweeping tests. Authoring gate for new tests plus audit workflow for low-value, implementation-coupled, or duplicative tests and the test-only production seams they demand.","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\u002F04-安全渗透\u002Ftest-audit\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: test-audit\ndescription: \"Invoke whenever writing, changing, reviewing, or sweeping tests. Authoring gate for new tests plus audit workflow for low-value, implementation-coupled, or duplicative tests and the test-only production seams they demand.\"\n---\n\n# Test Audit\n\nTwo modes, one value bar. Authoring mode gates every new or changed test at\nwrite time. Audit mode runs focused sweeps of tests that re-assert source,\nduplicate stronger proof, couple behavior to implementation, or keep test-only\nproduction seams alive. Continue broad audits as separate coherent follow-up\nPRs; optimize for confidence, not deletion count.\n\n## Authoring gate\n\nBefore adding any test, answer four questions; a missing answer means do not\nadd it yet:\n\n1. What observable behavior, invariant, or independent contract does it protect?\n2. What credible regression makes it fail?\n3. Why does existing coverage not already catch that failure? Prefer extending a\n   table-driven case or shared fixture over a near-duplicate test; consolidate\n   duplicated setup in the same change.\n4. Does it need a production seam (export, flag, wrapper, injection hook) that no\n   production caller needs? If yes, move the test to the real boundary instead.\n\nA test that would break under behavior-preserving refactoring is asserting\nimplementation, not behavior; rewrite it at the owning boundary before landing\nit.\n\nBug regression tests must fail on the pre-fix code for the intended reason and\npass after the owner-boundary repair. A regression test that never demonstrably\nfailed proves the mock, not the fix.\n\n## Value bar\n\nTests justify their maintenance cost by protecting behavior, a credible\nregression, or an independently meaningful contract. A test that must change\nfor behavior-preserving source reorganization is suspect, not automatically\ndeletable.\n\nBefore judging a candidate, read the complete test and production owner, its\nentry point, callers, callees, sibling implementations, overlapping tests, CI\nrouting, and relevant history. Read root and scoped `AGENTS.md` files first.\nWhen the test claims dependency-backed behavior, inspect the dependency source\nor types directly.\n\n## Discovery\n\nKeep discovery read-only and report evidence before editing. For broad scope,\nrun parallel discovery lanes when available:\n\n- core and packages (`src\u002F`, `packages\u002F`);\n- plugins (`extensions\u002F`);\n- UI, apps, scripts, and tooling;\n- a cross-cutting pattern sweep.\n\nPrefer a few high-confidence candidates over a large speculative inventory.\nLook for:\n\n- assertion-free coverage probes;\n- self-comparisons and identity copiers;\n- copied fixtures, inventories, manifests, or export lists;\n- exact source, import, or string greps;\n- private predicate or call-shape tests duplicated at real boundaries;\n- duplicate invocations of the same contract;\n- provider-local replays of shared helpers;\n- tests whose only purpose is preserving test-only exports, globals, or wrappers;\n- dead production code whose only callers are tests.\n\n## Retention bar\n\nKeep a test when it independently enforces a public API, plugin SDK, protocol,\nconfig, migration, storage, security, platform, default, prompt-byte, generated\ncross-language, package, release, or architecture contract. Also keep:\n\n- call ordering when order is observable behavior;\n- regressions with a credible failure mode;\n- source inspection when it is the cheapest independent guard.\n\nStatic or slow is not a deletion reason. A test that resembles implementation\nmay still be the independent contract; prove otherwise before removing it.\n\n## Candidate evidence\n\nRecord every field below before editing. A missing field means the candidate is\nnot ready for deletion:\n\n- exact test name and location;\n- what failure it can actually detect;\n- non-test callers of the covered production or support seam;\n- stronger remaining owner-boundary proof, or why no proof is needed;\n- relevant history and the reason the test or seam exists;\n- production or test-support deletion unlocked;\n- risk and the focused validation command.\n\n## Edit shape\n\nChoose one coherent owner-boundary batch. Delete obsolete test-only exports,\nglobals, wrappers, and dead production paths instead of preserving aliases.\nMove retained regressions to their canonical owners. Consolidate repeated\npackage or dependency assertions into one generic contract.\n\nPrefer net-negative production LOC. Do not add replacement tests that restate\nthe same implementation, and do not convert uncertain candidates into cleanup\nto increase deletion counts.\n\n## Validation\n\nNever edit source or tests while Vitest is running in the checkout. Follow\n`$openclaw-testing`; route heavy proof through its `$crabbox` rules.\n\n1. Run the smallest owner and sibling tests with\n   `node scripts\u002Frun-vitest.mjs \u003Cpath-or-filter>`.\n2. For removed source greps or plan assertions, run the executable script or\n   dry-run that owns the real contract.\n3. Run targeted formatting, then `git diff --check`.\n4. Classify with\n   `node scripts\u002Fcheck-changed.mjs --dry-run -- \u003Cchanged-paths>`, then run the\n   actual changed gate required by repository policy.\n5. Inspect `git diff --numstat`; report production\u002Ftooling separately from\n   tests and test support.\n6. After final audit edits, run mandatory `$autoreview`.\n\n## Landing and continuation\n\nCommit, push, open a PR, or land only when authorized. Use\n`$openclaw-pr-maintainer` and the repository `scripts\u002Fpr` flow. Land one\ncoherent PR at a time; after landing, refresh from current `main` and rerun\nread-only discovery for the next high-confidence batch.\n\n## Handoff\n\nReport:\n\n- root cause and removed low-value categories;\n- production owner simplifications;\n- retained false positives and why they remain valuable;\n- focused and full proof actually run;\n- production versus test LOC;\n- PR and merge state;\n- named follow-ups.\n","# Test Audit\n\nTwo modes, one value bar. Authoring mode gates every new or changed test at\nwrite time. Audit mode runs focused sweeps of tests that re-assert source,\nduplicate stronger proof, couple behavior to implementation, or keep test-only\nproduction seams alive. Continue broad audits as separate coherent follow-up\nPRs; optimize for confidence, not deletion count.\n\n## Authoring gate\n\nBefore adding any test, answer four questions; a missing answer means do not\nadd it yet:\n\n1. What observable behavior, invariant, or independent contract does it protect?\n2. What credible regression makes it fail?\n3. Why does existing coverage not already catch that failure? Prefer extending a\n   table-driven case or shared fixture over a near-duplicate test; consolidate\n   duplicated setup in the same change.\n4. Does it need a production seam (export, flag, wrapper, injection hook) that no\n   production caller needs? If yes, move the test to the real boundary instead.\n\nA test that would break under behavior-preserving refactoring is asserting\nimplementation, not behavior; rewrite it at the owning boundary before landing\nit.\n\nBug regression tests must fail on the pre-fix code for the intended reason and\npass after the owner-boundary repair. A regression test that never demonstrably\nfailed proves the mock, not the fix.\n\n## Value bar\n\nTests justify their maintenance cost by protecting behavior, a credible\nregression, or an independently meaningful contract. A test that must change\nfor behavior-preserving source reorganization is suspect, not automatically\ndeletable.\n\nBefore judging a candidate, read the complete test and production owner, its\nentry point, callers, callees, sibling implementations, overlapping tests, CI\nrouting, and relevant history. Read root and scoped `AGENTS.md` files first.\nWhen the test claims dependency-backed behavior, inspect the dependency source\nor types directly.\n\n## Discovery\n\nKeep discovery read-only and report evidence before editing. For broad scope,\nrun parallel discovery lanes when available:\n\n- core and packages (`src\u002F`, `packages\u002F`);\n- plugins (`extensions\u002F`);\n- UI, apps, scripts, and tooling;\n- a cross-cutting pattern sweep.\n\nPrefer a few high-confidence candidates over a large speculative inventory.\nLook for:\n\n- assertion-free coverage probes;\n- self-comparisons and identity copiers;\n- copied fixtures, inventories, manifests, or export lists;\n- exact source, import, or string greps;\n- private predicate or call-shape tests duplicated at real boundaries;\n- duplicate invocations of the same contract;\n- provider-local replays of shared helpers;\n- tests whose only purpose is preserving test-only exports, globals, or wrappers;\n- dead production code whose only callers are tests.\n\n## Retention bar\n\nKeep a test when it independently enforces a public API, plugin SDK, protocol,\nconfig, migration, storage, security, platform, default, prompt-byte, generated\ncross-language, package, release, or architecture contract. Also keep:\n\n- call ordering when order is observable behavior;\n- regressions with a credible failure mode;\n- source inspection when it is the cheapest independent guard.\n\nStatic or slow is not a deletion reason. A test that resembles implementation\nmay still be the independent contract; prove otherwise before removing it.\n\n## Candidate evidence\n\nRecord every field below before editing. A missing field means the candidate is\nnot ready for deletion:\n\n- exact test name and location;\n- what failure it can actually detect;\n- non-test callers of the covered production or support seam;\n- stronger remaining owner-boundary proof, or why no proof is needed;\n- relevant history and the reason the test or seam exists;\n- production or test-support deletion unlocked;\n- risk and the focused validation command.\n\n## Edit shape\n\nChoose one coherent owner-boundary batch. Delete obsolete test-only exports,\nglobals, wrappers, and dead production paths instead of preserving aliases.\nMove retained regressions to their canonical owners. Consolidate repeated\npackage or dependency assertions into one generic contract.\n\nPrefer net-negative production LOC. Do not add replacement tests that restate\nthe same implementation, and do not convert uncertain candidates into cleanup\nto increase deletion counts.\n\n## Validation\n\nNever edit source or tests while Vitest is running in the checkout. Follow\n`$openclaw-testing`; route heavy proof through its `$crabbox` rules.\n\n1. Run the smallest owner and sibling tests with\n   `node scripts\u002Frun-vitest.mjs \u003Cpath-or-filter>`.\n2. For removed source greps or plan assertions, run the executable script or\n   dry-run that owns the real contract.\n3. Run targeted formatting, then `git diff --check`.\n4. Classify with\n   `node scripts\u002Fcheck-changed.mjs --dry-run -- \u003Cchanged-paths>`, then run the\n   actual changed gate required by repository policy.\n5. Inspect `git diff --numstat`; report production\u002Ftooling separately from\n   tests and test support.\n6. After final audit edits, run mandatory `$autoreview`.\n\n## Landing and continuation\n\nCommit, push, open a PR, or land only when authorized. Use\n`$openclaw-pr-maintainer` and the repository `scripts\u002Fpr` flow. Land one\ncoherent PR at a time; after landing, refresh from current `main` and rerun\nread-only discovery for the next high-confidence batch.\n\n## Handoff\n\nReport:\n\n- root cause and removed low-value categories;\n- production owner simplifications;\n- retained false positives and why they remain valuable;\n- focused and full proof actually run;\n- production versus test LOC;\n- PR and merge state;\n- named follow-ups.\n",{"name":5,"description":7},"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","04-安全渗透\u002Ftest-audit",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":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill test-audit",{"tool":38,"command":39},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill test-audit",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill test-audit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Ftest-audit\u002FSKILL.md",true,[],[47,55,60,67,74,81],{"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":54},"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",[],[],"2026-11-16 10:05:34",{"skillNo":56,"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":57,"categories":58,"keywords":59,"publishedAt":54},"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":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":54},"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":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":54},"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":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":54},"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":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":54},"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",[],[]]