[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78C18C6TG62PY1PQBGCSKXR":3,"skill-same:01M78C18C6TG62PY1PQBGCSKXR":195},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M78C18C6TG62PY1PQBGCSKXR","tdd",null,"Use when writing or changing production behavior: implementing a feature, fixing a bug whose cause is already known, or altering stored, transformed, migrated, serialized, or externally transmitted data. Also use when a user says \"use TDD\", \"test first\", or \"red-green-refactor\", and when code is being written before a failing test. For a failure whose cause is unknown, diagnose first.","adriancodes\u002Fskills","adriancodes","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F940414?v=4","01M6NJ91CRRXPC6RRKWM4CVEGJ","Adrian Martin","01M78BV1DGXZ4VG3VVC30VH0MC",1,"MIT","https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: tdd\ndescription: >\n  Use when writing or changing production behavior: implementing a feature,\n  fixing a bug whose cause is already known, or altering stored, transformed,\n  migrated, serialized, or externally transmitted data. Also use when a user\n  says \"use TDD\", \"test first\", or \"red-green-refactor\", and when code is being\n  written before a failing test. For a failure whose cause is unknown, diagnose\n  first.\nlicense: MIT\nmetadata:\n  category: Building\n  summary: Enforces observable red-green-refactor cycles through stable behavior seams, with real data-boundary evidence.\n---\n\n# Test-Driven Development\n\n**No new production behavior before an observed, behaviorally valid red test.** Work one *red-green-refactor* tracer bullet at a time. Prove the test detects missing behavior. Write the smallest green change. Refactor only while green.\n\n## Scope\n\nUse for:\n\n- New caller- or user-visible behavior.\n- Fixes for bugs whose cause is already known.\n- API, validation, workflow, or state changes.\n- Stored, transformed, migrated, serialized, or transmitted data.\n- Legacy behavior that needs a stable test seam.\n- Work where agent-authored production code appeared before red.\n\nDo not use for:\n\n- Unknown root causes. Diagnose first.\n- Documentation, formatting, generated output, or mechanical renames with no behavior effect.\n- Immediate incident containment. Restore service first; test-drive the permanent fix.\n- Throwaway prototypes. Restart under TDD before shipping or using one as a reference implementation.\n\nWhen another workflow owns the task, use TDD at its implementation seam. Adversarial testing of the finished result is a separate task (`verify-work` when installed); it is not part of this workflow.\n\n## Required Context\n\nEstablish:\n\n- One requested observable behavior and its source of truth.\n- Repository instructions and current worktree ownership.\n- The existing test framework, focused command, and affected-suite command.\n- The narrowest stable public seam.\n- Any real persistence, serialization, migration, retry, or external boundary.\n\nUse existing test tools and conventions. Ask one question only when behavior or the correct seam cannot be inferred safely.\n\nDone when one behavior, one seam, one red command, and worktree authority are explicit.\n\n## Workflow\n\n### 1. Restore red-first order\n\nInspect the diff. If the agent wrote production code for the active behavior before red, revert only those known agent-authored hunks. Never comment them out, copy them into notes, or consult them while designing the test, so the test comes from the contract, not from the implementation.\n\nPreserve pre-existing and user-authored work. Ask before reverting when authorship is ambiguous. Existing legacy code is not a violation; test its new expectation directly.\n\nDone when no agent-authored implementation for the active behavior precedes its test.\n\n### 2. Choose one tracer bullet\n\nTest one observable behavior through the narrowest stable public seam. Use a unit seam for pure logic. Use an integration seam for real boundaries. Use end-to-end only when smaller tests cannot represent the contract.\n\nAssert public outcomes. Never assert private methods, incidental call counts, or an expected value calculated by the algorithm under test.\n\nFor legacy code without a stable seam:\n\n1. Characterize current observable behavior.\n2. Keep that test green while creating the smallest behavior-preserving seam.\n3. Write the new behavior test at that seam.\n\nStop when no meaningful seam can be created safely. A shallow test that cannot catch the defect is not progress.\n\nFor data paths, choose the seam from this table before writing the test:\n\n| Path | Evidence |\n|---|---|\n| Pure transformation | Representative inputs, outputs, and boundary values |\n| Database write | Isolated test database or transaction |\n| Migration | Before\u002Fafter fixture; rollback when supported |\n| Retry or upsert | Duplicate execution without corruption or unintended duplication |\n| Serialization or file output | Write, read back, and validate bytes or representation |\n| External service | Faithful fake or contract-tested adapter; never production |\n\nMocks may isolate nondeterministic external systems, time, or randomness. Mocks alone never prove stored, migrated, serialized, or transmitted data. Test public results instead of internal collaborator calls.\n\nDone when the test names one behavior, can fail specifically when that behavior is absent, and exercises the closest real boundary of every data contract it changes.\n\n### 3. Prove valid red\n\nWrite the smallest test for the active behavior. Include a boundary or failure case when it defines the same contract. Run the focused command and capture its output.\n\nRed counts only when the behavioral assertion fails for the expected reason. Syntax errors, imports, missing dependencies, broken fixtures, unrelated timeouts, manual throws, skips, and unrelated failures do not count. Repair setup without changing production behavior until the right assertion fails.\n\nIf the test passes first, check whether behavior already exists or the test is insensitive. Strengthen the test from the contract. Never break production code to manufacture red.\n\nDone when the focused command's captured failure identifies the missing behavior.\n\n### 4. Make the smallest green change\n\nWrite only enough production code to satisfy the red test. Run the same focused command after each small change. Add no speculative options, abstractions, adjacent cleanup, or unrequested behavior.\n\nKeep the test contract fixed. Never weaken assertions, relax input, blindly update snapshots, skip tests, or redefine the requirement to manufacture green. Stop for confirmation when the requirement appears wrong, then re-establish valid red.\n\nDone when the unchanged test is green because production behavior satisfies it.\n\n### 5. Refactor while green\n\nImprove names, duplication, boundaries, or structure only after green. Run the focused test after each refactor. Revert a refactor that breaks it.\n\nStart every new behavior as a new red-green-refactor cycle. Pick the next smallest requested behavior or boundary case and repeat from step 2. Keep only tests that protect observable contracts.\n\nDone when the code is as simple as the proven behavior permits and the test remains green.\n\n### 6. Verify and report\n\nRun:\n\n1. Every new or changed focused test.\n2. The affected package or subsystem suite.\n3. The full repository suite when proportionate and available.\n\nInspect the diff for weakened assertions, skipped or focused-only tests, blind snapshot updates, unrelated code, and temporary fixtures.\n\nReport the red command and decisive failure. Report the green command and result. Report affected and full-suite results, or why a suite was not run. Name changed files.\n\nFollow the discipline silently while working. Deliver evidence, not a TDD lecture.\n\nDone when every requested behavior and material boundary case completed its own observed cycle, the evidence is reproducible, the diff is scoped, and every unrun check is named.\n\n## Core Example\n\nRequest: “Treat usernames that differ only by case or surrounding spaces as the same user.”\n\nWrite the behavior test first:\n\n```js\nimport assert from \"node:assert\u002Fstrict\";\nimport test from \"node:test\";\nimport { createUserStore } from \"..\u002Fsrc\u002Fusers.js\";\n\ntest(\"a username is taken regardless of case or surrounding spaces\", () => {\n  const users = createUserStore();\n  users.register(\"ada\");\n  assert.throws(() => users.register(\"  Ada \"), \u002Ftaken\u002F);\n});\n```\n\nRun `node --test test\u002Fusers.test.js`. Capture the expected failure: the second `register` does not throw. Then implement only the normalization, applied before the existing uniqueness check:\n\n```js\nconst normalize = (name) => name.trim().toLowerCase();\n```\n\nRun the same command green, then the affected suite. A normalizer written first followed by a first-run-green test has no red evidence and fails this workflow.\n\n## Pressure\n\nRead [references\u002Fpressure.md](references\u002Fpressure.md) when urgency, authority, sunk cost, or an uncertain shortcut threatens the workflow. Those pressures do not waive its evidence or authority requirements.\n\n## Genuine Exceptions\n\nWhen a rule is genuinely impossible, name the blocked rule and show the evidence. Use the closest safe alternative and state the weaker conclusion. A missing or broken test framework needs reported evidence and authorization before installing or replacing tooling. Ask once per session: add a minimal test setup, or proceed without red and say so in the report. Apply the answer to later changes without asking again. An unavailable real data boundary takes the closest faithful substitute; never imply a mock proved persistence. Time pressure, tiny size, sunk cost, a green existing suite, and \"just code it\" never qualify.\n\n## Verification\n\n- Every production behavior follows an observed, valid red test.\n- Premature agent work is reverted without touching user work.\n- Tests use stable public seams and independent expectations.\n- Data changes prove their closest real boundary.\n- Every cycle reaches minimal green before refactoring.\n- No test or requirement is weakened to manufacture green.\n- Focused and affected suites pass; full-suite omissions are explicit.\n- Final evidence names red, green, and verification commands.\n\nNo new production behavior before valid red. Restore the order whenever it breaks.\n","# Test-Driven Development\n\n**No new production behavior before an observed, behaviorally valid red test.** Work one *red-green-refactor* tracer bullet at a time. Prove the test detects missing behavior. Write the smallest green change. Refactor only while green.\n\n## Scope\n\nUse for:\n\n- New caller- or user-visible behavior.\n- Fixes for bugs whose cause is already known.\n- API, validation, workflow, or state changes.\n- Stored, transformed, migrated, serialized, or transmitted data.\n- Legacy behavior that needs a stable test seam.\n- Work where agent-authored production code appeared before red.\n\nDo not use for:\n\n- Unknown root causes. Diagnose first.\n- Documentation, formatting, generated output, or mechanical renames with no behavior effect.\n- Immediate incident containment. Restore service first; test-drive the permanent fix.\n- Throwaway prototypes. Restart under TDD before shipping or using one as a reference implementation.\n\nWhen another workflow owns the task, use TDD at its implementation seam. Adversarial testing of the finished result is a separate task (`verify-work` when installed); it is not part of this workflow.\n\n## Required Context\n\nEstablish:\n\n- One requested observable behavior and its source of truth.\n- Repository instructions and current worktree ownership.\n- The existing test framework, focused command, and affected-suite command.\n- The narrowest stable public seam.\n- Any real persistence, serialization, migration, retry, or external boundary.\n\nUse existing test tools and conventions. Ask one question only when behavior or the correct seam cannot be inferred safely.\n\nDone when one behavior, one seam, one red command, and worktree authority are explicit.\n\n## Workflow\n\n### 1. Restore red-first order\n\nInspect the diff. If the agent wrote production code for the active behavior before red, revert only those known agent-authored hunks. Never comment them out, copy them into notes, or consult them while designing the test, so the test comes from the contract, not from the implementation.\n\nPreserve pre-existing and user-authored work. Ask before reverting when authorship is ambiguous. Existing legacy code is not a violation; test its new expectation directly.\n\nDone when no agent-authored implementation for the active behavior precedes its test.\n\n### 2. Choose one tracer bullet\n\nTest one observable behavior through the narrowest stable public seam. Use a unit seam for pure logic. Use an integration seam for real boundaries. Use end-to-end only when smaller tests cannot represent the contract.\n\nAssert public outcomes. Never assert private methods, incidental call counts, or an expected value calculated by the algorithm under test.\n\nFor legacy code without a stable seam:\n\n1. Characterize current observable behavior.\n2. Keep that test green while creating the smallest behavior-preserving seam.\n3. Write the new behavior test at that seam.\n\nStop when no meaningful seam can be created safely. A shallow test that cannot catch the defect is not progress.\n\nFor data paths, choose the seam from this table before writing the test:\n\n| Path | Evidence |\n|---|---|\n| Pure transformation | Representative inputs, outputs, and boundary values |\n| Database write | Isolated test database or transaction |\n| Migration | Before\u002Fafter fixture; rollback when supported |\n| Retry or upsert | Duplicate execution without corruption or unintended duplication |\n| Serialization or file output | Write, read back, and validate bytes or representation |\n| External service | Faithful fake or contract-tested adapter; never production |\n\nMocks may isolate nondeterministic external systems, time, or randomness. Mocks alone never prove stored, migrated, serialized, or transmitted data. Test public results instead of internal collaborator calls.\n\nDone when the test names one behavior, can fail specifically when that behavior is absent, and exercises the closest real boundary of every data contract it changes.\n\n### 3. Prove valid red\n\nWrite the smallest test for the active behavior. Include a boundary or failure case when it defines the same contract. Run the focused command and capture its output.\n\nRed counts only when the behavioral assertion fails for the expected reason. Syntax errors, imports, missing dependencies, broken fixtures, unrelated timeouts, manual throws, skips, and unrelated failures do not count. Repair setup without changing production behavior until the right assertion fails.\n\nIf the test passes first, check whether behavior already exists or the test is insensitive. Strengthen the test from the contract. Never break production code to manufacture red.\n\nDone when the focused command's captured failure identifies the missing behavior.\n\n### 4. Make the smallest green change\n\nWrite only enough production code to satisfy the red test. Run the same focused command after each small change. Add no speculative options, abstractions, adjacent cleanup, or unrequested behavior.\n\nKeep the test contract fixed. Never weaken assertions, relax input, blindly update snapshots, skip tests, or redefine the requirement to manufacture green. Stop for confirmation when the requirement appears wrong, then re-establish valid red.\n\nDone when the unchanged test is green because production behavior satisfies it.\n\n### 5. Refactor while green\n\nImprove names, duplication, boundaries, or structure only after green. Run the focused test after each refactor. Revert a refactor that breaks it.\n\nStart every new behavior as a new red-green-refactor cycle. Pick the next smallest requested behavior or boundary case and repeat from step 2. Keep only tests that protect observable contracts.\n\nDone when the code is as simple as the proven behavior permits and the test remains green.\n\n### 6. Verify and report\n\nRun:\n\n1. Every new or changed focused test.\n2. The affected package or subsystem suite.\n3. The full repository suite when proportionate and available.\n\nInspect the diff for weakened assertions, skipped or focused-only tests, blind snapshot updates, unrelated code, and temporary fixtures.\n\nReport the red command and decisive failure. Report the green command and result. Report affected and full-suite results, or why a suite was not run. Name changed files.\n\nFollow the discipline silently while working. Deliver evidence, not a TDD lecture.\n\nDone when every requested behavior and material boundary case completed its own observed cycle, the evidence is reproducible, the diff is scoped, and every unrun check is named.\n\n## Core Example\n\nRequest: “Treat usernames that differ only by case or surrounding spaces as the same user.”\n\nWrite the behavior test first:\n\n```js\nimport assert from \"node:assert\u002Fstrict\";\nimport test from \"node:test\";\nimport { createUserStore } from \"..\u002Fsrc\u002Fusers.js\";\n\ntest(\"a username is taken regardless of case or surrounding spaces\", () => {\n  const users = createUserStore();\n  users.register(\"ada\");\n  assert.throws(() => users.register(\"  Ada \"), \u002Ftaken\u002F);\n});\n```\n\nRun `node --test test\u002Fusers.test.js`. Capture the expected failure: the second `register` does not throw. Then implement only the normalization, applied before the existing uniqueness check:\n\n```js\nconst normalize = (name) => name.trim().toLowerCase();\n```\n\nRun the same command green, then the affected suite. A normalizer written first followed by a first-run-green test has no red evidence and fails this workflow.\n\n## Pressure\n\nRead [references\u002Fpressure.md](references\u002Fpressure.md) when urgency, authority, sunk cost, or an uncertain shortcut threatens the workflow. Those pressures do not waive its evidence or authority requirements.\n\n## Genuine Exceptions\n\nWhen a rule is genuinely impossible, name the blocked rule and show the evidence. Use the closest safe alternative and state the weaker conclusion. A missing or broken test framework needs reported evidence and authorization before installing or replacing tooling. Ask once per session: add a minimal test setup, or proceed without red and say so in the report. Apply the answer to later changes without asking again. An unavailable real data boundary takes the closest faithful substitute; never imply a mock proved persistence. Time pressure, tiny size, sunk cost, a green existing suite, and \"just code it\" never qualify.\n\n## Verification\n\n- Every production behavior follows an observed, valid red test.\n- Premature agent work is reverted without touching user work.\n- Tests use stable public seams and independent expectations.\n- Data changes prove their closest real boundary.\n- Every cycle reaches minimal green before refactoring.\n- No test or requirement is weakened to manufacture green.\n- Focused and affected suites pass; full-suite omissions are explicit.\n- Final evidence names red, green, and verification commands.\n\nNo new production behavior before valid red. Restore the order whenever it breaks.\n",{"name":5,"license":15,"metadata":24,"description":27},{"summary":25,"category":26},"Enforces observable red-green-refactor cycles through stable behavior seams, with real data-boundary evidence.","Building","Use when writing or changing production behavior: implementing a feature, fixing a bug whose cause is already known, or altering stored, transformed, migrated, serialized, or externally transmitted data. Also use when a user says \"use TDD\", \"test first\", or \"red-green-refactor\", and when code is being written before a failing test. For a failure whose cause is unknown, diagnose first.\n","main","9a3fe345285b86c3071deb2ecb302dff99a855b8","skills\u002Ftdd",0,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills","https:\u002F\u002Fgithub.com\u002Fadriancodes","2026-11-12 06:06:49",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add adriancodes\u002Fskills --skill tdd",{"tool":41,"command":42},"bunx","bunx skills add adriancodes\u002Fskills --skill tdd",{"tool":44,"command":45},"pnpm","pnpm dlx skills add adriancodes\u002Fskills --skill tdd","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002FSKILL.md",true,[49,55,61,65,69,75,79,83,87,91,95,99,102,105,109,113,117,121,125,129,133,136,139,142,146,150,154,158,161,164,167,171,175,179,183,187,191],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"evals\u002Fcases.jsonl","OTHER","其他",4604,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fcases.jsonl",{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"evals\u002Ffixtures\u002Fcustomer-migration\u002Ffixtures\u002Fcustomers.json","REFERENCE","参考文档",89,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Ffixtures\u002Fcustomer-migration\u002Ffixtures\u002Fcustomers.json",{"path":62,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":63,"sourceHtmlUrl":64},"evals\u002Ffixtures\u002Fcustomer-migration\u002Fpackage.json",132,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Ffixtures\u002Fcustomer-migration\u002Fpackage.json",{"path":66,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":67,"sourceHtmlUrl":68},"evals\u002Ffixtures\u002Fcustomer-migration\u002FREADME.md",572,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Ffixtures\u002Fcustomer-migration\u002FREADME.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"evals\u002Ffixtures\u002Fcustomer-migration\u002Fsrc\u002Fmigrate-customers.js","SCRIPT","脚本",161,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Ffixtures\u002Fcustomer-migration\u002Fsrc\u002Fmigrate-customers.js",{"path":76,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":77,"sourceHtmlUrl":78},"evals\u002Ffixtures\u002Ffree-shipping\u002Fpackage.json",127,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Ffixtures\u002Ffree-shipping\u002Fpackage.json",{"path":80,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":81,"sourceHtmlUrl":82},"evals\u002Ffixtures\u002Ffree-shipping\u002FREADME.md",276,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Ffixtures\u002Ffree-shipping\u002FREADME.md",{"path":84,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":85,"sourceHtmlUrl":86},"evals\u002Ffixtures\u002Ffree-shipping\u002Fsrc\u002Fshipping.js",63,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Ffixtures\u002Ffree-shipping\u002Fsrc\u002Fshipping.js",{"path":88,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":89,"sourceHtmlUrl":90},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fheldout-free-shipping\u002Fcase.json",1179,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fheldout-free-shipping\u002Fcase.json",{"path":92,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":93,"sourceHtmlUrl":94},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fheldout-free-shipping\u002Foutput.md",1213,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fheldout-free-shipping\u002Foutput.md",{"path":96,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":97,"sourceHtmlUrl":98},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fheldout-free-shipping\u002Fresult.json",786,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fheldout-free-shipping\u002Fresult.json",{"path":100,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":77,"sourceHtmlUrl":101},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fheldout-free-shipping\u002Fworkspace-after\u002Fpackage.json","https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fheldout-free-shipping\u002Fworkspace-after\u002Fpackage.json",{"path":103,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":81,"sourceHtmlUrl":104},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fheldout-free-shipping\u002Fworkspace-after\u002FREADME.md","https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fheldout-free-shipping\u002Fworkspace-after\u002FREADME.md",{"path":106,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":107,"sourceHtmlUrl":108},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fheldout-free-shipping\u002Fworkspace-after\u002Fsrc\u002Fshipping.js",233,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fheldout-free-shipping\u002Fworkspace-after\u002Fsrc\u002Fshipping.js",{"path":110,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":111,"sourceHtmlUrl":112},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fheldout-free-shipping\u002Fworkspace-after\u002Ftest\u002Fshipping.test.js",575,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fheldout-free-shipping\u002Fworkspace-after\u002Ftest\u002Fshipping.test.js",{"path":114,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":115,"sourceHtmlUrl":116},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fprompt-template.md",959,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fprompt-template.md",{"path":118,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":119,"sourceHtmlUrl":120},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002FREADME.md",2375,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002FREADME.md",{"path":122,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":123,"sourceHtmlUrl":124},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-code-first-pressure\u002Fcase.json",1134,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-code-first-pressure\u002Fcase.json",{"path":126,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":127,"sourceHtmlUrl":128},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-code-first-pressure\u002Foutput.md",1294,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-code-first-pressure\u002Foutput.md",{"path":130,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":131,"sourceHtmlUrl":132},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-code-first-pressure\u002Fresult.json",775,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-code-first-pressure\u002Fresult.json",{"path":134,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":77,"sourceHtmlUrl":135},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-code-first-pressure\u002Fworkspace-after\u002Fpackage.json","https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-code-first-pressure\u002Fworkspace-after\u002Fpackage.json",{"path":137,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":81,"sourceHtmlUrl":138},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-code-first-pressure\u002Fworkspace-after\u002FREADME.md","https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-code-first-pressure\u002Fworkspace-after\u002FREADME.md",{"path":140,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":107,"sourceHtmlUrl":141},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-code-first-pressure\u002Fworkspace-after\u002Fsrc\u002Fshipping.js","https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-code-first-pressure\u002Fworkspace-after\u002Fsrc\u002Fshipping.js",{"path":143,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":144,"sourceHtmlUrl":145},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-code-first-pressure\u002Fworkspace-after\u002Ftest\u002Fshipping.test.js",627,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-code-first-pressure\u002Fworkspace-after\u002Ftest\u002Fshipping.test.js",{"path":147,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":148,"sourceHtmlUrl":149},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-data-boundary\u002Fcase.json",1008,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-data-boundary\u002Fcase.json",{"path":151,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":152,"sourceHtmlUrl":153},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-data-boundary\u002Foutput.md",1467,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-data-boundary\u002Foutput.md",{"path":155,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":156,"sourceHtmlUrl":157},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-data-boundary\u002Fresult.json",782,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-data-boundary\u002Fresult.json",{"path":159,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":160},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-data-boundary\u002Fworkspace-after\u002Ffixtures\u002Fcustomers.json","https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-data-boundary\u002Fworkspace-after\u002Ffixtures\u002Fcustomers.json",{"path":162,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":63,"sourceHtmlUrl":163},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-data-boundary\u002Fworkspace-after\u002Fpackage.json","https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-data-boundary\u002Fworkspace-after\u002Fpackage.json",{"path":165,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":67,"sourceHtmlUrl":166},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-data-boundary\u002Fworkspace-after\u002FREADME.md","https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-data-boundary\u002Fworkspace-after\u002FREADME.md",{"path":168,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":169,"sourceHtmlUrl":170},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-data-boundary\u002Fworkspace-after\u002Fsrc\u002Fmigrate-customers.js",429,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-data-boundary\u002Fworkspace-after\u002Fsrc\u002Fmigrate-customers.js",{"path":172,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":173,"sourceHtmlUrl":174},"evals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-data-boundary\u002Fworkspace-after\u002Ftest\u002Fmigrate-customers.test.js",1300,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-restore-2026-09-07\u002Fregression-data-boundary\u002Fworkspace-after\u002Ftest\u002Fmigrate-customers.test.js",{"path":176,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":177,"sourceHtmlUrl":178},"evals\u002Fresults\u002Fatomic-rewrite-2026-08-29.md",2078,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Fatomic-rewrite-2026-08-29.md",{"path":180,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":181,"sourceHtmlUrl":182},"evals\u002Fresults\u002FREADME.md",4092,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002FREADME.md",{"path":184,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":185,"sourceHtmlUrl":186},"evals\u002Fresults\u002Ftier2-2026-08-01.md",5019,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fresults\u002Ftier2-2026-08-01.md",{"path":188,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":189,"sourceHtmlUrl":190},"evals\u002Fskill-brief.md",2643,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Fevals\u002Fskill-brief.md",{"path":192,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":193,"sourceHtmlUrl":194},"references\u002Fpressure.md",1216,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002Freferences\u002Fpressure.md",[196,203,210,217,224,231],{"skillNo":197,"name":198,"nameZh":6,"description":199,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":200,"categories":201,"keywords":202,"publishedAt":19},"01M78C1QNZAXX06QMDJ8R65TTV","write-agent-instructions","Make the smallest evidence-backed change to persistent project instructions and test downstream behavior.","https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-agent-instructions\u002FSKILL.md",[],[],{"skillNo":204,"name":205,"nameZh":6,"description":206,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":207,"categories":208,"keywords":209,"publishedAt":19},"01M78C1K3QVP67S0TRERZ5YNGB","verify-work","Use when a finished, runnable artifact (a script, config, parser, prompt, or CLI, not a diff under review) must survive hostile input before shipping: the user asks to \"verify this script\", \"find the loopholes\", \"test this properly against bad input\", or asks \"is this ready to ship\" about one. Also when a shipped artifact failed on an input nobody tried, or when verification so far is a happy-path smoke test.","https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fverify-work\u002FSKILL.md",[],[],{"skillNo":211,"name":212,"nameZh":6,"description":213,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":214,"categories":215,"keywords":216,"publishedAt":19},"01M78C1DDYDEQ7H1HNW84VW1V3","understand-codebase","Use when the user asks to \"understand this codebase\", \"how does this feature work in this repo?\", \"trace this feature through the code\", or needs onboarding, an architecture explanation, or answers about unfamiliar code. Also use for read-only code-path questions before a change.","https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Funderstand-codebase\u002FSKILL.md",[],[],{"skillNo":218,"name":219,"nameZh":6,"description":220,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":221,"categories":222,"keywords":223,"publishedAt":19},"01M78C151714X4Z3VQW5F23FZW","simplify-code","Use when the user asks to \"simplify this code\", \"remove the fluff\", or \"clean up this over-engineered module\", or wants working code that is bloated, duplicated, over-abstracted, or dependency-heavy reduced without changing behavior.","https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fsimplify-code\u002FSKILL.md",[],[],{"skillNo":225,"name":226,"nameZh":6,"description":227,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":228,"categories":229,"keywords":230,"publishedAt":19},"01M78C127TPYNJBX0B4BCF7246","review-session","Review an agent session for evidence-backed friction and the smallest measurable remedies.","https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Freview-session\u002FSKILL.md",[],[],{"skillNo":232,"name":233,"nameZh":6,"description":234,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":235,"categories":236,"keywords":237,"publishedAt":19},"01M78C0XJK1YEAQWV7NA2GYBRE","review-code","Use when a user asks to \"review this branch\", \"review this PR\", \"review my changes\", or \"review since main\". Also use when asked whether a branch, PR, or diff is ready to merge or ship, and for work-in-progress diffs, staged changes, suspected regressions in a patch, or checking implementation against a specification.","https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Freview-code\u002FSKILL.md",[],[]]