[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AGYHHPDMHED8S7AVBN4JJ7":3,"skill-same:01M7AGYHHPDMHED8S7AVBN4JJ7":59},{"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":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M7AGYHHPDMHED8S7AVBN4JJ7","test-driven-development",null,"Drive one observable software behavior at a time through a valid Test-Driven Development cycle: select the test, prove Red for the intended reason, implement the smallest Green change, and preserve the test as regression evidence. Use before adding production behavior, fixing defects, changing contracts, or safely characterizing legacy behavior. Also use when tests are brittle, over-mocked, skipped, weakened, or passing without proving the requirement.","projectamazonph\u002Fagent-skill-framework","projectamazonph","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F286085559?v=4","01M79QFF84668ZQCDVGZXP34RF","Ryan Roland Dabao ","01M7AGNPF0TY0MJR8KX7BGQK98",0,"MIT","https:\u002F\u002Fgithub.com\u002Fprojectamazonph\u002Fagent-skill-framework\u002Fblob\u002Fmain\u002Fskills\u002Fsuite-core\u002Ftest-driven-development\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: test-driven-development\ndescription: \"Drive one observable software behavior at a time through a valid Test-Driven Development cycle: select the test, prove Red for the intended reason, implement the smallest Green change, and preserve the test as regression evidence. Use before adding production behavior, fixing defects, changing contracts, or safely characterizing legacy behavior. Also use when tests are brittle, over-mocked, skipped, weakened, or passing without proving the requirement.\"\n---\n\n# Test-Driven Development\n\n## Mission\n\nOwn behavioral proof. Move one requirement from absent or defective to verified without broadening scope.\n\nDo not own project sequencing, architecture policy, or final completion. Return evidence to `engineering-orchestrator`, use `solid-design` for structural decisions, and let `loop-engineering` record and adjust the larger loop.\n\n## Suite Protocol\n\nWhen another skill routes work here, read [references\u002Fsuite-contract.md](references\u002Fsuite-contract.md). Accept the Task Packet and return the standard Handoff Packet. Mark `pass` only for one valid Red–Green–Refactor behavior cycle.\n\n## Require an Entry Contract\n\nBefore changing production code, obtain or determine:\n\n- One observable behavior or defect\n- Acceptance example with inputs, outputs, state, side effects, and errors\n- Relevant public contract\n- Existing baseline result\n- Smallest suitable test level\n\nIf the behavior cannot be stated clearly, return to the orchestrator for scope clarification.\n\n## Run Red–Green–Refactor\n\n### 1. Select\n\nChoose one independently verifiable behavior. Keep structural cleanup and unrelated requirements out of this cycle.\n\nSelect the narrowest test that proves the real contract:\n\n- Unit test for pure policy or calculation\n- Shared contract test for all implementations of one abstraction\n- Integration test for a database, API, filesystem, queue, or framework adapter\n- Component test for a use case crossing several internal collaborators\n- Acceptance or end-to-end test for a critical user-visible journey\n\nRead [references\u002Ftest-strategies.md](references\u002Ftest-strategies.md) when test level, doubles, contract testing, or legacy seams are unclear.\n\n### 2. Prove Red\n\n1. Write or update the test before production behavior.\n2. Run the smallest command that exercises it.\n3. Confirm the test fails because the selected behavior is missing or defective.\n4. Record the command, failing test, and relevant failure message.\n\nReject false Red states:\n\n- Syntax, import, compilation, fixture, environment, or setup failure\n- Failure in an unrelated test\n- A test that never reaches the intended assertion\n- A skipped, quarantined, or filtered-out test\n- A failure caused solely by changing the test contract incorrectly\n\nRepair the test harness and rerun until Red is valid.\n\n### 3. Reach Green\n\n1. Change the smallest amount of production code that satisfies the test.\n2. Avoid speculative options, layers, and adjacent cleanup.\n3. Run the focused test.\n4. Confirm it passes without weakening assertions or bypassing execution.\n5. Run immediately related tests when the behavior shares a contract or state.\n\nDo not add production code before valid Red evidence except minimal compilation scaffolding that contains no behavior. Treat exploratory code as a disposable spike, not TDD evidence.\n\n### 4. Refactor Safely\n\nImprove names, local duplication, and cohesion only while the focused tests remain green. Invoke `solid-design` before extracting architectural boundaries, interfaces, strategies, adapters, or inheritance relationships.\n\nRun the focused test after every structural step. Stop and reduce the step when behavior drifts.\n\n### 5. Return Evidence\n\nReturn this handoff:\n\n```text\nBehavior: \u003Cobservable requirement>\nTest level: \u003Cunit | contract | integration | component | e2e>\nRed: \u003Ccommand and intended failure>\nGreen: \u003Cminimal production change and passing command>\nRefactor: \u003Cnone or behavior-preserving cleanup>\nRelated checks: \u003Cresults>\nRemaining risk: \u003Cnone or concrete gap>\n```\n\nDo not declare the whole task complete. Return control to the orchestrator and Loop Engineering.\n\n## Handle Common Modes\n\n### Defect\n\nReproduce the defect first at the lowest level that captures the real cause. Keep the reproducing test permanently unless stronger existing coverage makes it genuinely redundant.\n\n### Legacy Code\n\n1. Characterize current observable behavior, including relied-upon quirks.\n2. Add the smallest seam needed to control a volatile dependency.\n3. Move or change one behavior per cycle.\n4. Add an explicit new test before intentionally changing a characterized quirk.\n\n### Contract Change\n\nUpdate or add consumer-facing contract tests first. Run them against every implementation. Treat compatibility breaks as intentional only when the user authorizes them.\n\n### UI Behavior\n\nTest stable user-observable behavior at the component or browser level. Avoid fragile selectors and snapshots that prove markup but not behavior. Perform visual inspection when layout matters, but keep automated assertions for interaction and state.\n\n### External Integration\n\nUse a boundary fake for domain tests and a focused integration test for the real adapter. Do not mock the vendor so deeply that the adapter contract becomes imaginary.\n\n## Protect Test Quality\n\n- Name the condition and expected behavior.\n- Assert outputs, state transitions, emitted events, or required side effects.\n- Keep one primary failure reason per test.\n- Control time, randomness, IDs, concurrency, and shared state.\n- Prefer real values and small fakes over deep mock graphs.\n- Mock architectural boundaries, not every internal call.\n- Do not test private methods or incidental call order unless part of the contract.\n- Do not delete, skip, loosen, or rewrite a valid test merely to reach Green.\n\n## Stop and Return When\n\n- The requested behavior is ambiguous.\n- Red cannot be made valid without a broader environment fix.\n- Green requires several unrelated changes.\n- A shared contract exposes an LSP or architecture defect.\n- The baseline contains relevant failures that make new evidence unreliable.\n\nReturn the evidence and blocker to the orchestrator instead of manufacturing progress.\n","# Test-Driven Development\n\n## Mission\n\nOwn behavioral proof. Move one requirement from absent or defective to verified without broadening scope.\n\nDo not own project sequencing, architecture policy, or final completion. Return evidence to `engineering-orchestrator`, use `solid-design` for structural decisions, and let `loop-engineering` record and adjust the larger loop.\n\n## Suite Protocol\n\nWhen another skill routes work here, read [references\u002Fsuite-contract.md](references\u002Fsuite-contract.md). Accept the Task Packet and return the standard Handoff Packet. Mark `pass` only for one valid Red–Green–Refactor behavior cycle.\n\n## Require an Entry Contract\n\nBefore changing production code, obtain or determine:\n\n- One observable behavior or defect\n- Acceptance example with inputs, outputs, state, side effects, and errors\n- Relevant public contract\n- Existing baseline result\n- Smallest suitable test level\n\nIf the behavior cannot be stated clearly, return to the orchestrator for scope clarification.\n\n## Run Red–Green–Refactor\n\n### 1. Select\n\nChoose one independently verifiable behavior. Keep structural cleanup and unrelated requirements out of this cycle.\n\nSelect the narrowest test that proves the real contract:\n\n- Unit test for pure policy or calculation\n- Shared contract test for all implementations of one abstraction\n- Integration test for a database, API, filesystem, queue, or framework adapter\n- Component test for a use case crossing several internal collaborators\n- Acceptance or end-to-end test for a critical user-visible journey\n\nRead [references\u002Ftest-strategies.md](references\u002Ftest-strategies.md) when test level, doubles, contract testing, or legacy seams are unclear.\n\n### 2. Prove Red\n\n1. Write or update the test before production behavior.\n2. Run the smallest command that exercises it.\n3. Confirm the test fails because the selected behavior is missing or defective.\n4. Record the command, failing test, and relevant failure message.\n\nReject false Red states:\n\n- Syntax, import, compilation, fixture, environment, or setup failure\n- Failure in an unrelated test\n- A test that never reaches the intended assertion\n- A skipped, quarantined, or filtered-out test\n- A failure caused solely by changing the test contract incorrectly\n\nRepair the test harness and rerun until Red is valid.\n\n### 3. Reach Green\n\n1. Change the smallest amount of production code that satisfies the test.\n2. Avoid speculative options, layers, and adjacent cleanup.\n3. Run the focused test.\n4. Confirm it passes without weakening assertions or bypassing execution.\n5. Run immediately related tests when the behavior shares a contract or state.\n\nDo not add production code before valid Red evidence except minimal compilation scaffolding that contains no behavior. Treat exploratory code as a disposable spike, not TDD evidence.\n\n### 4. Refactor Safely\n\nImprove names, local duplication, and cohesion only while the focused tests remain green. Invoke `solid-design` before extracting architectural boundaries, interfaces, strategies, adapters, or inheritance relationships.\n\nRun the focused test after every structural step. Stop and reduce the step when behavior drifts.\n\n### 5. Return Evidence\n\nReturn this handoff:\n\n```text\nBehavior: \u003Cobservable requirement>\nTest level: \u003Cunit | contract | integration | component | e2e>\nRed: \u003Ccommand and intended failure>\nGreen: \u003Cminimal production change and passing command>\nRefactor: \u003Cnone or behavior-preserving cleanup>\nRelated checks: \u003Cresults>\nRemaining risk: \u003Cnone or concrete gap>\n```\n\nDo not declare the whole task complete. Return control to the orchestrator and Loop Engineering.\n\n## Handle Common Modes\n\n### Defect\n\nReproduce the defect first at the lowest level that captures the real cause. Keep the reproducing test permanently unless stronger existing coverage makes it genuinely redundant.\n\n### Legacy Code\n\n1. Characterize current observable behavior, including relied-upon quirks.\n2. Add the smallest seam needed to control a volatile dependency.\n3. Move or change one behavior per cycle.\n4. Add an explicit new test before intentionally changing a characterized quirk.\n\n### Contract Change\n\nUpdate or add consumer-facing contract tests first. Run them against every implementation. Treat compatibility breaks as intentional only when the user authorizes them.\n\n### UI Behavior\n\nTest stable user-observable behavior at the component or browser level. Avoid fragile selectors and snapshots that prove markup but not behavior. Perform visual inspection when layout matters, but keep automated assertions for interaction and state.\n\n### External Integration\n\nUse a boundary fake for domain tests and a focused integration test for the real adapter. Do not mock the vendor so deeply that the adapter contract becomes imaginary.\n\n## Protect Test Quality\n\n- Name the condition and expected behavior.\n- Assert outputs, state transitions, emitted events, or required side effects.\n- Keep one primary failure reason per test.\n- Control time, randomness, IDs, concurrency, and shared state.\n- Prefer real values and small fakes over deep mock graphs.\n- Mock architectural boundaries, not every internal call.\n- Do not test private methods or incidental call order unless part of the contract.\n- Do not delete, skip, loosen, or rewrite a valid test merely to reach Green.\n\n## Stop and Return When\n\n- The requested behavior is ambiguous.\n- Red cannot be made valid without a broader environment fix.\n- Green requires several unrelated changes.\n- A shared contract exposes an LSP or architecture defect.\n- The baseline contains relevant failures that make new evidence unreliable.\n\nReturn the evidence and blocker to the orchestrator instead of manufacturing progress.\n",{"name":5,"description":7},"main","fbd23e0a0b843f9cc3f1f69d5317659ef0dfad0d","skills\u002Fsuite-core\u002Ftest-driven-development","https:\u002F\u002Fgithub.com\u002Fprojectamazonph\u002Fagent-skill-framework","https:\u002F\u002Fgithub.com\u002Fprojectamazonph","Amazon PPC specialist focused on campaign systems, automation, VA training, and practical eCommerce tools.","2026-09-22 23:51:13",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add projectamazonph\u002Fagent-skill-framework --skill test-driven-development",{"tool":37,"command":38},"bunx","bunx skills add projectamazonph\u002Fagent-skill-framework --skill test-driven-development",{"tool":40,"command":41},"pnpm","pnpm dlx skills add projectamazonph\u002Fagent-skill-framework --skill test-driven-development","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fprojectamazonph\u002Fagent-skill-framework\u002Fblob\u002Fmain\u002Fskills\u002Fsuite-core\u002Ftest-driven-development\u002FSKILL.md",true,[45,51,55],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"agents\u002Fopenai.yaml","REFERENCE","参考文档",345,"https:\u002F\u002Fgithub.com\u002Fprojectamazonph\u002Fagent-skill-framework\u002Fblob\u002Fmain\u002Fskills\u002Fsuite-core\u002Ftest-driven-development\u002Fagents\u002Fopenai.yaml",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fsuite-contract.md",2179,"https:\u002F\u002Fgithub.com\u002Fprojectamazonph\u002Fagent-skill-framework\u002Fblob\u002Fmain\u002Fskills\u002Fsuite-core\u002Ftest-driven-development\u002Freferences\u002Fsuite-contract.md",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Ftest-strategies.md",2424,"https:\u002F\u002Fgithub.com\u002Fprojectamazonph\u002Fagent-skill-framework\u002Fblob\u002Fmain\u002Fskills\u002Fsuite-core\u002Ftest-driven-development\u002Freferences\u002Ftest-strategies.md",[60,67,74,81,88,95],{"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":19},"01M7AGYB9EV23KZN66XG70RXRP","suite-orchestrator","Route complex work across the complete Agent Skill Suite while enforcing content preservation, explicit scope, correct specialist timing, evidence-backed completion, and durable state. Use when a task involves coding, agent operations, repository bootstrapping, conversation compilation, artifact generation, expert review, persistent memory, or several of these together. Also use when the correct skill is unclear or work must pass through multiple specialist skills in a controlled sequence.","https:\u002F\u002Fgithub.com\u002Fprojectamazonph\u002Fagent-skill-framework\u002Fblob\u002Fmain\u002Fskills\u002Fsuite-core\u002Fsuite-orchestrator\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":19},"01M7AGXX0ZJR3K8QNV7J38NF3X","solid-design","Design, refactor, and review object-oriented or modular code with the SOLID principles while preserving behavior and avoiding needless abstraction. Use when defining responsibilities, extension seams, subtype contracts, consumer interfaces, dependency direction, modules, services, strategies, plugins, adapters, repositories, or architecture boundaries; also use when test friction, tangled dependencies, large classes, unsupported methods, framework leakage, or repeated variant branches signal a structural problem.","https:\u002F\u002Fgithub.com\u002Fprojectamazonph\u002Fagent-skill-framework\u002Fblob\u002Fmain\u002Fskills\u002Fsuite-core\u002Fsolid-design\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":19},"01M7AGXRGA3HE2EFAEN81YP7BQ","quality-gates","Verify engineering work against required behavioral, architectural, regression, build, security, compatibility, documentation, and diff-hygiene evidence before completion. Use after a code change, defect fix, refactor, migration, generated-code update, or implementation plan appears complete; also use for read-only code reviews and release-readiness checks. Return PASS or BLOCKED without implementing the remediation.","https:\u002F\u002Fgithub.com\u002Fprojectamazonph\u002Fagent-skill-framework\u002Fblob\u002Fmain\u002Fskills\u002Fsuite-core\u002Fquality-gates\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":19},"01M7AGXM164VCP0ANC7FQXVHT2","loop-engineering","Execute non-trivial software work through small, observable build-test-observe-adjust loops with explicit hypotheses, evidence, outcomes, and next actions. Use throughout feature implementation, debugging, refactoring, migrations, performance work, and complex verification where feedback must guide each subsequent step. Use when work is stalling, changes are growing too large, failures repeat, or an engineering ledger is required.","https:\u002F\u002Fgithub.com\u002Fprojectamazonph\u002Fagent-skill-framework\u002Fblob\u002Fmain\u002Fskills\u002Fsuite-core\u002Floop-engineering\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7AGXFMA0Q813X6186JXKV7H","local-memory","Maintain fast, durable, curated local memory for AI agents on Android, Termux, Linux, macOS, Windows, or other lightweight environments. Use when an agent must remember stable preferences, project facts, decisions, procedures, failure resolutions, and task state across sessions; retrieve relevant memories before planning; resolve conflicting or stale memories; or provide explicit remember, search, pin, update, forget, status, and export controls without a cloud dependency.","https:\u002F\u002Fgithub.com\u002Fprojectamazonph\u002Fagent-skill-framework\u002Fblob\u002Fmain\u002Fskills\u002Fsuite-core\u002Flocal-memory\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M7AGXB090RWQ27P5BH4HPGN4","implementation-council","Pressure-test codebases, specifications, architecture notes, implementation plans, test strategies, migrations, and deployment plans through a structured council of fixed engineering leaders and task-specific specialists. Use when the user requests an expert panel, adversarial review, debate, gap analysis, implementation improvement, production-readiness assessment, or deployment verdict. Require evidence, disagreement, rebuttal, prioritized gaps, and a clear readiness decision.","https:\u002F\u002Fgithub.com\u002Fprojectamazonph\u002Fagent-skill-framework\u002Fblob\u002Fmain\u002Fskills\u002Fsuite-core\u002Fimplementation-council\u002FSKILL.md",[],[]]