[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DCXFWHTGF4KNCEJY93X9BF":3,"skill-same:01M7DCXFWHTGF4KNCEJY93X9BF":47},{"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":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M7DCXFWHTGF4KNCEJY93X9BF","test-driven-development",null,"Unified TDD skill with three input modes — from spec, from task, or from description. Enforces test-first development using repository patterns, with proptest guidance and backpressure integration.","flaviomartil\u002Fralph-jev","flaviomartil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F60192455?v=4","01M7DCWCHAAEJPMG1QM8T0ZN9F","Flávio Martil","01M7DCWCJTHN5T4YN12F3GTXGM",0,"MIT","https:\u002F\u002Fgithub.com\u002Fflaviomartil\u002Fralph-jev\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: test-driven-development\ndescription: Unified TDD skill with three input modes — from spec, from task, or from description. Enforces test-first development using repository patterns, with proptest guidance and backpressure integration.\ntype: anthropic-skill\nversion: \"1.0\"\nmetadata:\n  internal: true\n---\n\n# Test-Driven Development\n\n## Overview\n\nOne skill for all TDD workflows. Enforces test-first development using existing repository patterns. Three input modes handle different entry points — specs, task files, or ad-hoc descriptions — but the core cycle is always RED → GREEN → REFACTOR.\n\n## Input Modes\n\nDetect the input type and follow the corresponding mode:\n\n### Mode A: From Spec (`.spec.md`)\n\nUse when the input references a `.spec.md` file with Given\u002FWhen\u002FThen acceptance criteria.\n\n1. **Locate and parse** the spec file — extract all Given\u002FWhen\u002FThen triples\n2. **Generate one test stub per criterion** with `todo!()` bodies:\n   ```rust\n   \u002F\u002F\u002F Spec: \u003Cspec-file> — Criterion #\u003CN>\n   \u002F\u002F\u002F Given \u003Cgiven text>\n   \u002F\u002F\u002F When \u003Cwhen text>\n   \u002F\u002F\u002F Then \u003Cthen text>\n   #[test]\n   fn \u003Cspec_name>_criterion_\u003CN>_\u003Cslug>() {\n       todo!(\"Implement: \u003Cthen text>\");\n   }\n   ```\n3. **Verify stubs compile** but fail: `cargo test --no-run -p \u003Ccrate>`\n4. Proceed to the [TDD Cycle](#tdd-cycle) to make stubs pass\n\n**Programmatic support:** `ralph_core::preflight::{extract_acceptance_criteria, extract_criteria_from_file, extract_all_criteria}` can parse criteria from spec files.\n\n### Mode B: From Task (`.code-task.md`)\n\nUse when the input references a `.code-task.md` file or a specific implementation task.\n\n1. **Read the task** and identify acceptance criteria or requirements\n2. **Discover patterns** (see [Pattern Discovery](#pattern-discovery))\n3. **Design test scenarios** covering normal operation, edge cases, and error conditions\n4. **Write failing tests** for all requirements before any implementation\n5. Proceed to the [TDD Cycle](#tdd-cycle)\n\n### Mode C: From Description\n\nUse for ad-hoc tasks without a spec or task file.\n\n1. **Clarify requirements** from the description\n2. **Discover patterns** (see [Pattern Discovery](#pattern-discovery))\n3. **Write failing tests** targeting the described behavior\n4. Proceed to the [TDD Cycle](#tdd-cycle)\n\n## Pattern Discovery\n\nBefore writing tests, discover existing conventions:\n\n```bash\nrg --files -g \"crates\u002F*\u002Ftests\u002F*.rs\"\nrg -n \"#\\[cfg\\(test\\)\\]\" crates\u002F\n```\n\nRead 2-3 relevant test files near the target code. Mirror:\n- Test module layout, naming, and assertion style\n- Fixture helpers and test utilities\n- Use of `tempfile`, scenarios, or harnesses\n\n## TDD Cycle\n\n### 1) RED — Failing Tests\n\n- Write tests for the exact behavior required\n- Run tests to confirm failure **for the right reason**\n- If tests pass without implementation, the test is wrong\n\n### 2) GREEN — Minimal Implementation\n\n- Write the minimum code to make tests pass\n- No extra features or refactoring during this step\n\n### 3) REFACTOR — Clean Up\n\n- Improve implementation and tests while keeping tests green\n- Align with surrounding codebase conventions\n- Re-run tests after every change\n\n## Proptest Guidance\n\nUse `proptest` only when ALL of:\n- Function is pure (no I\u002FO, no time, no globals)\n- Deterministic output for given input\n- Non-trivial input space or edge cases\n\n```rust\nproptest! {\n    #[test]\n    fn round_trip(input in \"[a-z0-9]{0,32}\") {\n        let encoded = encode(input.as_str());\n        let decoded = decode(&encoded).expect(\"should decode\");\n        prop_assert_eq!(decoded, input);\n    }\n}\n```\n\nDon't introduce proptest as a new dependency without strong justification.\n\n## Backpressure Integration\n\nInclude coverage evidence in completion events:\n\n```bash\nralph emit \"build.done\" \"tests: pass, lint: pass, typecheck: pass, audit: pass, coverage: pass (82%)\"\n```\n\nRun `cargo tarpaulin --out Html --output-dir coverage --skip-clean` when feasible. If coverage cannot be run, state why and include targeted test evidence instead.\n\n## Test Location Rules\n\n- Spec maps to a single module → inline `#[cfg(test)]` tests\n- Spec spans multiple modules → integration test in `crates\u002F\u003Ccrate>\u002Ftests\u002F`\n- CLI behavior → `crates\u002Fralph-cli\u002Ftests\u002F`\n- Follow existing patterns in the target crate\n\n## Anti-Patterns\n\n- Writing implementation before tests\n- Generating tests that pass without implementation\n- Copying tests from other crates without adapting to local patterns\n- Adding proptest when a simple example test suffices\n- Emitting completion events without coverage evidence\n","# Test-Driven Development\n\n## Overview\n\nOne skill for all TDD workflows. Enforces test-first development using existing repository patterns. Three input modes handle different entry points — specs, task files, or ad-hoc descriptions — but the core cycle is always RED → GREEN → REFACTOR.\n\n## Input Modes\n\nDetect the input type and follow the corresponding mode:\n\n### Mode A: From Spec (`.spec.md`)\n\nUse when the input references a `.spec.md` file with Given\u002FWhen\u002FThen acceptance criteria.\n\n1. **Locate and parse** the spec file — extract all Given\u002FWhen\u002FThen triples\n2. **Generate one test stub per criterion** with `todo!()` bodies:\n   ```rust\n   \u002F\u002F\u002F Spec: \u003Cspec-file> — Criterion #\u003CN>\n   \u002F\u002F\u002F Given \u003Cgiven text>\n   \u002F\u002F\u002F When \u003Cwhen text>\n   \u002F\u002F\u002F Then \u003Cthen text>\n   #[test]\n   fn \u003Cspec_name>_criterion_\u003CN>_\u003Cslug>() {\n       todo!(\"Implement: \u003Cthen text>\");\n   }\n   ```\n3. **Verify stubs compile** but fail: `cargo test --no-run -p \u003Ccrate>`\n4. Proceed to the [TDD Cycle](#tdd-cycle) to make stubs pass\n\n**Programmatic support:** `ralph_core::preflight::{extract_acceptance_criteria, extract_criteria_from_file, extract_all_criteria}` can parse criteria from spec files.\n\n### Mode B: From Task (`.code-task.md`)\n\nUse when the input references a `.code-task.md` file or a specific implementation task.\n\n1. **Read the task** and identify acceptance criteria or requirements\n2. **Discover patterns** (see [Pattern Discovery](#pattern-discovery))\n3. **Design test scenarios** covering normal operation, edge cases, and error conditions\n4. **Write failing tests** for all requirements before any implementation\n5. Proceed to the [TDD Cycle](#tdd-cycle)\n\n### Mode C: From Description\n\nUse for ad-hoc tasks without a spec or task file.\n\n1. **Clarify requirements** from the description\n2. **Discover patterns** (see [Pattern Discovery](#pattern-discovery))\n3. **Write failing tests** targeting the described behavior\n4. Proceed to the [TDD Cycle](#tdd-cycle)\n\n## Pattern Discovery\n\nBefore writing tests, discover existing conventions:\n\n```bash\nrg --files -g \"crates\u002F*\u002Ftests\u002F*.rs\"\nrg -n \"#\\[cfg\\(test\\)\\]\" crates\u002F\n```\n\nRead 2-3 relevant test files near the target code. Mirror:\n- Test module layout, naming, and assertion style\n- Fixture helpers and test utilities\n- Use of `tempfile`, scenarios, or harnesses\n\n## TDD Cycle\n\n### 1) RED — Failing Tests\n\n- Write tests for the exact behavior required\n- Run tests to confirm failure **for the right reason**\n- If tests pass without implementation, the test is wrong\n\n### 2) GREEN — Minimal Implementation\n\n- Write the minimum code to make tests pass\n- No extra features or refactoring during this step\n\n### 3) REFACTOR — Clean Up\n\n- Improve implementation and tests while keeping tests green\n- Align with surrounding codebase conventions\n- Re-run tests after every change\n\n## Proptest Guidance\n\nUse `proptest` only when ALL of:\n- Function is pure (no I\u002FO, no time, no globals)\n- Deterministic output for given input\n- Non-trivial input space or edge cases\n\n```rust\nproptest! {\n    #[test]\n    fn round_trip(input in \"[a-z0-9]{0,32}\") {\n        let encoded = encode(input.as_str());\n        let decoded = decode(&encoded).expect(\"should decode\");\n        prop_assert_eq!(decoded, input);\n    }\n}\n```\n\nDon't introduce proptest as a new dependency without strong justification.\n\n## Backpressure Integration\n\nInclude coverage evidence in completion events:\n\n```bash\nralph emit \"build.done\" \"tests: pass, lint: pass, typecheck: pass, audit: pass, coverage: pass (82%)\"\n```\n\nRun `cargo tarpaulin --out Html --output-dir coverage --skip-clean` when feasible. If coverage cannot be run, state why and include targeted test evidence instead.\n\n## Test Location Rules\n\n- Spec maps to a single module → inline `#[cfg(test)]` tests\n- Spec spans multiple modules → integration test in `crates\u002F\u003Ccrate>\u002Ftests\u002F`\n- CLI behavior → `crates\u002Fralph-cli\u002Ftests\u002F`\n- Follow existing patterns in the target crate\n\n## Anti-Patterns\n\n- Writing implementation before tests\n- Generating tests that pass without implementation\n- Copying tests from other crates without adapting to local patterns\n- Adding proptest when a simple example test suffices\n- Emitting completion events without coverage evidence\n",{"name":5,"type":24,"version":25,"metadata":26,"description":7},"anthropic-skill","1.0",{"internal":27},true,"main","adaf7f4432d523a43d920c5d2d875271e7ec0873",".claude\u002Fskills\u002Ftest-driven-development","https:\u002F\u002Fgithub.com\u002Fflaviomartil\u002Fralph-jev","https:\u002F\u002Fgithub.com\u002Fflaviomartil","2026-09-26 07:24:05",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":27},[36,39,42],{"tool":37,"command":38},"npx","npx skills add flaviomartil\u002Fralph-jev --skill test-driven-development",{"tool":40,"command":41},"bunx","bunx skills add flaviomartil\u002Fralph-jev --skill test-driven-development",{"tool":43,"command":44},"pnpm","pnpm dlx skills add flaviomartil\u002Fralph-jev --skill test-driven-development","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fflaviomartil\u002Fralph-jev\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7DCYHX0EBXRGAKSVTYXS96D","ralph-loop","Run, monitor, resume, merge, and debug Ralph loops. Use this skill whenever the user asks to operate `ralph run` or `ralph loops`, inspect loop state, recover suspended loops, analyze diagnostics, or unblock merge queue issues.","https:\u002F\u002Fgithub.com\u002Fflaviomartil\u002Fralph-jev\u002Fblob\u002Fmain\u002Fskills\u002Fralph-loop\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7DCYDCFEJFYD4V5JWV7HJFS","ralph-hats","Create, inspect, validate, explain, and improve Ralph hat collections. Use this skill whenever the user asks to make or refine a `.ralph\u002Fhats\u002F*.yml` workflow, debug hat routing, explain event topology, or tune a multi-hat Ralph run.","https:\u002F\u002Fgithub.com\u002Fflaviomartil\u002Fralph-jev\u002Fblob\u002Fmain\u002Fskills\u002Fralph-hats\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7DCY5Z7EGXE9S116KQ5EFJY","ralph-docs","Introspect, explain, and improve ralph-jev using the documentation shipped in its repository. Use this skill whenever the user asks questions about Ralph's behavior, wants to understand how a Ralph internal works (event loop, completion gate, judge evidence, Jev hooks, parallel loops, configuration), debug an unfamiliar failure mode, or propose a code change to the ralph-jev repo. The skill teaches the agent to answer from the repo's docs and source before guessing, and to scope improvements through the documented architecture rather than the local checkout alone.","https:\u002F\u002Fgithub.com\u002Fflaviomartil\u002Fralph-jev\u002Fblob\u002Fmain\u002Fskills\u002Fralph-docs\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7DCY37C342859GXBPYTN5EK","complex-test-skill","A directory-style test skill for smoke testing","https:\u002F\u002Fgithub.com\u002Fflaviomartil\u002Fralph-jev\u002Fblob\u002Fmain\u002Fcrates\u002Fralph-core\u002Ftests\u002Ffixtures\u002Fskills\u002Fcomplex-test-skill\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7DCXX2582CZB0ZK7213M7B3","tui-validate","Validates Terminal User Interface (TUI) output using freeze for screenshot capture and LLM-as-judge for semantic validation. Supports both visual (PNG\u002FSVG) and text-based validation modes.","https:\u002F\u002Fgithub.com\u002Fflaviomartil\u002Fralph-jev\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftui-validate\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7DCXSQN75KTR4QG0PF3DNVM","tui-debug-in-pane","Use when you need to reproduce or debug TUI rendering issues (garbled output, broken streaming, layout corruption) by running ralph in a tmux split pane and capturing live output.","https:\u002F\u002Fgithub.com\u002Fflaviomartil\u002Fralph-jev\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftui-debug-in-pane\u002FSKILL.md",[],[]]