[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73EAKWWAQ2NDRVGXB6B2TYE":3,"skill-same:01M73EAKWWAQ2NDRVGXB6B2TYE":57},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":6,"ownerHtmlUrl":40,"ownerBlogUrl":6,"ownerDescription":41,"updatedAt":42,"install":43,"resources":56},"01M73EAKWWAQ2NDRVGXB6B2TYE","swe-solve",null,"Autonomous 5-stage issue-to-PR resolution pipeline for software engineering tasks, featuring test-driven validation, pull-request synthesis, and resolution-trajectory logging.","5throck\u002Fai-workspace-standards","5throck","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F10958964?v=4","01M73BFEH0V0VS483TW4JD49JW","01M73BFEJ5VQZJHJSFTVPAZGDM",25,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-develop\u002F.codex\u002Fskills\u002Fswe-solve\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: swe-solve\ndescription: Autonomous 5-stage issue-to-PR resolution pipeline for software engineering tasks, featuring test-driven validation, pull-request synthesis, and resolution-trajectory logging.\nversion: 1.1.1\nlast_reviewed: 2026-08-25\nstatus: active\nscope: co-develop\nowner: pm\nprerequisites: Bun runtime, workspace-root scripts\u002Ftest-runner.ts (L0 — available in the workspace dev home, not inside adopted co-develop projects; use the project's own test command there)\nmetadata:\n  type: process\n  triggers:\n    - swe-solve\n    - solve issue\n    - autonomous issue resolution\n    - issue to pr\n---\n\n# 🛠️ Skill: swe-solve\n\n## Context\nProvides a structured 5-stage autonomous software engineering workflow for resolving repository issues, fixing bugs, and implementing features using test-driven development (TDD) and multi-agent coordination. Every run produces a scoreable trajectory record for measuring resolve-rate over time.\n\n## When to Use\n- Resolving GitHub issues autonomously in `co-develop` variant templates.\n- Executing multi-step code refactoring or bug fixes requiring systematic verification.\n- Running autonomous coding pipelines with automated PR output.\n- Any issue resolution where you need a durable, machine-greppable record of the resolution attempt for later analysis.\n\n## Execution Steps\n\n### Stage 1: Ingest & Inspect\n- Parse the target issue description, bug report, or feature spec.\n- Identify candidate source files and data structures using `grep_search` and `view_file`.\n- Inspect data schemas, exported interfaces, and caller dependencies.\n\n### Stage 2: Localization & Plan\n- Formulate a precise root-cause hypothesis or technical solution design.\n- Create or update a failing test suite (TDD) that reproduces the reported issue.\n- Verify test failure: `bun scripts\u002Ftest-runner.ts` or `bun test`.\n\n### Stage 3: Mutation & Test\n- Apply minimal, surgical code modifications to resolve the underlying cause.\n- Re-run test suite until all unit, integration, and contract tests pass 100%.\n- Ensure no regression errors or side-effects are introduced.\n\n### Stage 4: Review & PR Synthesis\n- Run workspace quality gates: `bun scripts\u002Faudit.ts`.\n- Generate structured PR body detailing issue root cause, code modifications, and test evidence.\n- Submit PR via `\u002Fsync` pipeline.\n\n### Stage 5: Trajectory Record\n- Append a trajectory record file to capture the complete resolution attempt for scoring and retrospective analysis.\n- **File path**: `memory\u002Ftrajectories\u002Fswe-solve\u002F\u003CYYYY-MM-DD>-\u003Cissue-or-slug>.md` (one file per run; the directory is created on first use).\n- **YAML frontmatter** (machine-greppable for resolve-rate computation):\n  ```yaml\n  ---\n  run: \u003CYYYY-MM-DD>-\u003Cslug>\n  issue: \u003Cissue URL or local spec ref>\n  resolved: true|false  # true only if PR merged or all stages passed with tests green\n  tests_failed_before: \u003Cn>\n  tests_passed_after: \u003Cn>\n  files_touched: \u003Cn>\n  pr: \u003CPR URL or \"none\">\n  stages_completed: 1-5\n  ---\n  ```\n- **Body**: Brief per-stage notes (hypothesis, key edits, test evidence). Reuse and extend the Output Format summary structure rather than duplicating it verbatim. The Execution Summary belongs in the PR body; the trajectory file is the durable scoreable record.\n- **Resolve-rate calculation**: `resolved: true` count ÷ total trajectory files for a given period. Compute with:\n  ```bash\n  grep -c '^resolved: true' memory\u002Ftrajectories\u002Fswe-solve\u002F*.md\n  ```\n- **Pipeline regression check**: the benchmark fixture set at `docs\u002Fbenchmark-fixtures\u002F` freezes three issues (pure-function bug, error-handling bug, micro-feature) with known-good resolutions for SWE-bench-style accepted\u002Fresolved scoring - run the pipeline against those when you need to attribute a resolve-rate change to the pipeline rather than the target. See the set's [README](..\u002F..\u002Fdocs\u002Fbenchmark-fixtures\u002FREADME.md) for the scoring rubric.\n\n## Output Format\n\n```markdown\n# 🛠️ SWE-Solve Execution Summary\n\n### 🎯 Target Issue\n[Issue description and scope summary]\n\n### 🔍 Root Cause Analysis\n[Detailed technical explanation of failure mechanism or missing capability]\n\n### 🧪 Test Evidence\n- **Reproducing Test**: `tests\u002Funit\u002Ftarget-feature.test.ts`\n- **Initial Status**: FAIL (Expected X, got Y)\n- **Final Status**: PASS (All 12 assertions clean)\n\n### 📝 Code Modifications\n- `src\u002Fcomponents\u002Ftarget-module.ts`: Fixed parameter boundary check\n- `scripts\u002Fhelpers\u002Fschema-validator.ts`: Updated schema mapping\n\n### 🚀 PR Synthesis\n- **Branch**: `pr\u002F20260824-swe-solve-fix`\n- **Sync Status**: Opened PR #451\n\n### 📊 Trajectory Record\n- **Path**: `memory\u002Ftrajectories\u002Fswe-solve\u002F2026-08-24-target-fix.md`\n- **Resolved**: true\n```\n\n## Related Skills\n- [test-driven-development](..\u002Ftest-driven-development\u002FSKILL.md) — TDD workflow guidelines\n- [systematic-debugging](..\u002Fsystematic-debugging\u002FSKILL.md) — Diagnostic and root cause analysis techniques\n- [sync](..\u002Fsync\u002FSKILL.md) — Commit and PR submission pipeline\n","# 🛠️ Skill: swe-solve\n\n## Context\nProvides a structured 5-stage autonomous software engineering workflow for resolving repository issues, fixing bugs, and implementing features using test-driven development (TDD) and multi-agent coordination. Every run produces a scoreable trajectory record for measuring resolve-rate over time.\n\n## When to Use\n- Resolving GitHub issues autonomously in `co-develop` variant templates.\n- Executing multi-step code refactoring or bug fixes requiring systematic verification.\n- Running autonomous coding pipelines with automated PR output.\n- Any issue resolution where you need a durable, machine-greppable record of the resolution attempt for later analysis.\n\n## Execution Steps\n\n### Stage 1: Ingest & Inspect\n- Parse the target issue description, bug report, or feature spec.\n- Identify candidate source files and data structures using `grep_search` and `view_file`.\n- Inspect data schemas, exported interfaces, and caller dependencies.\n\n### Stage 2: Localization & Plan\n- Formulate a precise root-cause hypothesis or technical solution design.\n- Create or update a failing test suite (TDD) that reproduces the reported issue.\n- Verify test failure: `bun scripts\u002Ftest-runner.ts` or `bun test`.\n\n### Stage 3: Mutation & Test\n- Apply minimal, surgical code modifications to resolve the underlying cause.\n- Re-run test suite until all unit, integration, and contract tests pass 100%.\n- Ensure no regression errors or side-effects are introduced.\n\n### Stage 4: Review & PR Synthesis\n- Run workspace quality gates: `bun scripts\u002Faudit.ts`.\n- Generate structured PR body detailing issue root cause, code modifications, and test evidence.\n- Submit PR via `\u002Fsync` pipeline.\n\n### Stage 5: Trajectory Record\n- Append a trajectory record file to capture the complete resolution attempt for scoring and retrospective analysis.\n- **File path**: `memory\u002Ftrajectories\u002Fswe-solve\u002F\u003CYYYY-MM-DD>-\u003Cissue-or-slug>.md` (one file per run; the directory is created on first use).\n- **YAML frontmatter** (machine-greppable for resolve-rate computation):\n  ```yaml\n  ---\n  run: \u003CYYYY-MM-DD>-\u003Cslug>\n  issue: \u003Cissue URL or local spec ref>\n  resolved: true|false  # true only if PR merged or all stages passed with tests green\n  tests_failed_before: \u003Cn>\n  tests_passed_after: \u003Cn>\n  files_touched: \u003Cn>\n  pr: \u003CPR URL or \"none\">\n  stages_completed: 1-5\n  ---\n  ```\n- **Body**: Brief per-stage notes (hypothesis, key edits, test evidence). Reuse and extend the Output Format summary structure rather than duplicating it verbatim. The Execution Summary belongs in the PR body; the trajectory file is the durable scoreable record.\n- **Resolve-rate calculation**: `resolved: true` count ÷ total trajectory files for a given period. Compute with:\n  ```bash\n  grep -c '^resolved: true' memory\u002Ftrajectories\u002Fswe-solve\u002F*.md\n  ```\n- **Pipeline regression check**: the benchmark fixture set at `docs\u002Fbenchmark-fixtures\u002F` freezes three issues (pure-function bug, error-handling bug, micro-feature) with known-good resolutions for SWE-bench-style accepted\u002Fresolved scoring - run the pipeline against those when you need to attribute a resolve-rate change to the pipeline rather than the target. See the set's [README](..\u002F..\u002Fdocs\u002Fbenchmark-fixtures\u002FREADME.md) for the scoring rubric.\n\n## Output Format\n\n```markdown\n# 🛠️ SWE-Solve Execution Summary\n\n### 🎯 Target Issue\n[Issue description and scope summary]\n\n### 🔍 Root Cause Analysis\n[Detailed technical explanation of failure mechanism or missing capability]\n\n### 🧪 Test Evidence\n- **Reproducing Test**: `tests\u002Funit\u002Ftarget-feature.test.ts`\n- **Initial Status**: FAIL (Expected X, got Y)\n- **Final Status**: PASS (All 12 assertions clean)\n\n### 📝 Code Modifications\n- `src\u002Fcomponents\u002Ftarget-module.ts`: Fixed parameter boundary check\n- `scripts\u002Fhelpers\u002Fschema-validator.ts`: Updated schema mapping\n\n### 🚀 PR Synthesis\n- **Branch**: `pr\u002F20260824-swe-solve-fix`\n- **Sync Status**: Opened PR #451\n\n### 📊 Trajectory Record\n- **Path**: `memory\u002Ftrajectories\u002Fswe-solve\u002F2026-08-24-target-fix.md`\n- **Resolved**: true\n```\n\n## Related Skills\n- [test-driven-development](..\u002Ftest-driven-development\u002FSKILL.md) — TDD workflow guidelines\n- [systematic-debugging](..\u002Fsystematic-debugging\u002FSKILL.md) — Diagnostic and root cause analysis techniques\n- [sync](..\u002Fsync\u002FSKILL.md) — Commit and PR submission pipeline\n",{"name":5,"owner":23,"scope":24,"status":25,"version":26,"metadata":27,"description":7,"last_reviewed":33,"prerequisites":34},"pm","co-develop","active","1.1.1",{"type":28,"triggers":29},"process",[5,30,31,32],"solve issue","autonomous issue resolution","issue to pr",1787616000000,"Bun runtime, workspace-root scripts\u002Ftest-runner.ts (L0 — available in the workspace dev home, not inside adopted co-develop projects; use the project's own test command there)","main","1162ccc568cf90c01b3886d6143cbfd851a37883","templates\u002Fco-develop\u002F.codex\u002Fskills\u002Fswe-solve",9,"https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards","https:\u002F\u002Fgithub.com\u002F5throck","Experienced in digital transformation, enterprise IT, startup acceleration, and business strategy. Focused on building practical systems that connect technolo","2026-11-14 21:22:34",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add 5throck\u002Fai-workspace-standards --skill swe-solve",{"tool":49,"command":50},"bunx","bunx skills add 5throck\u002Fai-workspace-standards --skill swe-solve",{"tool":52,"command":53},"pnpm","pnpm dlx skills add 5throck\u002Fai-workspace-standards --skill swe-solve","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-develop\u002F.codex\u002Fskills\u002Fswe-solve\u002FSKILL.md",true,[],[58,66,71,76,81,86],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":65},"01M7BBJDYHJMGTJYSC37JVWY8S","i18n-layout","Text layout and encoding guidance: character encoding (UTF-8, legacy Korean code pages, BOM hazards), line endings, RTL\u002Fbidi handling, and script-specific font selection (Hangul focus). Use when: encoding is corrupted or mojibake appears, an RTL locale must render correctly, fonts must be chosen for a script, or CRLF\u002FBOM issues surface.","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":67,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":65},"01M7BBJ9XHAAS1AVGKZZ841VBZ","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.hermes\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],{"skillNo":72,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":65},"01M7BBJ5C3X8TKFKG5R9P9P49W","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.gemini\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],{"skillNo":77,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":65},"01M7BBJ1B52X0QMJ2QVBMPJB37","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.codex\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],{"skillNo":82,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":65},"01M7BBHX91BW2Q2R276MRX5AW3","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.claude\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],{"skillNo":87,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":65},"01M7BBHQWGXPSFRWN1PRC2NMMV","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.agents\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[]]