[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HZ2MPZ9KHPPTZHSZ96KQGF":3,"skill-same:01M6HZ2MPZ9KHPPTZHSZ96KQGF":70},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":55,"install":56,"resources":69},"01M6HZ2MPZ9KHPPTZHSZ96KQGF","bug-investigation",null,"Use for defects, regressions, outages, flaky tests, and unexpected behavior. Guides the agent through triage, containment, reproduction, hypotheses, root-cause evidence, fix verification, and recurrence prevention. Do not use as the primary workflow for new features; use double-diamond-feature instead.","ldilov\u002Fharness-forge","ldilov","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F25016670?v=4","01M6HYXAEJP0KYT2DF86WYN8QK","Lazar Dilov","01M6HYXAJETHAW5DD5TAAFEQ7D",6,"GPL-3.0","https:\u002F\u002Fgithub.com\u002Fldilov\u002Fharness-forge\u002Fblob\u002Fmain\u002Fskills\u002Fbug-investigation\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"investigation","Bug Investigation","bug","root-cause","features","defects","for","guides","as","feature","tests","do","workflow","evidence","use","fix","behavior","prevention","containment","verification","2026-11-10 10:12:30",false,"---\nname: bug-investigation\ndescription: Use for defects, regressions, outages, flaky tests, and unexpected behavior. Guides the agent through triage, containment, reproduction, hypotheses, root-cause evidence, fix verification, and recurrence prevention. Do not use as the primary workflow for new features; use double-diamond-feature instead.\n---\n\n# Bug Investigation\n\n## Trigger Signals\n\nUse this skill when the user reports:\n\n- broken behavior\n- a regression\n- a failing or flaky test\n- production degradation\n- incorrect data\u002Foutput\n- an incident-like symptom\n- a bug report with expected vs actual behavior\n\nDo not use as the primary workflow for new features. Use `double-diamond-feature` instead.\n\n## Workflow\n\n### 1. Triage\n\nClassify:\n\n- severity: low, medium, high, incident\n- user\u002Fsystem impact\n- data risk\n- production risk\n- containment needed or not\n\nIf harm is ongoing, contain first and preserve evidence.\n\n### 2. Problem Report\n\nCapture:\n\n- expected behavior\n- actual behavior\n- reproduction steps or evidence gap\n- environment\u002Fversion\u002Ftime window\n- relevant logs\u002Ftraces\u002Fscreenshots if available\n\n### 3. Evidence Inspection\n\nInspect relevant code, tests, recent changes, config, logs, and runtime artifacts. Reuse Harness Forge surfaces when present: `.hforge\u002Fruntime\u002Frepo\u002Frepo-map.json`, `.hforge\u002Fruntime\u002Ffindings\u002Frisk-signals.json`. Label assumptions clearly.\n\n### 4. Hypotheses\n\nCreate a ranked hypothesis table:\n\n| ID | Hypothesis | Likelihood | Evidence for | Evidence against | Test | Status |\n|---|---|---|---|---|---|---|\n\nPrefer tests that rule out multiple causes. Record negative results.\n\n### 5. Fix\n\nImplement the smallest fix for the confirmed cause. Avoid broad refactors unless the cause requires them.\n\n### 6. Verify\n\nVerify using:\n\n- reproduction now passes\n- regression test added or updated\n- relevant existing tests\n- manual verification if automated tests are unavailable\n\n### 7. Prevent Recurrence\n\nRecommend one or more:\n\n- regression test\n- input validation\n- type\u002Fschema guard\n- monitor\u002Falert\n- docs\u002Fplaybook update\n- postmortem or A3\u002F8D-lite for severe\u002Frecurrent issues\n\n## Output Before Fix\n\n```markdown\n## Bug Investigation Frame\n\n### Triage\n- Severity:\n- Impact:\n- Data risk:\n- Containment:\n\n### Problem report\n- Expected:\n- Actual:\n- Reproduction:\n- Environment:\n\n### Evidence\n- User-provided:\n- Repository\u002Fruntime:\n- Assumptions:\n\n### Hypotheses\n| ID | Hypothesis | Likelihood | Evidence for | Evidence against | Test | Status |\n|---|---|---|---|---|---|---|\n\n### Fix plan\n- Confirmed\u002Flikely cause:\n- Proposed fix:\n- Verification:\n- Prevention:\n```\n\n## Output After Fix\n\n```markdown\n## Bug Fix Report\n- Root cause evidence:\n- Changes made:\n- Verification:\n- Regression coverage:\n- Recurrence prevention:\n- Follow-up\u002Fpostmortem need:\n```\n\n## Root-Cause Honesty\n\nDo not claim a root cause unless it is supported by reproduction, logs, tests, code-path evidence, or clearly stated confidence.\n\n## Target Compatibility\n\nThis skill is plain-markdown and host-agnostic. Claude Code invokes it as `\u002Fbug-investigation`; Codex selects it via `\u002Fskills` or `$bug-investigation`. Do not rely on host-native hooks or interactive prompts.\n","# Bug Investigation\n\n## Trigger Signals\n\nUse this skill when the user reports:\n\n- broken behavior\n- a regression\n- a failing or flaky test\n- production degradation\n- incorrect data\u002Foutput\n- an incident-like symptom\n- a bug report with expected vs actual behavior\n\nDo not use as the primary workflow for new features. Use `double-diamond-feature` instead.\n\n## Workflow\n\n### 1. Triage\n\nClassify:\n\n- severity: low, medium, high, incident\n- user\u002Fsystem impact\n- data risk\n- production risk\n- containment needed or not\n\nIf harm is ongoing, contain first and preserve evidence.\n\n### 2. Problem Report\n\nCapture:\n\n- expected behavior\n- actual behavior\n- reproduction steps or evidence gap\n- environment\u002Fversion\u002Ftime window\n- relevant logs\u002Ftraces\u002Fscreenshots if available\n\n### 3. Evidence Inspection\n\nInspect relevant code, tests, recent changes, config, logs, and runtime artifacts. Reuse Harness Forge surfaces when present: `.hforge\u002Fruntime\u002Frepo\u002Frepo-map.json`, `.hforge\u002Fruntime\u002Ffindings\u002Frisk-signals.json`. Label assumptions clearly.\n\n### 4. Hypotheses\n\nCreate a ranked hypothesis table:\n\n| ID | Hypothesis | Likelihood | Evidence for | Evidence against | Test | Status |\n|---|---|---|---|---|---|---|\n\nPrefer tests that rule out multiple causes. Record negative results.\n\n### 5. Fix\n\nImplement the smallest fix for the confirmed cause. Avoid broad refactors unless the cause requires them.\n\n### 6. Verify\n\nVerify using:\n\n- reproduction now passes\n- regression test added or updated\n- relevant existing tests\n- manual verification if automated tests are unavailable\n\n### 7. Prevent Recurrence\n\nRecommend one or more:\n\n- regression test\n- input validation\n- type\u002Fschema guard\n- monitor\u002Falert\n- docs\u002Fplaybook update\n- postmortem or A3\u002F8D-lite for severe\u002Frecurrent issues\n\n## Output Before Fix\n\n```markdown\n## Bug Investigation Frame\n\n### Triage\n- Severity:\n- Impact:\n- Data risk:\n- Containment:\n\n### Problem report\n- Expected:\n- Actual:\n- Reproduction:\n- Environment:\n\n### Evidence\n- User-provided:\n- Repository\u002Fruntime:\n- Assumptions:\n\n### Hypotheses\n| ID | Hypothesis | Likelihood | Evidence for | Evidence against | Test | Status |\n|---|---|---|---|---|---|---|\n\n### Fix plan\n- Confirmed\u002Flikely cause:\n- Proposed fix:\n- Verification:\n- Prevention:\n```\n\n## Output After Fix\n\n```markdown\n## Bug Fix Report\n- Root cause evidence:\n- Changes made:\n- Verification:\n- Regression coverage:\n- Recurrence prevention:\n- Follow-up\u002Fpostmortem need:\n```\n\n## Root-Cause Honesty\n\nDo not claim a root cause unless it is supported by reproduction, logs, tests, code-path evidence, or clearly stated confidence.\n\n## Target Compatibility\n\nThis skill is plain-markdown and host-agnostic. Claude Code invokes it as `\u002Fbug-investigation`; Codex selects it via `\u002Fskills` or `$bug-investigation`. Do not rely on host-native hooks or interactive prompts.\n",{"name":5,"description":7},"main","27337828f396bcf279d7c4353a4a4f0cdc97659f","skills\u002Fbug-investigation",1,"https:\u002F\u002Fgithub.com\u002Fldilov\u002Fharness-forge","https:\u002F\u002Fgithub.com\u002Fldilov","2026-05-19 21:48:38",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add ldilov\u002Fharness-forge --skill bug-investigation",{"tool":62,"command":63},"bunx","bunx skills add ldilov\u002Fharness-forge --skill bug-investigation",{"tool":65,"command":66},"pnpm","pnpm dlx skills add ldilov\u002Fharness-forge --skill bug-investigation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fldilov\u002Fharness-forge\u002Fblob\u002Fmain\u002Fskills\u002Fbug-investigation\u002FSKILL.md",true,[],[71,100,129,148,171,183],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":80,"publishedAt":44},"01M6HZ7WE4DSYWPX0W2JX9BD8K","typescript-engineering","typescript and javascript engineering guidance seeded from the harness forge knowledge base. use when the repo or task is dominated by .ts, .tsx, package.json, tsconfig, node.js services, react, next.js, frontend tooling, or multi-package workspaces where type boundaries matter.","https:\u002F\u002Fgithub.com\u002Fldilov\u002Fharness-forge\u002Fblob\u002Fmain\u002Fskills\u002Ftypescript-engineering\u002FSKILL.md",[77],{"categoryNo":78,"categoryName":79,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[81,82,83,84,85,86,87,88,89,90,91,92,93,38,94,95,96,97,98,99],"typescript","engineering","typescript engineering","frontend","javascript","react","harness","package","forge","Next.js","knowledge","node","repo","workspaces","tsx","task","next","knowledge base","type",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":112,"publishedAt":44},"01M6HZ7QRWHQP72E7DPB6W5S6C","token-budget-optimizer","compact context, reuse existing runtime artifacts, and choose the smallest authoritative surface before expanding prompt history. use when the task is growing large, when earlier repo intelligence already exists, or when repeated rescans would waste tokens without adding new evidence.","https:\u002F\u002Fgithub.com\u002Fldilov\u002Fharness-forge\u002Fblob\u002Fmain\u002Fskills\u002Ftoken-budget-optimizer\u002FSKILL.md",[106,107],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":108,"categoryName":109,"taxonomyType":110,"taxonomyTypeDesc":111},"01JBSEEDCAT000000000000040","财务","PROFESSION","适用职业",[113,114,115,116,117,118,119,120,93,121,122,38,37,96,123,124,125,126,127,128],"Budget","optimizer","token","token budget","token budget optimizer","artifacts","choose","history","prompt","context","intelligence","compact","tokens","runtime","reuse","Existing",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":138,"publishedAt":44},"01M6HZ7MMX3ZZP4KF2FVC2EHP0","test-strategy-and-coverage","Define right-sized test layers and coverage priorities for a change.","https:\u002F\u002Fgithub.com\u002Fldilov\u002Fharness-forge\u002Fblob\u002Fmain\u002Fskills\u002Ftest-strategy-and-coverage\u002FSKILL.md",[135],{"categoryNo":136,"categoryName":137,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[139,140,141,142,143,144,145,146,147,30],"test","strategy","coverage","test strategy","test strategy and coverage","change","priorities","define","layers",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":154,"publishedAt":44},"01M6HZ7HE9C6MGWT9JG17Z3Y3M","speckit-taskstoissues","Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.","https:\u002F\u002Fgithub.com\u002Fldilov\u002Fharness-forge\u002Fblob\u002Fmain\u002Fskills\u002Fspeckit-taskstoissues\u002FSKILL.md",[],[155,156,157,158,159,160,161,118,162,163,164,165,166,167,168,33,169,170,30,128],"speckit taskstoissues","speckit","design","directory","project structure","tasks","github issues","issues","specify","convert","dependency","structure","project","commands","actionable","kit",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":177,"publishedAt":44},"01M6HZ7E2NMYB9N2GKYVRF09AK","speckit-tasks","Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.","https:\u002F\u002Fgithub.com\u002Fldilov\u002Fharness-forge\u002Fblob\u002Fmain\u002Fskills\u002Fspeckit-tasks\u002FSKILL.md",[],[160,178,156,157,158,179,159,180,118,163,165,166,167,168,33,169,181,182,170,30],"speckit tasks","github","generate","spec-kit","with",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":189,"publishedAt":44},"01M6HZ7AS0E880YSZN4FEFF6QF","speckit-specify","Create or update the feature specification from a natural language feature description.","https:\u002F\u002Fgithub.com\u002Fldilov\u002Fharness-forge\u002Fblob\u002Fmain\u002Fskills\u002Fspeckit-specify\u002FSKILL.md",[],[163,190,156,158,191,179,159,192,193,194,195,196,166,167,168,33,181,182,197,170],"speckit specify","spec","create","update","templates","specification","natural language","feature specification"]