[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AAJJZSH2DPV3KRGE1H40MM":3,"skill-same:01M7AAJJZSH2DPV3KRGE1H40MM":50},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"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":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":27,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7AAJJZSH2DPV3KRGE1H40MM","diagnosing-bugs",null,"Diagnose hard bugs and performance regressions, and repair them when authorized. Use when the user asks to diagnose or debug, reports something broken\u002Fthrowing\u002Ffailing\u002Fslow, or explicitly asks to fix a suspected bug; default to diagnosis-only unless repair is requested.","joeloverbeck\u002Fskill-evidence","joeloverbeck","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F120873?v=4","01M758KCBJ0GWAPGN74C9NJF8T","01M7AAJ49JAQNVPTMQSWVB57TY",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fskill-evidence\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fdiagnosing-bugs\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: diagnosing-bugs\ndescription: Diagnose hard bugs and performance regressions, and repair them when authorized. Use when the user asks to diagnose or debug, reports something broken\u002Fthrowing\u002Ffailing\u002Fslow, or explicitly asks to fix a suspected bug; default to diagnosis-only unless repair is requested.\n---\n\n# Diagnosing Bugs\n\nA discipline for hard bugs. Skip phases only when explicitly justified.\n\nWhen exploring the codebase, read `CONTEXT.md` (if it exists) to get a clear mental model of the relevant modules, and check ADRs in the area you're touching.\n\n## Redact\n\nThis skill has you show commands, outputs and captured artifacts. **Redact every secret first** — write `\u003CREDACTED>` in its place. Build loops against env vars, so the credential stays in the environment rather than in what you show. Captured artifacts carry auth headers: quote only the lines that carry the signal.\n\nIf the redacted output is not enough to diagnose the bug, say so and ask the user.\n\n## Request Mode\n\nClassify the request before any mutation:\n\n- **Diagnosis only** — run Phases 1–4 as needed, then stop with the failure-surface classification, supported causal finding, confidence and remaining unknowns, and repair options. Do not enter Phase 5.\n- **Diagnosis and repair** — run the full loop only when the user explicitly asked to fix or change the system, or later authorizes one of the repair options.\n\nWhen scope is ambiguous, default to diagnosis only. Permission for temporary instrumentation authorizes only that instrumentation, not the eventual repair.\n\n## Phase 1 — Build a feedback loop\n\n**This is the skill.** Everything else is mechanical. If you have a **tight** pass\u002Ffail signal for the bug — one that goes red on _this_ bug — you will find the cause; bisection, hypothesis-testing, and instrumentation all just consume it. If you don't have one, no amount of staring at code will save you.\n\nSpend disproportionate effort here. **Be aggressive. Be creative. Refuse to give up.**\n\n### Ways to construct one — try them in roughly this order\n\n1. **Failing test** at whatever seam reaches the bug — unit, integration, e2e.\n2. **Curl \u002F HTTP script** against a running dev server.\n3. **CLI invocation** with a fixture input, diffing stdout against a known-good snapshot.\n4. **Headless browser script** (Playwright \u002F Puppeteer) — drives the UI, asserts on DOM\u002Fconsole\u002Fnetwork.\n5. **Replay a captured trace.** Save a real network request \u002F payload \u002F event log to disk; replay it through the code path in isolation.\n6. **Throwaway harness.** Spin up a minimal subset of the system (one service, mocked deps) that exercises the bug code path with a single function call.\n7. **Property \u002F fuzz loop.** If the bug is \"sometimes wrong output\", run a budgeted random sample, record the observed failure rate, and retain failing seeds as fixtures.\n8. **Bisection harness.** If the bug appeared between two known states (commit, dataset, version), automate \"boot at state X, check, repeat\" so you can `git bisect run` it.\n9. **Differential loop.** Run the same input through old-version vs new-version (or two configs) and diff outputs.\n10. **HITL bash script.** Last resort. If a human must click, drive _them_ with `scripts\u002Fhitl-loop.template.sh` so the loop is still structured. Captured output feeds back to you.\n\nA tight feedback loop materially reduces uncertainty; it does not establish the cause or prove the repair.\n\n### Tighten the loop\n\nTreat the loop as a product. Once you have _a_ loop, **tighten** it:\n\n- Can I make it faster? (Cache setup, skip unrelated init, narrow the test scope.)\n- Can I make the signal sharper? (Assert on the specific symptom, not \"didn't crash\".)\n- Can I make it more deterministic? (Pin time, seed RNG, isolate filesystem, freeze network.)\n\nA loop is tight when it is specific and deterministic enough to compare probes, and cheap enough to rerun after every meaningful change within the task's diagnostic budget. Record its wall time and failure rate instead of applying a universal duration cutoff.\n\n### Non-deterministic bugs\n\nThe goal is not a clean repro but enough observed failures to compare hypotheses within the available time or cost budget. Measure the baseline rate, estimate expected failures per batch (`attempts × rate`), and choose a batch that should yield several observations. A low raw rate remains usable when attempts are cheap and agent-runnable; when expected observations are too sparse, parallelise, add stress, narrow timing windows, or inject sleeps until the loop becomes informative. Record the rate, batch size, run cost, and observed failures instead of applying a universal percentage cutoff.\n\n### When you genuinely cannot build a loop\n\nStop and say so explicitly. List what you tried. Ask the user for: (a) access to whatever environment reproduces it, (b) a redacted captured artifact (HAR file, log dump, core dump, screen recording with timestamps), or (c) permission to add temporary production instrumentation. Do **not** proceed to hypothesise without a loop.\n\n### Completion criterion — a tight loop that goes red\n\nPhase 1 is done when the loop is **tight** and **red-capable**: you can name **one command** — a script path, a test invocation, a curl — that you have **already run at least once** (show the invocation and its output, redacted), and that is:\n\n- [ ] **Red-capable** — it drives the actual bug code path and asserts the **user's exact symptom**, so it can go red on this bug and green once fixed. Not \"runs without erroring\" — it must be able to _catch this specific bug_.\n- [ ] **Deterministic** — same verdict every run (flaky bugs: a pinned, high reproduction rate, per above).\n- [ ] **Affordable** — cheap enough to rerun after every meaningful probe within the task's diagnostic budget; record its wall time and per-batch cost.\n- [ ] **Agent-runnable** — you can run it unattended; a human in the loop only via `scripts\u002Fhitl-loop.template.sh`.\n\nIf you catch yourself reading code to build a theory before this command exists, **stop — jumping straight to a hypothesis is the exact failure this skill prevents.** No red-capable command, no Phase 2.\n\n## Phase 2 — Reproduce + minimise\n\nRun the loop. Watch it go red — the bug appears.\n\nConfirm:\n\n- [ ] The loop produces the failure mode the **user** described — not a different failure that happens to be nearby. Wrong bug = wrong fix.\n- [ ] The failure is reproducible across multiple runs (or, for non-deterministic bugs, reproducible at a high enough rate to debug against).\n- [ ] You have captured the exact symptom (error message, wrong output, slow timing) so later phases can verify the fix actually addresses it.\n\n### Classify the failure surface\n\nBefore calling the red signal \"the bug\", record one row per distinct failure:\n\n| Field | Required content |\n|---|---|\n| Observed signal | Exact error, wrong output, timing, or rejection |\n| Controlling contract | Assertion, schema, protocol, specification, or user expectation that makes it red |\n| Expected | Required value or behavior |\n| Actual | Observed value or behavior |\n| Fault class | `implementation defect`, `input defect`, `protocol prerequisite`, `substantive failure`, or `unknown` |\n| Causal impact | What this failure blocks or invalidates |\n| Unaffected scope | Behavior, evidence, or verdicts this failure does not decide |\n\nA validator rejection may be intended enforcement rather than a validator defect. Keep separate rows when one run exposes failures in different layers. Show the classification and a plain-language causal chain to the user before recommending repair; if the class remains `unknown`, do not imply that an implementation is defective.\n\n### Minimise\n\nOnce it's red, shrink the repro to the **smallest scenario that still goes red**. Cut inputs, callers, config, data, and steps **one at a time**, re-running the loop after each cut — keep only what's load-bearing for the failure.\n\nWhy bother: a minimal repro shrinks the hypothesis space in Phase 3 (fewer moving parts left to suspect) and becomes the clean regression test in Phase 5.\n\nDone when **every remaining element is load-bearing** — removing any one of them makes the loop go green.\n\nDo not proceed until you have reproduced **and** minimised.\n\n## Phase 3 — Hypothesise\n\nUnless the direct-proof exception below applies, generate **3–5 ranked hypotheses** before testing any of them. Single-hypothesis generation anchors on the first plausible idea.\n\n**Direct-proof exception.** Skip the ranked set only when the red signal names the exact mismatch, the controlling assertion is current, and direct source bytes establish one complete causal chain. Record `red signal → controlling assertion → expected → actual → mechanism` plus one observation that would falsify the chain, and show it to the user. If any link is inferred, ambiguous, or contested, use the ranked-hypothesis path.\n\nEach hypothesis must be **falsifiable**: state the prediction it makes.\n\n> Format: \"If \u003CX> is the cause, then \u003Cchanging Y> will make the bug disappear \u002F \u003Cchanging Z> will make it worse.\"\n\nIf you cannot state the prediction, the hypothesis is a vibe — discard or sharpen it.\n\n**Show the ranked list to the user before testing.** They often have domain knowledge that re-ranks instantly (\"we just deployed a change to #3\"), or know hypotheses they've already ruled out. Cheap checkpoint, big time saver. Don't block on it — proceed with your ranking if the user is AFK.\n\n## Phase 4 — Instrument\n\nEach probe must map to a specific prediction from Phase 3. **Change one variable at a time.**\n\nTool preference:\n\n1. **Debugger \u002F REPL inspection** if the env supports it. One breakpoint beats ten logs.\n2. **Targeted logs** at the boundaries that distinguish hypotheses.\n3. Never \"log everything and grep\".\n\n**Tag every debug log** with a unique prefix, e.g. `[DEBUG-a4f2]`. Cleanup at the end becomes a single grep. Untagged logs survive; tagged logs die.\n\n**Perf branch.** For performance regressions, logs are usually wrong. Instead: establish a baseline measurement (timing harness, `performance.now()`, profiler, query plan), then bisect. Measure first, fix second.\n\n## Phase 5 — Authorized fix + regression test\n\nEnter this phase only on a diagnosis-and-repair request. A diagnosis-only run ends after the supported causal finding and repair options are delivered.\n\n### Artifact lifecycle gate\n\nBefore editing, read the repository or project convention that owns the target artifact and classify it as a mutable working surface or frozen, published, or custodied evidence. Mutate only a mutable owner. For frozen evidence, preserve the producing bytes, hashes, invalid attempts, and superseded artifacts, then use the owner's versioning or supersession route and rerun every downstream check it requires.\n\nA stronger governing or companion workflow's custody, freeze, or supersession protocol takes precedence and is followed unchanged.\n\nWrite the regression test **before the fix** — but only if there is a **correct seam** for it.\n\nA correct seam is one where the test exercises the **real bug pattern** as it occurs at the call site. If the only available seam is too shallow (single-caller test when the bug needs multiple callers, unit test that can't replicate the chain that triggered the bug), a regression test there gives false confidence.\n\n**If no correct seam exists, that itself is the finding.** Note it. The codebase architecture is preventing the bug from being locked down. Flag this for the next phase.\n\nIf a correct seam exists:\n\n1. Turn the minimised repro into a failing test at that seam.\n2. Watch it fail.\n3. Apply the authorized fix at the earliest mutable owner, or create the governed superseding or versioned artifact when the lifecycle owner forbids in-place change.\n4. Watch it pass.\n5. Re-run the Phase 1 feedback loop against the original (un-minimised) scenario.\n\n## Phase 6 — Authorized-repair cleanup + post-mortem\n\nRequired before declaring an authorized repair done:\n\n- [ ] Original repro no longer reproduces (re-run the Phase 1 loop)\n- [ ] Regression test passes (or absence of seam is documented)\n- [ ] All `[DEBUG-...]` instrumentation removed (`grep` the prefix)\n- [ ] Truly throwaway prototypes deleted (or moved to a clearly-marked debug location); captured traces, invalid attempts, frozen artifacts, and superseded evidence retained whenever the governing custody or provenance contract requires them\n- [ ] The proven causal chain or hypothesis that turned out correct is stated in the commit \u002F PR message — so the next debugger learns\n\n**Then ask: what would have prevented this bug?** If the answer involves architectural change (no good test seam, tangled callers, hidden coupling) tell the user to run the `improve-codebase-architecture` skill with the specifics. Make the recommendation **after** the fix is in, not before — you have more information now than when you started.\n","# Diagnosing Bugs\n\nA discipline for hard bugs. Skip phases only when explicitly justified.\n\nWhen exploring the codebase, read `CONTEXT.md` (if it exists) to get a clear mental model of the relevant modules, and check ADRs in the area you're touching.\n\n## Redact\n\nThis skill has you show commands, outputs and captured artifacts. **Redact every secret first** — write `\u003CREDACTED>` in its place. Build loops against env vars, so the credential stays in the environment rather than in what you show. Captured artifacts carry auth headers: quote only the lines that carry the signal.\n\nIf the redacted output is not enough to diagnose the bug, say so and ask the user.\n\n## Request Mode\n\nClassify the request before any mutation:\n\n- **Diagnosis only** — run Phases 1–4 as needed, then stop with the failure-surface classification, supported causal finding, confidence and remaining unknowns, and repair options. Do not enter Phase 5.\n- **Diagnosis and repair** — run the full loop only when the user explicitly asked to fix or change the system, or later authorizes one of the repair options.\n\nWhen scope is ambiguous, default to diagnosis only. Permission for temporary instrumentation authorizes only that instrumentation, not the eventual repair.\n\n## Phase 1 — Build a feedback loop\n\n**This is the skill.** Everything else is mechanical. If you have a **tight** pass\u002Ffail signal for the bug — one that goes red on _this_ bug — you will find the cause; bisection, hypothesis-testing, and instrumentation all just consume it. If you don't have one, no amount of staring at code will save you.\n\nSpend disproportionate effort here. **Be aggressive. Be creative. Refuse to give up.**\n\n### Ways to construct one — try them in roughly this order\n\n1. **Failing test** at whatever seam reaches the bug — unit, integration, e2e.\n2. **Curl \u002F HTTP script** against a running dev server.\n3. **CLI invocation** with a fixture input, diffing stdout against a known-good snapshot.\n4. **Headless browser script** (Playwright \u002F Puppeteer) — drives the UI, asserts on DOM\u002Fconsole\u002Fnetwork.\n5. **Replay a captured trace.** Save a real network request \u002F payload \u002F event log to disk; replay it through the code path in isolation.\n6. **Throwaway harness.** Spin up a minimal subset of the system (one service, mocked deps) that exercises the bug code path with a single function call.\n7. **Property \u002F fuzz loop.** If the bug is \"sometimes wrong output\", run a budgeted random sample, record the observed failure rate, and retain failing seeds as fixtures.\n8. **Bisection harness.** If the bug appeared between two known states (commit, dataset, version), automate \"boot at state X, check, repeat\" so you can `git bisect run` it.\n9. **Differential loop.** Run the same input through old-version vs new-version (or two configs) and diff outputs.\n10. **HITL bash script.** Last resort. If a human must click, drive _them_ with `scripts\u002Fhitl-loop.template.sh` so the loop is still structured. Captured output feeds back to you.\n\nA tight feedback loop materially reduces uncertainty; it does not establish the cause or prove the repair.\n\n### Tighten the loop\n\nTreat the loop as a product. Once you have _a_ loop, **tighten** it:\n\n- Can I make it faster? (Cache setup, skip unrelated init, narrow the test scope.)\n- Can I make the signal sharper? (Assert on the specific symptom, not \"didn't crash\".)\n- Can I make it more deterministic? (Pin time, seed RNG, isolate filesystem, freeze network.)\n\nA loop is tight when it is specific and deterministic enough to compare probes, and cheap enough to rerun after every meaningful change within the task's diagnostic budget. Record its wall time and failure rate instead of applying a universal duration cutoff.\n\n### Non-deterministic bugs\n\nThe goal is not a clean repro but enough observed failures to compare hypotheses within the available time or cost budget. Measure the baseline rate, estimate expected failures per batch (`attempts × rate`), and choose a batch that should yield several observations. A low raw rate remains usable when attempts are cheap and agent-runnable; when expected observations are too sparse, parallelise, add stress, narrow timing windows, or inject sleeps until the loop becomes informative. Record the rate, batch size, run cost, and observed failures instead of applying a universal percentage cutoff.\n\n### When you genuinely cannot build a loop\n\nStop and say so explicitly. List what you tried. Ask the user for: (a) access to whatever environment reproduces it, (b) a redacted captured artifact (HAR file, log dump, core dump, screen recording with timestamps), or (c) permission to add temporary production instrumentation. Do **not** proceed to hypothesise without a loop.\n\n### Completion criterion — a tight loop that goes red\n\nPhase 1 is done when the loop is **tight** and **red-capable**: you can name **one command** — a script path, a test invocation, a curl — that you have **already run at least once** (show the invocation and its output, redacted), and that is:\n\n- [ ] **Red-capable** — it drives the actual bug code path and asserts the **user's exact symptom**, so it can go red on this bug and green once fixed. Not \"runs without erroring\" — it must be able to _catch this specific bug_.\n- [ ] **Deterministic** — same verdict every run (flaky bugs: a pinned, high reproduction rate, per above).\n- [ ] **Affordable** — cheap enough to rerun after every meaningful probe within the task's diagnostic budget; record its wall time and per-batch cost.\n- [ ] **Agent-runnable** — you can run it unattended; a human in the loop only via `scripts\u002Fhitl-loop.template.sh`.\n\nIf you catch yourself reading code to build a theory before this command exists, **stop — jumping straight to a hypothesis is the exact failure this skill prevents.** No red-capable command, no Phase 2.\n\n## Phase 2 — Reproduce + minimise\n\nRun the loop. Watch it go red — the bug appears.\n\nConfirm:\n\n- [ ] The loop produces the failure mode the **user** described — not a different failure that happens to be nearby. Wrong bug = wrong fix.\n- [ ] The failure is reproducible across multiple runs (or, for non-deterministic bugs, reproducible at a high enough rate to debug against).\n- [ ] You have captured the exact symptom (error message, wrong output, slow timing) so later phases can verify the fix actually addresses it.\n\n### Classify the failure surface\n\nBefore calling the red signal \"the bug\", record one row per distinct failure:\n\n| Field | Required content |\n|---|---|\n| Observed signal | Exact error, wrong output, timing, or rejection |\n| Controlling contract | Assertion, schema, protocol, specification, or user expectation that makes it red |\n| Expected | Required value or behavior |\n| Actual | Observed value or behavior |\n| Fault class | `implementation defect`, `input defect`, `protocol prerequisite`, `substantive failure`, or `unknown` |\n| Causal impact | What this failure blocks or invalidates |\n| Unaffected scope | Behavior, evidence, or verdicts this failure does not decide |\n\nA validator rejection may be intended enforcement rather than a validator defect. Keep separate rows when one run exposes failures in different layers. Show the classification and a plain-language causal chain to the user before recommending repair; if the class remains `unknown`, do not imply that an implementation is defective.\n\n### Minimise\n\nOnce it's red, shrink the repro to the **smallest scenario that still goes red**. Cut inputs, callers, config, data, and steps **one at a time**, re-running the loop after each cut — keep only what's load-bearing for the failure.\n\nWhy bother: a minimal repro shrinks the hypothesis space in Phase 3 (fewer moving parts left to suspect) and becomes the clean regression test in Phase 5.\n\nDone when **every remaining element is load-bearing** — removing any one of them makes the loop go green.\n\nDo not proceed until you have reproduced **and** minimised.\n\n## Phase 3 — Hypothesise\n\nUnless the direct-proof exception below applies, generate **3–5 ranked hypotheses** before testing any of them. Single-hypothesis generation anchors on the first plausible idea.\n\n**Direct-proof exception.** Skip the ranked set only when the red signal names the exact mismatch, the controlling assertion is current, and direct source bytes establish one complete causal chain. Record `red signal → controlling assertion → expected → actual → mechanism` plus one observation that would falsify the chain, and show it to the user. If any link is inferred, ambiguous, or contested, use the ranked-hypothesis path.\n\nEach hypothesis must be **falsifiable**: state the prediction it makes.\n\n> Format: \"If \u003CX> is the cause, then \u003Cchanging Y> will make the bug disappear \u002F \u003Cchanging Z> will make it worse.\"\n\nIf you cannot state the prediction, the hypothesis is a vibe — discard or sharpen it.\n\n**Show the ranked list to the user before testing.** They often have domain knowledge that re-ranks instantly (\"we just deployed a change to #3\"), or know hypotheses they've already ruled out. Cheap checkpoint, big time saver. Don't block on it — proceed with your ranking if the user is AFK.\n\n## Phase 4 — Instrument\n\nEach probe must map to a specific prediction from Phase 3. **Change one variable at a time.**\n\nTool preference:\n\n1. **Debugger \u002F REPL inspection** if the env supports it. One breakpoint beats ten logs.\n2. **Targeted logs** at the boundaries that distinguish hypotheses.\n3. Never \"log everything and grep\".\n\n**Tag every debug log** with a unique prefix, e.g. `[DEBUG-a4f2]`. Cleanup at the end becomes a single grep. Untagged logs survive; tagged logs die.\n\n**Perf branch.** For performance regressions, logs are usually wrong. Instead: establish a baseline measurement (timing harness, `performance.now()`, profiler, query plan), then bisect. Measure first, fix second.\n\n## Phase 5 — Authorized fix + regression test\n\nEnter this phase only on a diagnosis-and-repair request. A diagnosis-only run ends after the supported causal finding and repair options are delivered.\n\n### Artifact lifecycle gate\n\nBefore editing, read the repository or project convention that owns the target artifact and classify it as a mutable working surface or frozen, published, or custodied evidence. Mutate only a mutable owner. For frozen evidence, preserve the producing bytes, hashes, invalid attempts, and superseded artifacts, then use the owner's versioning or supersession route and rerun every downstream check it requires.\n\nA stronger governing or companion workflow's custody, freeze, or supersession protocol takes precedence and is followed unchanged.\n\nWrite the regression test **before the fix** — but only if there is a **correct seam** for it.\n\nA correct seam is one where the test exercises the **real bug pattern** as it occurs at the call site. If the only available seam is too shallow (single-caller test when the bug needs multiple callers, unit test that can't replicate the chain that triggered the bug), a regression test there gives false confidence.\n\n**If no correct seam exists, that itself is the finding.** Note it. The codebase architecture is preventing the bug from being locked down. Flag this for the next phase.\n\nIf a correct seam exists:\n\n1. Turn the minimised repro into a failing test at that seam.\n2. Watch it fail.\n3. Apply the authorized fix at the earliest mutable owner, or create the governed superseding or versioned artifact when the lifecycle owner forbids in-place change.\n4. Watch it pass.\n5. Re-run the Phase 1 feedback loop against the original (un-minimised) scenario.\n\n## Phase 6 — Authorized-repair cleanup + post-mortem\n\nRequired before declaring an authorized repair done:\n\n- [ ] Original repro no longer reproduces (re-run the Phase 1 loop)\n- [ ] Regression test passes (or absence of seam is documented)\n- [ ] All `[DEBUG-...]` instrumentation removed (`grep` the prefix)\n- [ ] Truly throwaway prototypes deleted (or moved to a clearly-marked debug location); captured traces, invalid attempts, frozen artifacts, and superseded evidence retained whenever the governing custody or provenance contract requires them\n- [ ] The proven causal chain or hypothesis that turned out correct is stated in the commit \u002F PR message — so the next debugger learns\n\n**Then ask: what would have prevented this bug?** If the answer involves architectural change (no good test seam, tangled callers, hidden coupling) tell the user to run the `improve-codebase-architecture` skill with the specifics. Make the recommendation **after** the fix is in, not before — you have more information now than when you started.\n",{"name":5,"description":7},"main","9b13db1df193bd0709752040255bd64b682d3242",".claude\u002Fskills\u002Fdiagnosing-bugs","https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fskill-evidence","https:\u002F\u002Fdocs.rs\u002Fskill-evidence","https:\u002F\u002Fgithub.com\u002Fjoeloverbeck","2026-08-23 17:23:53",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add joeloverbeck\u002Fskill-evidence --skill diagnosing-bugs",{"tool":36,"command":37},"bunx","bunx skills add joeloverbeck\u002Fskill-evidence --skill diagnosing-bugs",{"tool":39,"command":40},"pnpm","pnpm dlx skills add joeloverbeck\u002Fskill-evidence --skill diagnosing-bugs","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fskill-evidence\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fdiagnosing-bugs\u002FSKILL.md",true,[44],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Fhitl-loop.template.sh","SCRIPT","脚本",1318,"https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fskill-evidence\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fdiagnosing-bugs\u002Fscripts\u002Fhitl-loop.template.sh",[51,58,63,70,75,80],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":18},"01M7AAQDXB1QQET7VSTF1FCEET","triage","Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.","https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fskill-evidence\u002Fblob\u002Fmain\u002Freports\u002Fskill-evidence\u002Ftriage\u002Freviews\u002Ffce6031a-a8f1-44b9-93cc-5c27488a51d3\u002Fcandidate\u002FSKILL.md",[],[],{"skillNo":59,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":18},"01M7AAQBCSHN0ZH9MHQZNEHCGR","https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fskill-evidence\u002Fblob\u002Fmain\u002Freports\u002Fskill-evidence\u002Ftriage\u002Freviews\u002F48b04150-c9c8-42a7-982a-324aceb6d21e\u002Fheld\u002Fember\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":18},"01M7AAQ8BDCGNPBVJVGQ1KWSN7","tdd","Test-driven development. Use when the user wants a red-green development loop or integration tests.","https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fskill-evidence\u002Fblob\u002Fmain\u002Freports\u002Fskill-evidence\u002Ftdd\u002Freviews\u002Frev_c25c6d82-756b-49e4-85ed-bd164820f2f2\u002Fpre-land-backup\u002FSKILL.md",[],[],{"skillNo":71,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M7AAQ6DRHY95HPCDGG7TBP93","https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fskill-evidence\u002Fblob\u002Fmain\u002Freports\u002Fskill-evidence\u002Ftdd\u002Freviews\u002Frev_c25c6d82-756b-49e4-85ed-bd164820f2f2\u002Fcandidate\u002FSKILL.md",[],[],{"skillNo":76,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M7AAQ3XN1HSP13RC35NFTKT0","https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fskill-evidence\u002Fblob\u002Fmain\u002Freports\u002Fskill-evidence\u002Ftdd\u002Freviews\u002Frev_3e39da1f-a737-4029-bd88-f710519fe3de\u002Fpre-land-backup\u002FSKILL.md",[],[],{"skillNo":81,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M7AAQ1NGVGK62GB5Z6JSNJ76","https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fskill-evidence\u002Fblob\u002Fmain\u002Freports\u002Fskill-evidence\u002Ftdd\u002Freviews\u002Frev_3e39da1f-a737-4029-bd88-f710519fe3de\u002Fcandidate\u002FSKILL.md",[],[]]