Agent skill

tasks-bug-diagnosis

Use when diagnosing bugs, analyzing errors/stack traces, or performing root cause analysis with evidence-based debugging protocols.

majiayu000534★ · 1 repos on radarProfile →
claude-codecan modify filesMIT
Install
npx skills add majiayu000/claude-skill-registry --skill tasks-bug-diagnosis-congdon1207-agents-md-2 --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 9 KB
Bundled scripts: none
Allowed tools: ReadWriteEditGrepGlobBashTaskTodoWrite
Path: skills/analysis/tasks-bug-diagnosis-congdon1207-agents-md-2/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

> **Skill Variant:** Use this skill for **autonomous, structured debugging workflows** with comprehensive verification protocols. For interactive debugging sessions with user feedback, use `bug-diagnosis` instead. # Bug Diagnosis Workflow ## Core Anti-Hallucination Protocols ### ASSUMPTION_VALIDATION_CHECKPOINT Before every major operation: 1. "What assumptions am I making about [X]?" 2. "Have I verified this with actual code evidence?" 3. "Could I be wrong about [specific pattern/relationship]?" ### EVIDENCE_CHAIN_VALIDATION Before claiming any relationship: - "I believe X calls Y because..." → show actual code - "This follows pattern Z because..." → cite specific examples - "Service A owns B because..." → grep for actual boundaries ### CONTEXT_ANCHOR_SYSTEM Every 10 operations: 1. Re-read the original task 2. Verify current operation aligns with goals 3. Check if solving the right problem --- ## Quick Verification Checklist **Before removing/changing ANY code:** - [ ] Searched static imports? - [ ] Searched string literals in code? - [ ] Checked dynamic invocations (attributes, reflection)? - [ ] Read actual implementations? - [ ] Traced who depends on this? - [ ] Assessed what b

What's inside
Steps it walks through
  1. Core Anti-Hallucination Protocols
  2. ASSUMPTIONVALIDATIONCHECKPOINT
  3. EVIDENCECHAINVALIDATION
  4. CONTEXTANCHORSYSTEM
  5. Quick Verification Checklist
  6. Phase 1: Bug Report Analysis
  7. Phase 2: Evidence Gathering
  8. Multi-Pattern Search Strategy
  9. Dependency Tracing
  10. Error-Specific Searches
  11. EasyPlatform-Specific Searches
  12. Phase 3: Root Cause Analysis
  13. Analysis Dimensions
  14. Ranked Causes
Ships with 1 file
  • metadata.json
Commands it runs
grep -r "ExactClassName" --include="*.cs" --include="*.ts"
grep -r "ClassName\|className\|class_name" --include="*.cs"
grep -r '"ClassName"' --include="*.cs" --include="*.json" --include="*.config"
grep -r "typeof(.*ClassName)\|nameof(.*ClassName)" --include="*.cs"
grep -r "ClassName" --include="*.json" --include="appsettings*.json"
grep -r "\[.*ClassName.*\]" --include="*.cs"
Direct usages (imports)
grep -r "using.*{Namespace}" --include="*.cs"
Interface implementations
grep -r ": I{ClassName}\|: I{ClassName}," --include="*.cs"
More from claude-skill-registry
All skills →
About this skill
What does the tasks-bug-diagnosis skill do?

Use when diagnosing bugs, analyzing errors/stack traces, or performing root cause analysis with evidence-based debugging protocols.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill tasks-bug-diagnosis-congdon1207-agents-md-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going