agentleFS
renanflustosarenanflustosa/octo-cluster/.claude/skills/systematic-debugging/SKILL.md

systematic-debugging

Skill3 starsChanged 23 days agoMITView on GitHub

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

190 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use chinese-code-review, chinese-commit-conventions and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Leodorareluctant259Skill

    chinese-code-review

    中文代码审查规范——在保持专业严谨的同时,用符合国内团队文化的方式给出有效反馈

    Also in 8 projects that use this

  • Leodorareluctant259Skill

    chinese-commit-conventions

    中文 Git 提交规范 — 适配国内团队的 commit message 规范和 changelog 自动化

    Also in 8 projects that use this

  • obraSkill

    diagnosing-superpowers

    Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.

    Also in 20 projects that use this

  • SethGammonSkill

    ascii-diagram

    Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.

    Also in 4 projects that use this

  • mjunaidcaSkill

    building-chatgpt-apps

    Guides creation of ChatGPT Apps with interactive widgets using OpenAI Apps SDK and MCP servers. Use when building ChatGPT custom apps with visual UI components, embedded widgets, or rich interactive experiences. Covers widget architecture, MCP server setup with FastMCP, response metadata, and Developer Mode configuration. NOT when building standard MCP servers without widgets (use building-mcp-servers skill instead).

    Also in 4 projects that use this

  • mjunaidcaSkill

    building-chat-interfaces

    Build AI chat interfaces with custom backends, authentication, and context injection. Use when integrating chat UI with AI agents, adding auth to chat, injecting user/page context, or implementing httpOnly cookie proxies. Covers ChatKitServer, useChatKit, and MCP auth patterns. NOT when building simple chatbots without persistence or custom agent integration.

    Also in 4 projects that use this

  • +2 more from Leodorareluctant259
  • +4 more from mjunaidca

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 177 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify fix and no regressions.

    line 38
  2. Distinctive:

    After root cause found, optional hardening: defense-in-depth.md, condition-based-waiting.md.

    line 41
  3. Distinctive:

    If truly environmental/external after full investigation: document findings, add handling/monitoring — do not skip phases to get there.

    line 70

“Common” is measured: kept by at least 6 in 10 of the 177 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Systematic Debugging

Adapted from obra/superpowers (MIT). Deep dives: references/ in this directory.

Iron Law

NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST

Complete Phase 1 before proposing fixes. Use for test failures, production bugs, build failures, perf issues — especially under time pressure or after a failed fix.

Phase 1: Root Cause Investigation

  1. Read errors — stack traces, line numbers, codes; do not skip warnings.
  2. Reproduce — exact steps; if flaky, gather data instead of guessing.
  3. Recent changes — git diff, deps, config, environment.
  4. Multi-component systems — log at each boundary (in/out, config propagation); run once to see where it breaks.
  5. Trace data flow — bad value upstream? See root-cause-tracing.md.

Phase 2: Pattern Analysis

Find working examples in the codebase. Compare broken vs working line by line. Read reference implementations fully before adapting.

Phase 3: Hypothesis and Testing

One hypothesis: "X is the cause because Y." Smallest test change; one variable. Failed? New hypothesis — do not stack fixes.

Phase 4: Implementation

  1. Failing repro (test or script) before the fix.
  2. Single fix at root cause — no bundled refactors.
  3. Verify fix and no regressions.
  4. ≥ 3 failed fix attempts → stop; question architecture with operator before fix #4.

After root cause found, optional hardening: defense-in-depth.md, condition-based-waiting.md.

Red flags — STOP, return to Phase 1

  • "Quick fix now, investigate later"
  • "Just try X and see"
  • Multiple changes before one verified hypothesis
  • Proposing fixes before tracing data flow
  • "One more attempt" after 2+ failures
ExcuseReality
"Too simple for process"Simple bugs still have root causes
"No time"Systematic beats thrashing
"I'll test after"Repro first or fixes do not stick

Output (/debug)

Root cause (1 line) + fix + proof command, ≤30 lines.

Quick reference

PhaseSuccess
1 Root causeKnow WHAT and WHY
2 PatternDifferences identified
3 HypothesisConfirmed or replaced
4 ImplementationBug resolved, proof run

If truly environmental/external after full investigation: document findings, add handling/monitoring — do not skip phases to get there.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.