agentleFS
Sign inStart free
HarambeeAIHarambeeAI/bayes-ship/skills/systematic-debugging/SKILL.md

systematic-debugging

Skill1 starsChanged 7 months agoMITView on GitHub

4-phase root cause debugging process. Gather evidence, form hypotheses, test hypotheses, confirm root cause. Use for any bug diagnosis within the Bayes Ship pipeline. Includes defense-in-depth and condition-based-waiting techniques.

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

  • 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
  • +5 more from mjunaidca

The file

We split this skill into the rules it gives an agent

12 rules. 0 are common, 11 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 177 edited versions we read keep these.

  • 11

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never guess at fixes. Follow the 4-phase process:

    line 9
  2. Distinctive:

    Read error messages, stack traces, and logs CAREFULLY

    line 12
  3. Distinctive:

    Add targeted logging or breakpoints

    line 22
  4. Distinctive:

    Ask: "If I revert this fix, does the bug come back?" (mentally or actually)

    line 29
  5. Distinctive:

    Ask: "Does this fix handle the general case, or just the specific trigger I found?"

    line 30
  6. Distinctive:

    After fixing the immediate bug, consider:

    line 34
  7. Distinctive:

    Should there be a defensive check upstream that catches this class of error earlier?

    line 35
  8. Distinctive:

    Should there be a test that prevents regression?

    line 36
  9. Distinctive:

    When debugging async or timing-dependent issues:

    line 41
  10. Very specific:

    Never use sleep() as a fix.

    line 42
  11. Distinctive:

    Wait for CONDITIONS, not TIME.

    line 43
  12. Distinctive:

    If a race condition exists, the fix is synchronization, not delays.

    line 44

“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

Process over guessing

Never guess at fixes. Follow the 4-phase process:

Phase 1: Gather evidence

  • Read error messages, stack traces, and logs CAREFULLY
  • Identify the exact line and condition where failure occurs
  • Note what DOES work (narrowing the search space is as valuable as finding the bug)

Phase 2: Form hypotheses

  • List 2-3 possible causes based on evidence
  • Rank by likelihood
  • Each hypothesis must be testable

Phase 3: Test hypotheses

  • Add targeted logging or breakpoints
  • Inspect state at the point of failure
  • Trace execution path
  • Eliminate hypotheses one by one

Phase 4: Confirm root cause

  • The fix must address the ACTUAL cause, not a symptom
  • Ask: "If I revert this fix, does the bug come back?" (mentally or actually)
  • Ask: "Does this fix handle the general case, or just the specific trigger I found?"

Defence-in-depth

After fixing the immediate bug, consider:

  • Should there be a defensive check upstream that catches this class of error earlier?
  • Should there be a test that prevents regression?
  • Is this a symptom of a broader design issue?

Condition-based waiting

When debugging async or timing-dependent issues:

  • Never use sleep() as a fix. It masks the problem.
  • Wait for CONDITIONS, not TIME. Poll for the expected state.
  • If a race condition exists, the fix is synchronization, not delays.

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.

Check your setup, free