agentleFS
Sign inStart free
stevemarksavastevemarksava/superteam/skills/systematic-debugging/SKILL.md

systematic-debugging

Skill1 starsChanged 2 months agoMITView on GitHub

Isolate, reproduce, and fix bugs the disciplined way — hypothesis-driven, minimal test case, regression coverage. Adapted from obra/superpowers.

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

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 177 edited versions we read keep these.

  • 4

    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:

    Hypothesise: Write down what you think is wrong in one sentence.

    line 20
  2. Distinctive:

    No fix without a reproducing test — "it works on my machine" is not resolution

    line 32
  3. Distinctive:

    Never fix and refactor in the same commit

    line 33
  4. Distinctive:

    Never skip steps because the bug "looks obvious" — obvious bugs bite twice

    line 34

“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 — Disciplined Bug Hunting

Debugging is not guessing. It is a repeatable protocol: reproduce → isolate → hypothesise → minimal test → fix → cover. Skipping a step is how bugs come back.

When to invoke

  • A test is failing and the cause is not obvious from the stack trace
  • A production incident needs a root-cause diagnosis before a patch is safe
  • A flaky test needs to be pinned down as real vs environmental
  • Vera flags a bug and Eric/Diesel need to fix it without regressing anything else

Steps

  1. Reproduce. Get the bug reliably firing on your machine. If you cannot reproduce, you cannot fix — gather more evidence first. Record exact inputs, environment, and command used.
  2. Isolate variables. Strip the failing case to the smallest reproducer: remove unrelated code, mock external calls, hardcode inputs. Every removal is a controlled experiment.
  3. Hypothesise. Write down what you think is wrong in one sentence. Include which observation supports it. If you have three hypotheses, list all three and rank them.
  4. Minimal test case. Convert the reproducer into a failing test (unit or integration). This becomes the RED step for TDD. Save the test — it lives on as regression coverage.
  5. Fix. Change the minimum code needed to turn the test green. Do not refactor while fixing — one concern per commit.
  6. Regression coverage. Confirm the new test lives in the suite. Add adjacent edge cases the fix touches. Run the full test suite before handing to Vera.

Deliverable format

  • Failing test committed (RED) → passing after fix (GREEN)
  • One-paragraph root-cause note in the PR description
  • Any adjacent tests added, listed by name
  • Environment/config notes if the bug was environmental

Non-negotiables

  • No fix without a reproducing test — "it works on my machine" is not resolution
  • Never fix and refactor in the same commit
  • Never skip steps because the bug "looks obvious" — obvious bugs bite twice
  • Vera signs off before delivery — this skill does not replace her gate

References

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