agentleFS
Sign inStart free
PrisacariuRobertPrisacariuRobert/sidemates/skills/bundled/systematic-debugging/SKILL.md

systematic-debugging

Skill9 starsChanged 37 days agoMITView on GitHub

Diagnose reproducible bugs, test a focused fix and review the exact diff before claiming a problem is solved.

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

5 rules. 0 are common, 4 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read the project's instructions and relevant code.

    line 8
  2. Distinctive:

    Create a minimal reproduction or failing regression test.

    line 9
  3. Distinctive:

    Only implement a fix when the user requested implementation.

    line 11
  4. Distinctive:

    Run the regression that failed, relevant neighboring tests and normal project checks.

    line 12
  5. Distinctive:

    When the workflow requires review/publishing, commit the intended files, rerun meaningful checks against that exact commit and use …

    line 13

“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

Reproduce → explain → fix → verify

  1. Read the project's instructions and relevant code. Use code_projects and code_list/code_search/code_read for shared projects. Check the failing behavior, recent changes and actual error before guessing.
  2. Create a minimal reproduction or failing regression test. Record expected versus observed behavior. If reproduction is blocked, report what was checked and the missing prerequisite.
  3. Trace the value or control flow back to its cause. Rank a few hypotheses and test the smallest discriminating check. Change one causal factor at a time. Stop repeating an unchanged failed approach.
  4. Only implement a fix when the user requested implementation. Use code_branch for an isolated workspace, then code_replace/code_write. Prefer the smallest change that addresses the demonstrated cause, not unrelated refactoring.
  5. Run the regression that failed, relevant neighboring tests and normal project checks. Inspect code_diff for accidental changes and secrets. Advisory security warnings need inspection, not automatic suppression.
  6. When the workflow requires review/publishing, commit the intended files, rerun meaningful checks against that exact commit and use code_request_review with another teammate. Publishing remains approval-gated.
  7. Report the cause, the change, checks actually run and unresolved risks. Do not call an untested workaround a verified fix. If several attempts fail, revisit the causal model instead of stacking more patches.

This is a Sidemates tool adaptation of the Hermes/superpowers method; it does not require their command runner or delegation API.

Provenance

Reviewed Sidemates adaptation of systematic-debugging. Instructions are bundled with Sidemates and do not grant tool or account permissions. See LICENSE for reuse terms.

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