agentleFS
Sign inStart free
mattmirelesmattmireles/gemma-tuner-multimodal/.claude/skills/research-debugging/SKILL.md

research-debugging

Skill1.5k starsChanged 4 days agoMITView on GitHub

Investigate external bugs, vendor limits, SDK mismatches, and workarounds, then save a durable debug guide under README/. Use when a failure depends on web research outside the repo. Do not use for purely local bugs, generic implementation work, or broad planning research not tied to a concrete failure.

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Adapted from Gist: Use when debugging requires external confirmation (vendor issues, official documentation, trackers) and the result …

    line 10
  2. Distinctive:

    Read references/index.md first.

    line 24
  3. Distinctive:

    Use Context7 and official docs.

    line 26
  4. Very specific:

    Write or update README/<topic>-debug.md (or append to README/notes/debug-notes.md for short items).

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “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

Research Debugging

Purpose

Adapted from Gist. Use when debugging requires external confirmation (vendor issues, official documentation, trackers) and the result should live under README/ for reuse.

Use When

  • The failure depends on vendor behavior, quotas, or API shape.
  • The research should be saved for the next incident.

Do Not Use When

  • The bug is fully explained by local code and tests.
  • The task is implementation without an external mystery.

Procedure

  1. Read references/index.md first.
  2. Capture: symptom, minimal repro, what was ruled out locally.
  3. Use Context7 and official docs; add targeted web research when needed.
  4. Write or update README/<topic>-debug.md (or append to README/notes/debug-notes.md for short items).
  5. Hand off to code changes or research-planning when the root cause is clear and work should continue outside note-taking.

Handoff Rules

  • research-planning for broad technology surveys without a single failure.
  • debug (repo debug skill) for systematic local investigation first.

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