agentleFS
Sign inStart free
wedabrowedabro/bro-skills/.agents/skills/speckit.debug/SKILL.md

speckit.debug

Skill3 starsChanged 45 days agoMITView on GitHub

Systematic Debugger - Reproduce, isolate, prove root causes, and produce a scoped fix plan.

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the issue report, logs, source, configuration, recent changes, and constitution.

    line 10
  2. Very specific:

    Write .agents/debug/[issue-slug].md with timeline, reproduction, hypotheses, evidence, root cause, impact, and fix plan.

    line 11
  3. Distinctive:

    Read-only during diagnosis.

    line 24

≈ “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

Mission

Find the smallest proven root cause without changing production code during investigation.

Inputs and Outputs

  • Read the issue report, logs, source, configuration, recent changes, and constitution.
  • Write .agents/debug/[issue-slug].md with timeline, reproduction, hypotheses, evidence, root cause, impact, and fix plan.

Protocol

  1. Record expected versus actual behavior, environment, first-known-good/bad revision, exact reproduction, frequency, and severity.
  2. Reproduce with the smallest deterministic command or test; capture bounded logs and inputs without secrets.
  3. Trace callers and data/control flow. Form ranked hypotheses, then run one falsifiable check per hypothesis.
  4. Identify the exact failing condition and explain why it produces the symptom. Separate trigger, root cause, contributing factors, and non-causes.
  5. Define a minimal fix, regression test, blast radius, rollback, and follow-up debt. Hand implementation to speckit.implement.

Completion Gate

Root cause is tied to file/line or configuration evidence, reproduction is recorded, and the fix plan has verification and rollback criteria.

Guard Rails

Read-only during diagnosis. Do not guess, patch symptoms across callers, expose secrets, or close an issue without reproducible evidence.

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