agentleFS
Sign inStart free
pankaj-mahaurpankaj-mahaur/Agent-Daemon/skills/daemon/bug-flow/SKILL.md

bug-flow

Skill0 starsChanged 6 days agoMITView on GitHub

Use when the user wants a bug fixed properly end to end — \"fix this bug properly\", \"debug and fix and verify\", \"root cause and fix\", \"bug ko poora theek karo\", \"fix it and prove it works\". Chains debug-triage → fix → verify as one workflow: triage first, fix the root cause, prove the fix by observation.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    If a step's skill is not installed, say so and offer ad skill install <name>.

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Bug Flow

Triage → fix → prove. The most common failure this flow prevents: patching a symptom before the root cause is identified, then claiming "fixed" without observing the repro pass.

If a step's skill is not installed, say so and offer ad skill install <name>.

Steps

Step 1 — Triage

  • uses: debug-triage
  • entry: a bug report or unexpected behavior (get the exact symptom + repro first)
  • discipline: strict triage order — services → data → cache → request → code; no code edits in this step
  • exit checkpoint: FLOW bug-flow 1/3 root-cause: <one-line root cause + evidence>

Step 2 — Fix

  • uses: implement-feature
  • entry: a confirmed root cause (not a hypothesis — re-triage if unconfirmed)
  • discipline: fix the root cause, not the symptom; never widen security to make a bug "go away" (constitution rule 7); one commit per root cause
  • exit checkpoint: FLOW bug-flow 2/3 fixed: <files + what changed>

Step 3 — Prove

  • uses: verify
  • entry: the fix is in place
  • discipline: re-run the ORIGINAL repro and observe it pass; run the surrounding test suite; add a regression test when one is missing
  • exit checkpoint: FLOW bug-flow 3/3 proven: <repro result + tests run>

Rules

  • Step 1 produces a root cause, never a fix. If the "root cause" turns out wrong in Step 3, return to Step 1 — don't iterate blind patches.
  • A bug that can't be reproduced gets reported as such — not "fixed".
  • Record one activeContext.md line at completion: - YYYY-MM-DD: bug-flow: <root cause> fixed in <files>

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