agentleFS
danielvm-gitdanielvm-git/bigpowers/skills/quick-fix/SKILL.md

quick-fix

Skill288 starsChanged 6 days agoMITView on GitHub

Streamlined fast-path for trivial data-only fixes — no TDD, no branching ceremony. Collapses 6 skills into 2 for changes that are purely data with no logic risk. Aborts with fallback to investigate-bug if guardrails trigger.

14 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 4

    Distinctive

    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. Distinctive:

    When a bug fix is purely data — an add-missing-key, a typo correction, a config value update — the standard 6-skill chain (investigate-bug …

    line 16
  2. Distinctive:

    Before invoking quick-fix, evaluate every item in this checklist:

    line 24
  3. Very specific:

    If ANY guardrail triggers, abort immediately and suggest investigate-bug instead:

    line 36
  4. Distinctive:

    Only 2 skills needed for eligible fixes:

    line 50
  5. Very specific:

    Run the entry criteria checklist above.

    line 72
  6. Distinctive:

    Run the single-assertion verify command.

    line 80

“Common” is measured: kept by at least 6 in 10 of the 7 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

Quick Fix

HARD GATE — ALL entry criteria must pass before invoking quick-fix. If any guardrail triggers during execution, abort immediately and fall back to investigate-bug. Do NOT use quick-fix for logic changes, multi-file edits, or diffs > 5 lines.

Fast-track for trivial data-only fixes that do not require the full bug-fix chain.

When a bug fix is purely data — an add-missing-key, a typo correction, a config value update — the standard 6-skill chain (investigate-bug → diagnose-root → develop-tdd → kickoff-branch → verify-work → release-branch) is wasteful overhead. Quick-fix collapses it to 2 skills: quick-fix then release-branch.

Discovered gate failures (e51s04)

A Preflight, golden suite, or baseline red failure discovered during unrelated work is valid quick-fix entry when the root cause is a data-only gap (missing key, typo, stale config) — no user-reported bug required. If guardrails abort (logic change, >1 file, >5 lines), fall back to fix-bug instead of narrating and continuing.

Entry Criteria (ALL must be true)

Before invoking quick-fix, evaluate every item in this checklist:

  1. Purely data change — adding a missing key, fixing a typo, updating a config value, correcting a constant
  2. No logic change — no function signature, condition, loop, or control flow is modified
  3. No refactor risk — the change does not reorganize or rename existing structures
  4. No API surface change — no exported symbol, interface, or contract changes
  5. Verifiable with a single assertion — one test, one curl, one grep can prove it works
  6. Affects ≤ 1 file
  7. Affects ≤ 5 lines changed

Guardrails (HARD ABORT — all must pass)

If ANY guardrail triggers, abort immediately and suggest investigate-bug instead:

GuardrailCheck
>1 fileThe fix touches more than one file
>5 linesThe diff exceeds 5 lines
Logic changeAny function signature, condition, or loop is modified
Complex verifyThe verify command is more than one pipeline
Test breakageRunning npm test or equivalent breaks any existing test

Fallback: If any guardrail triggers, tell the user: "This fix exceeds quick-fix guardrails. Use investigate-bug for the full TDD bug-fix chain instead."

Fast-Path Workflow

Only 2 skills needed for eligible fixes:

quick-fix  →  apply change, run one-line verify, commit with fix:
release-branch  →  merge and ship (existing skill)

Skipped skills (with justification):

Skipped skillWhy skipped
investigate-bugRoot cause is obvious (data gap, not logic error)
diagnose-rootNo isolation needed — the data point is the root cause
develop-tddNo logic to test — single assertion proves correctness
kickoff-branchChange is so small it does not warrant a separate worktree

Justification is included in the fix: commit body so the audit trail is preserved.

Process

1. Evaluate entry criteria

Run the entry criteria checklist above. If any criterion fails → abort, suggest investigate-bug.

2. Apply the fix

Make the data change — add the missing key, fix the typo, update the value. Keep it to ≤5 lines in 1 file.

3. Verify

Run the single-assertion verify command. Example:

grep -q "Bosnia" src/flags.js && echo "FIX VERIFIED" || echo "FIX FAILED"

4. Commit

git add <file>
git commit -m "fix(<scope>): <description>"
git commit --amend -m "fix(<scope>): <description>

Skipped skills (justified for data-only change):
- investigate-bug: root cause is a data gap, not a logic error
- diagnose-root: the missing data point is the root cause
- develop-tdd: single assertion proves correctness
- kickoff-branch: change is too small for a separate worktree"

5. Release

Invoke release-branch to merge and ship.

Example

Bosnia flag missing from FLAGS dictionary

Given a bug where FLAGS dictionary is missing entry "Bosnia"
And no logic depends on the missing entry (purely a data gap)
When the agent invokes quick-fix
Then the missing entry is added to the dictionary
And a one-line verify confirms the key exists: grep -q "Bosnia" src/flags.js
And a fix: commit is created with the skipped-skills rationale in the body
And the change is ready for release-branch

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.