agentleFS
DailybotHQDailybotHQ/deepworkplan-website/.agents/skills/fix-lint/SKILL.md

fix-lint

Skill15 starsChanged 5 months agoMITView on GitHub

Fix Biome linting/formatting errors in 1-3 files using auto-fix and minimal manual edits. Use proactively for lint issues.

3 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

8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Does NOT fix TypeScript type errors (use type-fix or Tier 2)

    line 24
  2. Distinctive:

    Does NOT refactor logic or add features

    line 25
  3. Distinctive:

    Does NOT modify more than 3 files

    line 26
  4. Distinctive:

    Does NOT change behavior

    line 27
  5. Distinctive:

    Before running this skill, ensure:

    line 47
  6. Distinctive:

    Read remaining Biome messages

    line 64
  7. Distinctive:

    Do not change logic

    line 66
  8. Distinctive:

    Stop and escalate: if:

    line 116

“Common” is measured: kept by at least 6 in 10 of the 3 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

Skill: Fix Lint

Objective

Fix Biome linting and formatting errors in specified files: run pnpm run biome:fix (or equivalent), then resolve any remaining issues with minimal manual edits. Adapted for this repo: Astro, TypeScript, Biome; no logic changes; follow AGENTS.md conventions.

Non-Goals

  • Does NOT fix TypeScript type errors (use type-fix or Tier 2)
  • Does NOT refactor logic or add features
  • Does NOT modify more than 3 files
  • Does NOT change behavior

Tier Classification

Tier: 1 - Light/Cheap

Reasoning: Mechanical fixes (formatting, rule compliance); small scope (1–3 files, <100 LOC); low risk.

Inputs

Required Parameters

  • $FILES: File(s) to fix (paths or "current file"); optional — default to files reported by Biome

Optional Parameters

  • $RULES: Specific rules to focus on (default: all reported)

Prerequisites

Before running this skill, ensure:

  • No uncommitted changes or working on a dedicated branch
  • Biome config is present (biome.json)

Steps

Step 1: Run Auto-Fix

pnpm run biome:fix
# or for specific files:
pnpm exec biome check --write "path/to/files"

Step 2: Address Remaining Issues

  • Read remaining Biome messages
  • Apply minimal edits (e.g., add missing types, fix import order per AGENTS.md)
  • Do not change logic

Step 3: Validate

pnpm run biome:check
pnpm run astro:check

Output Format

Success Output

## ✅ Lint Fix Complete

### Files
- `{file1}`: {what was fixed}
- `{file2}`: {what was fixed}

### Validation
- pnpm run biome:check: ✅
- pnpm run astro:check: ✅

### Commit Message
style: fix Biome issues in {files}

Escalation

## ❌ Fix Lint Not Enough

### Reason
{Remaining issues require type changes / refactor / many files}

### Recommendation
Escalate to Tier 2 or use quick-fix for logical issues.

Guardrails

Scope Limits

  • Maximum files: 3
  • Maximum LOC changed: 100
  • Allowed: Style, import order, simple rule compliance

Stop Conditions

Stop and escalate if:

  • Fixes require logic changes or new types across many files
  • More than 3 files need changes
  • Auto-fix causes build failures (revert and escalate)

Definition of Done

  • pnpm run biome:check passes for modified files
  • pnpm run astro:check passes
  • No behavior change

Related

  • quick-fix - Small bug fixes
  • doc-edit - Docs only

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.