dirien/yet-another-agent-harness / .claude/skills/lint-fix
lint-fix
VerifiedDetect project linting and validation tools, build an execution pipeline, run all tools to zero errors, and fix issues using an atomic fix protocol. Auto-detects Makefile targets, package.json scripts, Go tools, Python tools, and other common linters. Use when fixing linting errors, running validation pipelines, or ensuring code quality before committing.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.2 KB |
| references/fix-protocol.md | markdown | 2.2 KB |
| references/tool-detection.md | markdown | 3.0 KB |
references/fix-protocol.md
View on GitHub<!-- Copyright 2025-2026 Richard Shade. Licensed under Apache-2.0. -->
<!-- SPDX-License-Identifier: Apache-2.0 -->
# Atomic fix protocol
Fix linting and validation issues one at a time to prevent cascade
failures. Each fix is immediately verified before moving on.
## Core rule
**Fix ONE issue, then re-verify.** Do not batch fixes. A fix that
resolves one issue may introduce new ones — catching this immediately
is cheaper than debugging a chain of cascading changes.
## Protocol
For each issue reported by a failing command:
1. **Mark the issue** — note the file, line, and rule/error
2. **Fix exactly one issue** — make the minimal change needed
3. **Re-run the failing command** — not the full pipeline, just the
command that reported this issue
4. **Verify two things**:
- The specific issue is resolved
- No NEW issues were introduced by the fix
5. **If the fix created new issues**: revert the fix and try a
different approach
6. **If the fix is clean**: move to the next issue
7. **After all issues for this command are resolved**: move to the
next command in the pipeline
## When a fix creates more issues
```bash
# See what changed
git diff
# Revert a specific file
git checkout -- path/to/file
# If multiple files need reverting
git stash
# Try a different approach, then:
git stash pop
```
Try alternative approaches in order:
1. Different fix for the same issue
2. Fix the new issues too (if they are genuine improvements)
3. Suppress the rule for this line with a justification comment
(last resort)
## When to stop fixing
- **Zero errors**: all commands in the pipeline pass — success
- **Circular fixes**: fix A introduces B, fix B reintroduces A —
ask the user which to prioritize
- **Non-fixable issues**: the issue requires an architectural change
or upstream fix — document it and skip with justification
- **False positives**: the linter is wrong — suppress with a
justification comment
## Re-verification cadence
- After each individual fix: re-run the failing command only
- After all issues in one command are fixed: re-run that command
once more (full pass)
- After all commands pass individually: run the full pipeline
end-to-end as final verification
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |