lint-fix
Skill19 starsChanged 8 months agoMITView on GitHub
Detect 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.
17 other projects use a version of this.
Adopted by
Most recently taken up by
- allanninal/claude-code-skillstheir own version, first seen Oct 17, 2026
- chrisselig/claude-code-toolkittheir own version, first seen Oct 9, 2026
- llp-dev/claude-skillstheir own version, first seen Sep 9, 2026
- llp42/claude-skillstheir own version, first seen Sep 9, 2026
- soumatheusgomes/agentvilletheir own version, first seen Aug 13, 2026
- emaraschio/cursor-commandstheir own version, first seen Aug 7, 2026
Used with
Projects with it also use docstring, changelog and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
NVIDIASkilldocstring
Write or review docstrings for public modules, classes, and functions in sdm/. Use when adding or reviewing docstrings to follow repo best practices (Args sections, paper citations, tensor shape notation).
Also in 3 projects that use this
HashiCorpSkillchangelog
Add a `.changelog/<PR_NUMBER>.txt` entry for a GitHub Pull Request, commit, and push.
Also in 5 projects that use this
GoogleSkilltdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
Also in 3 projects that use this
GoogleSkillcode-review
Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.
Also in 3 projects that use this
Other versions17 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 17
- getsentry/sentry★ 46ksame name
- jhd3197/CachiBot★ 19same name
- minh2004pd/chatbotfullpipeline★ 18same name
- emaraschio/cursor-commands★ 9same name
- soumatheusgomes/agentville★ 9same name
- peopleforrester/claude-dotfiles★ 3same name
- fotoflo/claude-skills★ 2same name
- lodetomasi/claude-code-training-lab★ 2same name
- Pradnyeshp/Claude-Skills★ 2same name
- yu-iskw/meta-agent-skills★ 2same name
7 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository53 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/skills/agent-rules/AGENTS.mdAGENTS.md
- .github/workflows/AGENTS.mdAGENTS.md
- pkg/AGENTS.mdAGENTS.md
- agent-ready-goSkill
- agent-rulesSkill
- architecture-designerSkill
- cli-developerSkill
- cloudformation-to-pulumiSkill
- code-reviewerSkill
- commitlintSkill
- commitSkill
- csharp-developerSkill
- decideSkill
- dep-upgradeSkill
- design-principlesSkill
- devops-engineerSkill
- flux-cliSkill
- flux-operator-cliSkill
- golang-proSkill
- go-nolint-auditSkill
- javascript-proSkill
- kubernetes-specialistSkill
- markdownlintSkill
- prSkill
- pull-request-msg-with-ghSkill
- pulumi-arm-to-pulumiSkill
- pulumi-automation-apiSkill
- pulumi-best-practicesSkill
- pulumi-cdk-to-pulumiSkill
- pulumi-cliSkill
- pulumi-componentSkill
- pulumi-escSkill
- pulumi-goSkill
- pulumi-neoSkill
- pulumi-pythonSkill
- pulumi-terraform-to-pulumiSkill
- pulumi-typescriptSkill
- python-proSkill
- reviewSkill
- roadmapSkill
- rust-async-patternsSkill
- rust-best-practicesSkill
- rust-engineerSkill
- scoutSkill
- security-auditSkill
- spring-boot-engineerSkill
- sre-engineerSkill
- sync-websiteSkill
- tailscale-installSkill
- tech-debtSkill
- the-foolSkill
- typescript-proSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. 0 are common, 11 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 16 edited versions we read keep these.
11
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 46
If no tools are detected, report to the user and offer to help set up linting.
- Very specific: line 51
If make gen, make generate, or an equivalent code generation command is detected, run it before any linting.
- Distinctive: line 60
If generation fails, stop and fix the generation issue before proceeding to linting.
- Distinctive: line 89
If the user wants to add, remove, or reorder commands, adjust the pipeline accordingly.
- Distinctive: line 94
Run each command in order.
- Distinctive: line 122
Verify: the issue is resolved AND no new issues appeared
- Distinctive: line 123
If fix created new issues: revert and try a different approach
- Distinctive: line 124
If fix is clean: move to the next issue
- Distinctive: line 126
After all issues for the failing command are resolved, continue the pipeline from the next command.
- Distinctive: line 134
After all commands pass individually, run the full pipeline end-to-end as a single sequence:
- Distinctive: line 141
All commands must pass in sequence.
- Very specific: line 161
Formatting issues: run the formatter with --write or -w flag instead of --check.
- Very specific: line 165
Check for --fix flags.
- Distinctive: line 171
Read the error carefully and fix the root cause.
“Common” is measured: kept by at least 6 in 10 of the 16 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.
Files
<!-- Copyright 2025-2026 Richard Shade. Licensed under Apache-2.0. --><!-- SPDX-License-Identifier: Apache-2.0 -->Lint and Validation Pipeline
Detect all linting, formatting, and validation tools in the project, build an ordered execution pipeline, run everything to zero errors, and fix issues atomically.
Step 1: Detect project tools
Scan the project root for configuration files, Makefile targets, and package manager scripts to identify available tools.
Check in order:
- Makefile — discover targets: lint, test, validate, format, gen, build, check, vet
- package.json — discover scripts: lint, test, format, prettier, eslint, build, typecheck
- go.mod — check for golangci-lint, gofmt, go vet, go test
- pyproject.toml / setup.py — check for ruff, black, flake8, mypy, pytest
- .csproj / .sln — check for dotnet format, build, test
- Cargo.toml — check for cargo clippy, fmt, test
- Standalone configs — .eslintrc*, .prettierrc*, biome.json, .golangci.yml, .markdownlint*
For detailed detection commands per ecosystem, see
references/tool-detection.md.
If no tools are detected, report to the user and offer to help set up linting. Do not proceed with an empty pipeline.
Step 2: Check for code generation
If make gen, make generate, or an equivalent code generation
command is detected, run it before any linting.
Generated code can overwrite manual fixes. Always generate first.
make gen 2>&1If generation fails, stop and fix the generation issue before proceeding to linting.
Step 3: Build ordered pipeline
Arrange detected tools in execution order:
- Generation (make gen, code generators)
- Formatting (prettier, black, gofmt, rustfmt, dotnet format)
- Linting (eslint, golangci-lint, ruff, clippy, markdownlint)
- Type checking (tsc --noEmit, mypy)
- Validation (make validate, schema checks)
- Testing (go test, pytest, jest, cargo test, dotnet test)
- Building (go build, cargo build, dotnet build)
Present the detected pipeline to the user before executing:
Detected validation pipeline:
1. make gen
2. gofmt -s -l .
3. golangci-lint run
4. markdownlint '**/*.md'
5. go test ./...
6. go build ./...
Proceed? (y/n)If the user wants to add, remove, or reorder commands, adjust the pipeline accordingly.
Step 4: Execute pipeline
Run each command in order. Stop at the first failure.
# Run each command, stop on failure
for cmd in "${PIPELINE[@]}"; do
echo "Running: $cmd"
eval "$cmd" 2>&1
if [ $? -ne 0 ]; then
echo "FAILED: $cmd"
# Proceed to atomic fix protocol for this command
break
fi
echo "PASSED: $cmd"
doneCapture the full output of the failing command — file paths, line numbers, rule names, and error messages are needed for fixing.
Step 5: Atomic fix protocol
Fix issues from the failing command one at a time. This prevents cascade failures where fixing one issue introduces others.
For each issue:
- Fix exactly ONE issue (minimal change)
- Re-run the failing command immediately
- Verify: the issue is resolved AND no new issues appeared
- If fix created new issues: revert and try a different approach
- If fix is clean: move to the next issue
After all issues for the failing command are resolved, continue the pipeline from the next command.
For detailed protocol, rollback strategies, and edge cases, see
references/fix-protocol.md.
Step 6: Final verification
After all commands pass individually, run the full pipeline end-to-end as a single sequence:
cmd1 && cmd2 && cmd3 && ... && echo "PASS" || echo "FAIL"All commands must pass in sequence. If any command fails in the final run, return to Step 5 for that command.
Present the final result:
Validation pipeline: ALL PASSED
1. make gen PASS
2. gofmt -s -l . PASS
3. golangci-lint run PASS
4. markdownlint PASS
5. go test ./... PASS
6. go build ./... PASS
Zero errors across all validation tools.Common fix patterns
Formatting issues: run the formatter with --write or -w flag
instead of --check. Most formatters have an auto-fix mode.
Import ordering: most linters have auto-fix for import sorting.
Check for --fix flags.
Trailing whitespace / EOF newlines: fix with editor settings or
sed -i 's/[[:space:]]*$//' file.
Type errors: these usually require code changes, not auto-fix. Read the error carefully and fix the root cause.
Test failures: investigate the failure — is it a real bug introduced by your changes, or a pre-existing flaky test?
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
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.

