AztecProtocolAztecProtocol/aztec-packages/.claude/skills/fix/SKILL.md

fix

Skill458 starsChanged 2 months agoApache-2.0View on GitHub

Analyze Linear issues, validate them against the codebase, then implement fixes and create draft PRs.

Commits and pushes

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

0
Common
Most of the 69 edited versions we read keep these.
2
Distinctive
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

Distinctive:
Read the relevant code and assess whether the described bug or problem actually exists.
line 18
Distinctive:
Ask the user which issues to proceed with.
line 25
Very specific:
Build: Run yarn build from yarn-project to verify the fix compiles.
line 40

“Common” is measured: kept by at least 6 in 10 of the 69 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

Fix Issues

Given a list of Linear issue numbers, analyze each one against the codebase, then implement fixes and create draft PRs.

Phase 1: Triage (main context)

For each issue number provided:

Fetch the full issue description using mcp__linear-server__get_issue.
Investigate the codebase to determine if the issue is valid:
- Find the files/functions mentioned in the issue description.
- Read the relevant code and assess whether the described bug or problem actually exists.
Produce a summary table for the user:

Issue	Title	Verdict	Reasoning
A-XXX	...	Valid / Invalid / Unclear	One-line explanation

Ask the user which issues to proceed with. Default is all valid issues.
For each confirmed issue, set its Linear status to "In Progress" using mcp__linear-server__save_issue.

Phase 2: Implementation

Work through each confirmed issue sequentially in the main checkout:

Stash & branch: Stash any uncommitted changes, then create a branch from next using the issue's gitBranchName from Linear (or the component's merge train, see CLAUDE.md). For a fix scoped to the v5 release line, branch from v5-next instead.
```
git stash
git checkout -B <gitBranchName> origin/next
```
Implement the fix: Edit the relevant files.
Build: Run yarn build from yarn-project to verify the fix compiles.
Commit: Stage only the changed files and commit with a descriptive message.
- Message format: fix: <short description> (A-XXX)
- Include Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Push & PR: Push the branch and create a draft PR. Use --base v5-next for v5-scoped fixes.
```
git push -u origin <gitBranchName>
gh pr create --draft --base next --title "fix: ..." --body "..."
```
- The PR body should reference the Linear issue (e.g. Fixes A-XXX).
Return to original branch: Switch back and restore stashed changes before moving to the next issue.
```
git checkout <original-branch>
git stash pop
```

Repeat for each issue.

After all issues are done

Report a summary table with the PR URL for each issue, or what went wrong if any failed.

Issue	Title	PR
A-XXX	...	URL or error

Download now (ZIP)

Other versions75 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 75
react/react★ 252ksame name
facebook/react★ 252ksame name
motiondivision/motion★ 35ksame name
parcadei/Continuous-Claude★ 3.9ksame name
parcadei/Continuous-Claude-v2★ 3.9ksame name
parcadei/Continuous-Claude-v3★ 3.9ksame name
crbnos/carbon★ 2.8ksame name
Akylas/OSS-DocumentScanner★ 2.6ksame name
kdlbs/kandev★ 1ksame name
GoogleCloudPlatform/magic-modules★ 975same name
65 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.
Used alongsideProjects with it also use feature, frontend-code-review and 10 more.
Other files people use alongside this one.
- EffortlessMetricsSkill
  feature
  Also in 10 projects that use this
- chendongqiSkill
  frontend-code-review
  Trigger when the user requests a review of frontend files (e.g., `.tsx`, `.ts`, `.js`). Support both pending-change reviews and focused file reviews while applying the checklist rules.
  Also in 4 projects that use this
- GoogleSkill
  pr-creator
  Also in 4 projects that use this
- PJuniszewskiSkill
  cook
  Feature development with guardrails. Plan → Review → Code → Ship.
  Also in 3 projects that use this
- vbrevikSkill
  work
  Use when the user says 'plan', 'todo', 'copy plan', 'append plan', 'resume plan', 'priorities', or 'what's next'.
  Also in 4 projects that use this
- MetaSkill
  roadmap
  Build, continue, inspect, or visualize a source-grounded mathematical roadmap and theorem DAG in an existing Autoform Markdown blueprint. Use for source research, repository-wide inventories of existing and planned mathematics, scope, coverage, milestones, and roadmap articles; do not create repository infrastructure or prove Lean declarations.
  Also in 4 projects that use this
In this repository22 other files it gives its agents.
- avm-transpiler/CLAUDE.mdCLAUDE.md
- barretenberg/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- docs/CLAUDE.mdCLAUDE.md
- docs/llms.txtllms.txt
- acir-formal-proofsSkill
- adding-benchmarksSkill
- bench-regressionSkill
- capture-app-flowSkill
- chonk-inputsSkill
- ci-logsSkill
- create-issueSkill
- cycleSkill
- genesis-constantsSkill
- merge-train-infraSkill
- merge-trainsSkill
- noir-sync-updateSkill
- prep-cycleSkill
- release-docsSkill
- release-network-docsSkill
- update-doc-referencesSkill
- updating-changelogSkill

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

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

Fix Issues

Phase 1: Triage (main context)

Phase 2: Implementation

After all issues are done

Word for word · 0

Edited · 0

Wrote their own version · 75

feature

frontend-code-review

pr-creator

cook

work

roadmap

Does it work?

No reviews yet

Your trail

Now do this for your own.