Parallel lint fixing pattern - runs lint checks, groups issues into independent streams, and dispatches AI agents to fix all issues until the codebase is clean.
/plugin marketplace add lerianstudio/ring/plugin install ring-default@ringThis skill inherits all available tools. When active, it can use any tool Claude has access to.
This skill runs lint checks on the codebase, analyzes the results to identify independent fix streams, and dispatches parallel AI agents to fix all issues. The process iterates until the codebase passes all lint checks.
Core principle: Group lint issues by file/component, dispatch one agent per independent stream, iterate until clean.
These constraints are NON-NEGOTIABLE and must be communicated to ALL dispatched agents:
┌─────────────────────────────────────────────────────────────────┐
│ 🚫 DO NOT CREATE AUTOMATED SCRIPTS TO FIX LINT ISSUES │
│ 🚫 DO NOT CREATE DOCUMENTATION OR README FILES │
│ 🚫 DO NOT ADD COMMENTS EXPLAINING THE FIXES │
│ ✅ FIX EACH ISSUE DIRECTLY BY EDITING THE SOURCE CODE │
│ ✅ MAKE MINIMAL CHANGES - ONLY WHAT'S NEEDED FOR LINT │
└─────────────────────────────────────────────────────────────────┘
Priority: make lint → npm run lint → yarn lint → pnpm lint → golangci-lint run → cargo clippy → ruff check . → eslint .
<lint_command> 2>&1 | tee /tmp/lint-output.txt && echo "EXIT_CODE: $?"
Extract: file path, line:column, error code/rule, message, severity (error/warning).
Group lint issues into independent streams that can be fixed in parallel:
Grouping strategies (choose based on issue count):
| Issue Count | Grouping Strategy |
|---|---|
| < 10 issues | Group by file |
| 10-50 issues | Group by directory |
| 50-100 issues | Group by error type/rule |
| > 100 issues | Group by component/module |
A stream is independent if: files don't import/depend on each other, fixes won't conflict, agents can work without knowledge of other streams.
Output format: Total issues, Streams (path, issue types, count, independence status), Recommended agents (one per stream).
Each agent receives: Scope (files/directories), Issues (file:line:col + message), Constraints (from Critical Constraints above), Output (files modified, issues fixed, issues unable to fix with reasons).
CRITICAL: Single message with multiple Task tool calls - one general-purpose agent per stream.
Wait for all dispatched agents to complete before proceeding.
After all agents complete, run <lint_command> 2>&1.
| Result | Action |
|---|---|
| Lint passes | ✅ Done |
| Same issues remain | ⚠️ Investigate why fixes failed |
| New issues appeared | 🔄 Analyze + dispatch new agents |
| Fewer issues remain | 🔄 Create new streams, repeat |
Maximum iterations: 5. If issues persist: report remaining, ask user, investigate (lint conflicts, auto-fix impossible).
| Issue Type | Agent Type |
|---|---|
| TypeScript/JavaScript | general-purpose |
| Go | general-purpose or backend-engineer-golang |
| Security lints | security-reviewer for analysis first |
| Style/formatting | general-purpose |
Success: Initial issues, Streams processed, Agents dispatched, Iterations, Final status (all pass), Changes by stream (files, issues fixed).
Partial: Initial/fixed/remaining issues, Iterations (max reached), Remaining issues with reasons (e.g., requires external types, intentional usage), Recommended actions (manual review, lint exceptions, type definitions).
| Error | Response |
|---|---|
| Lint command not found | Ask user to specify command |
| Agent failure | Options: retry stream, skip, investigate manually |
| Conflicting changes | Report file + lines, ask user to merge manually |
| Skill | When to use |
|---|---|
dispatching-parallel-agents | Pattern basis for this skill |
systematic-debugging | If lint errors indicate deeper issues |
requesting-code-review | After lint passes, before merge |
/lint → Run lint → 16 issues in 3 areas → Analyze streams (API: 5, Services: 8, Utils: 3) → Dispatch 3 parallel agents → All complete → Re-run lint → ✅ All pass.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.