AI Agent Workflow Collection

Creates agent skill and instruction surfaces. Use when authoring SKILL.md folders, AGENTS.md/AGENTS.override.md, CLAUDE.md, Copilot or Cursor rules, or when asked to bootstrap, design, scaffold, or migrate reusable agent guidance.

Audits and improves agent skill and instruction surfaces. Use when reviewing SKILL.md, AGENTS.md/AGENTS.override.md, CLAUDE.md, Copilot or Cursor rules, or when asked to lint, score, modernize, deduplicate, secure, or repair agent guidance.

Debug CI failures and validate release readiness. Use when Codex needs to inspect GitHub Actions runs, fix failed checks, validate dependency updates, run release gates, prepare a repository for release, or execute a full release-readiness loop without publishing unless explicitly requested.

Review and improve repositories, files, configurations, and low-confidence review claims. Use when Codex is asked to review a codebase or file, fix brittle or hacky implementation choices, normalize duplicated logic or consistency drift, or triage AI review comments without accepting speculative claims.

Validates and optionally performs dependency updates without weakening quality gates. Use when handling Dependabot/Renovate/npm-check-updates changes, lockfile review, update-tool runs, or code/config/type/lint/build/test fallout.

Build, audit, and maintain ESLint plugin repositories. Use when Codex needs to bootstrap a new ESLint plugin from a template, audit plugin best practices, synchronize rule docs/tests/presets/generated surfaces, or discover and implement high-value net-new ESLint rules.

Maintains GitHub Actions workflows. Use when creating, reviewing, editing, or hardening .github/workflows YAML, workflowcall callers, CI/CD automation, action pinning, permissions, npm publishing, caching, matrices, actionlint, or review comments.

Fix lint, ESLint, and static-analysis diagnostics properly. Use when Codex needs to run lint commands, resolve ESLint errors or warnings, remove unnecessary disable comments, or replace suppressions with root-cause code, type, config, or test fixes.

Maintains Mermaid diagrams and config. Use when creating, editing, reviewing, theming, or debugging Mermaid flowcharts, sequence/ER/Gantt diagrams, dark themes, themeVariables, frontmatter config, renderer issues, or Markdown blocks.

Migrates npm-managed repositories from npm 11 or older to npm 12 with lifecycle-script allowlisting, Node and CI alignment, config and lockfile review, breaking-output fixes, and full validation. Use when explicitly invoked for an npm 12 upgrade, migration audit, or allowScripts rollout.

Builds, audits, and maintains Prettier plugin and shared config repos. Use when scaffolding plugins, fixing parsers/printers/options, auditing doc-builder behavior, testing formatting output, or validating package/editor/CI integration.

Maintains strict Python projects with Ruff, mypy, Pyright, pytest, editor, and package-script gates. Use when creating, auditing, or repairing strict lint, format, typecheck, test, compile, or VS Code tooling practices.

Executes authorized release publishing. Use when the user explicitly asks Codex to commit/push, watch CI and SonarCloud/SonarQube gates, fix failed checks, choose semver, dispatch publish or release workflows, and verify artifacts.

Builds, audits, and maintains remark and remark-lint plugin repos. Use when scaffolding plugins, creating or repairing remark-lint rules, auditing unified/Markdown AST usage, syncing docs/tests/configs, or validating package/CLI behavior.

Maintains SchemaStore PRs. Use when working in SchemaStore/schemastore on JSON schemas, catalog entries, fileMatch patterns, tests, schema-validation.jsonc exceptions, CODEOWNERS-owned schemas, or PR readiness.

Build, audit, and maintain Stylelint plugin repositories. Use when Codex needs to bootstrap a new Stylelint plugin from a template, audit Stylelint plugin best practices, or discover and implement domain-specific Stylelint rules with docs, tests, configs, and package validation.

Add, repair, and improve tests and coverage. Use when Codex needs to generate unit tests, fix failing tests, improve meaningful coverage, test error handling, add Playwright end-to-end tests, or create focused performance benchmarks.

Generates copy-pasteable vscode-icons association objects. Use when mapping workspace filenames, extensions, generated files, dotfolders, test/config/framework folders, or other paths to supported VS Code Icons names.

Continue active work, implement an existing plan, or write a compact handoff. Use when Codex needs to resume from current workspace state, carry an existing plan through implementation and validation, or summarize work so a fresh session can continue without rediscovery.