brainstorming
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
compound-learnings
Extract patterns from git history and session files, recommend artifacts (skill/rule/hook/agent) based on frequency thresholds
devils-advocate
Forces adversarial reasoning before committing to decisions. Triggers on architectural choices, approach selection, and planning phases to prevent premature commitment bias.
document-refinement
Use when reviewing brainstorms, plans, or PRDs for clarity and readiness before next workflow phase. Assesses documents for vagueness, gaps, and YAGNI violations.
multi-agent-architecture
Patterns for designing multi-agent systems with Claude Code - job description method, shared folder communication, handbook consolidation, context management. Use when building complex agent orchestrations.
reasoning-verifier
Verify LLM reasoning using Reverse Chain-of-Thought (RCoT) to detect overlooked conditions.
skill-archetypes
Four common skill archetypes with structure templates - CLI reference, methodology, safety/security, and orchestration. Use when creating new skills to select appropriate structure.
skill-design-philosophy
Core philosophy for designing Claude Code skills - when to use skills vs agents, the knowledge test, and what makes skills valuable. Use when deciding component type or evaluating skill quality.
skill-grader
Evaluate skill test run outputs against expectations and extract implicit claims.
skill-structure
Skill file structure, naming conventions, directory layout, frontmatter requirements, and invocation control. Use when creating skill files or slash commands to ensure correct format and validation.
add-config-field
Add new field to .agents.yml config schema (updates init.md templates, version, migration)
fluff-detector
Detect human-oriented content in LLM artifacts. Flags attribution, personas, redundant explanations, marketing language, and decorative elements that waste tokens without improving LLM behavior.
skill-auditor
Audit installed skills across project, global, and plugin levels. Lists skills with line counts, identifies improvement opportunities (conciseness, clarity, overlap, token waste). Use when reviewing skill quality, finding bloated skills, or optimizing token budgets.
learn
Extract cross-session patterns from git history, PRs, and handoffs, then recommend artifacts (skill/rule/hook/agent) based on frequency thresholds. Use when consolidating recurring patterns into durable artifacts. For single-session reflection, use `reflect` instead.
reflect
Reflect on the current session and suggest AGENTS.md improvements based on user corrections, repeated feedback, and patterns observed during interaction. Use when ending a session to encode lessons learned. Don't use for cross-session learning from git history - use `learn` instead.
skill-eval
Test and iterate on a skill using parallel eval runs. Spawns with-skill and baseline runs, grades results, and helps improve the skill based on feedback. Use when testing skill quality or iterating on skill improvements.
release
Release a marketplace plugin - bump version, verify checklist, commit, and push in one invocation. Use when shipping a new version of any plugin in plugins/.
ai-work-governance
>
auto-decision-framework
Framework for automated decision-making during multi-step planning workflows. Classifies planning decisions as Mechanical (auto-decide silently), Taste (auto-decide but surface at gate), or User Challenge (never auto-decide). Reduces question fatigue by batching only decisions that need human judgment. Use when running blueprint, PRD, refactor-plan, or any workflow that asks 5+ intermediate planning questions.
blueprint
Transform feature descriptions into well-structured project plans
build-task
Autonomous task implementation - research, plan, build, review, fix, ship
code-review
Generic code review that auto-detects tech stack and delegates to appropriate framework-specific orchestrator
debug
Debug errors, test failures, or unexpected behavior. Auto-detects project type.
favicon
Generate a complete favicon set (ICO, PNG variants, apple-touch-icon, web manifest) from a source image and integrate into the project's HTML layout. Use when user asks to generate favicons, set up PWA icons, or add an apple-touch-icon.
frontend-performance
Use when modifying layouts, adding assets, or optimizing page speed. Frontend performance patterns for Core Web Vitals (LCP, CLS, INP). Covers font loading, resource preloading, asset scoping, and render-blocking elimination. Not for backend performance — use performance-reviewer instead.
init
Initialize AGENTS.md with hierarchical structure and .agents.yml config
plan-gate
>
prd
Create a Product Requirements Document (PRD) for a new product or feature
quality-gate
Run quality gate checks on code changes with tech stack-aware reviewers
question
Answer questions about the project structure, documentation, or external topics without coding
refactor-agents
Refactor existing AGENTS.md to follow progressive disclosure principles
run-blueprint
Execute all tasks in a blueprint using build-task workflow
ship-it
Complete checkout workflow - runs linting, creates commit, and opens PR
data-integrity-reviewer
Review data integrity for Rails changes. Use when the user asks for migration safety review, constraint validation, transaction boundary audit, or PII/privacy compliance review.
database-admin
PostgreSQL and SQLite database administration for Rails apps. Use when the user asks about backups, monitoring, connection pooling, vacuum/analyze, emergency procedures, restore testing, or production database health checks.
database-optimizer
Optimize PostgreSQL/SQLite query performance for Rails. Use when the user asks about EXPLAIN ANALYZE, slow queries, missing indexes (composite/partial/expression/covering/GIN/GiST/BRIN), N+1 detection, eager loading, or ActiveRecord batch processing.
gemfile-organize
Reorganize a Rails Gemfile with categorized sections, comment headers, and alphabetized gems within each section. Use when the user asks to organize, sort, group, clean up, or restructure a Gemfile.
gemfile-upgrade
Safely upgrade a Ruby gem with changelog review, breaking changes analysis, bundle update, test run, and commit. Use when the user asks to upgrade, bump, or update a gem, or to review outdated gems.
intershop-icm-best-practices
Intershop Commerce Management (ICM) backend development best practices. This skill should be used when writing, reviewing, or refactoring ICM Java code to ensure optimal patterns for customization, performance, B2B features, security, testing, and maintainability. Triggers on tasks involving ICM cartridge development, REST API creation, business objects, pipelines, database operations, jobs, events, or search.
shopware6-best-practices
Comprehensive Shopware 6.6+ development best practices for agency developers. Covers backend PHP, storefront Twig/JS, administration Vue.js, app system, integrations, CLI, multi-channel, and DevOps. Triggers on tasks involving plugin development, storefront customization, admin modules, app creation, payment/shipping integrations, or deployment.
storyblok-best-practices
Comprehensive Storyblok CMS development best practices for agency developers. Covers content modeling, SDK integration (React, Vue, Nuxt, Next.js), Visual Editor configuration, field plugins, API usage, internationalization, webhooks, and deployment patterns. Triggers on tasks involving Storyblok components, Visual Editor setup, content fetching, field plugin development, or headless CMS integration.
woocommerce-markdown
Guidelines for creating and modifying markdown files in WooCommerce. Use when writing documentation, README files, or any markdown content.
woocommerce-copy-guidelines
Guidelines for UI text and copy in WooCommerce. Use when writing user-facing text, labels, buttons, or messages.
woocommerce-performance
Identify performance issues in WooCommerce PHP code. Use when writing or reviewing code that loads collections of post-based objects (products, orders), renders product lists with images, reads multiple options in a loop or method, or writes SQL queries involving joins, aggregates, meta lookups, or range queries.
woocommerce-backend-dev
Add or modify WooCommerce backend PHP code following project conventions. Use when creating new classes, methods, hooks, or modifying existing backend code. **MUST be invoked before writing any PHP unit tests.**
woocommerce-code-review
Review WooCommerce code changes for coding standards compliance. Use when reviewing code locally, performing automated PR reviews, or checking code quality.
woocommerce-dev-cycle
Run tests, linting, and quality checks for WooCommerce development. Use when running tests, fixing code style, or following the development workflow.
woocommerce-email-editor
Setup and develop the WooCommerce block email editor. Use when working on email templates, transactional emails, or the email editor feature.
woocommerce-git-draft-pr
Create a high-quality draft PR for the current branch. Use when the user says "create a PR", "draft PR", "open a PR", "make a PR", "push and create PR", or "submit PR".
woocommerce-git-commit
Commit uncommitted changes with well-crafted messages following WooCommerce repo conventions. Use when the user says "commit", "commit changes", "commit this", "git commit", or "save my work".
Page 716 of 1652 · 82575 results