AI Skills Hub

Name: Ai-skills
Author: codebygarv

A community-driven collection of reusable AI skills — for discovering, exploring, and reusing specialized agent capabilities.

npx github:codebygarv/Ai-skills add grill-me

That's it — one command drops a battle-tested skill directly into your AI workflow.

🌐 Universal Multi-Agent Compatibility (Not Just for Claude Code!)

While skills install by default to .claude/skills/, AI Skills Hub is universal and agent-agnostic. Every skill is authored in standard Markdown with YAML frontmatter following the Skill Specification, making them natively compatible with all major AI coding assistants and agent frameworks:

AI Assistant / Agent	Install Target	How to Install
Claude Code	`.claude/skills/`	`npx github:codebygarv/Ai-skills add grill-me`
Google Antigravity	`.agents/skills/`	`npx github:codebygarv/Ai-skills add grill-me --target .agents/skills`
Cursor	`.cursor/rules/`	`npx github:codebygarv/Ai-skills add grill-me --target .cursor/rules`
Windsurf	`.windsurf/rules/`	`npx github:codebygarv/Ai-skills add grill-me --target .windsurf/rules`
GitHub Copilot / Workspace	`.github/skills/` or custom docs	`npx github:codebygarv/Ai-skills add grill-me --target .github/skills`
Roo Code / Cline	Custom rule directories	`npx github:codebygarv/Ai-skills add grill-me --target .roo/rules`
Aider & Custom LLM Toolchains	Any local path	`npx github:codebygarv/Ai-skills add grill-me --target .ai/skills`

See it in action

GrillMe — challenges an idea instead of agreeing with it.

You: "Grill me on this: our new feature flag system stores flags as rows in the primary Postgres database, read on every request."

GrillMe: Every request now takes a read-path dependency on your primary database for something that's almost always the same answer for minutes at a time — you've turned a config lookup into a scaling bottleneck for your most critical path.

Assumption: flag reads are cheap. At 10x traffic, this competes for connections with actual business queries — a flag check can degrade checkout.

No caching layer. A single flag toggle now means every pod issues fresh reads with zero staleness tolerance, when 30 seconds of staleness would've been invisible.

Alternative not addressed: a push-based cache or a dedicated flag service solves this entirely — why wasn't that considered?

Questions to answer before shipping this: What's your target read latency at peak, and does this design hit it with headroom?

Full transcript: skills/reasoning/grill-me/examples/example.md. 99 more skills below.

What is this?

AI Skills Hub is a centralized catalogue of reusable AI skills designed to extend the capabilities of AI coding agents, assistants, and developer workflows.

Instead of every developer re-writing the same instructions, prompts, and agent behaviors from scratch, you can browse this catalogue, find a skill that matches what you need, read what it does, and drop it into your own AI workflow.

Each skill is a self-contained package of instructions that teaches an AI agent how to perform one specific type of task consistently — for example:

GrillMe → aggressively reviews, questions, and challenges an idea, implementation, architecture, or plan.
UI Auditor → analyzes a UI implementation for design-system, responsiveness, accessibility, and consistency issues.
PR Reviewer → reviews a pull request like a senior engineer and flags bugs, architectural problems, and maintainability issues.
SQL Query Optimizer → analyzes execution plans (EXPLAIN), eliminates table scans, and designs targeted composite indexes.

Core Vision

Think of it like a package registry, but for AI agent skills:

AI Skills Hub
      ↓
Search / Explore Skills
      ↓
Find "PR Reviewer"
      ↓
Read Documentation
      ↓
Install / Copy Skill (Claude, Antigravity, Cursor, Windsurf, Copilot, etc.)
      ↓
Use it with your AI Agent

The long-term goal is to make AI skills discoverable, reusable, shareable, version-controlled, community-driven, easy to install, easy to customize, and easy to contribute to.

What is an AI Skill?

An AI Skill is a structured set of instructions that gives an AI agent a specialized capability or behavior. A skill defines:

What the AI should do
When the AI should use the skill
What information it should analyze
What rules it should follow
What output it should produce
What it should avoid
Examples of expected behavior

See docs/SKILL_SPEC.md for the full folder structure and quality standards every skill in this repo follows.

The Catalogue

100 skills across 9 categories.

🧠 Reasoning & Thinking (`skills/reasoning/`)

Skill	Description
Cognitive Bias Detector	Audits design documents, sprint estimates, and technical debates for cognitive biases like anchoring, sunk cost, and optimistic scoping.
Decision Maker	Compares multiple candidate solutions against explicit criteria and trade-offs, and produces a structured recommendation. Use when the user has several real options and needs a defensible pick, not just a pros/cons list.
Deep Think	Breaks a complicated problem into smaller reasoning steps and evaluates multiple possible approaches before recommending one. Use for genuinely hard, multi-faceted problems, not routine tasks.
Devils Advocate	Deliberately takes the opposing position to a stated idea or decision and builds the strongest possible case against it, to identify weaknesses before commitment. Use when the user wants a genuine counter-argument, not agreement.
First Principles Analyzer	Deconstructs problems down to fundamental truths and foundational constraints rather than reasoning by analogy or convention.
Grill Me	Aggressively reviews, questions, and challenges an idea, implementation, architecture, or plan instead of agreeing with it. Use when the user wants their thinking pressure-tested, not validated.
Pre Mortem Facilitator	Runs prospective failure simulations by assuming a project or deployment has failed and working backward to identify vulnerabilities.
Requirements Extractor	Converts vague, informal, or incomplete requirements into clear functional and technical requirements, and flags open questions. Use when a request is too ambiguous to implement directly.
Root Cause Diagnoser	Performs 5-Whys and Ishikawa fishbone causal analysis to discover root causes behind systemic bugs, outages, and regressions.
Tradeoff Matrix Builder	Constructs weighted, multi-attribute decision matrices evaluating technical, architectural, or library choices.

💻 Development (`skills/development/`)

Skill	Description
Api Designer	Helps design REST APIs - routes, request/response structures, validation, status codes, and conventions. Use when designing new endpoints or reviewing an existing API's design for consistency.
Bug Hunter	Searches code specifically for potential bugs, edge cases, race conditions, and incorrect assumptions rather than general style/quality. Use when the goal is finding what's broken, not improving what already works.
Code Reviewer	Reviews source code for bugs, readability, maintainability, performance, and best-practice violations. Use for general-purpose code review of a diff, file, or function, not tied to a specific language concern.
Concurrency Race Detector	Identifies race conditions, mutex contention, unsafe shared state, and deadlocks in concurrent and async code.
Database Architect	Reviews database schemas, relationships, indexes, constraints, and data modeling decisions. Use when designing a new schema or reviewing an existing one for correctness and scalability.
Dependency Auditor	Reviews package dependencies for unnecessary packages, outdated or risky patterns, duplication, and licensing/maintenance risk. Use when a dependency manifest has grown unchecked or before adding a new dependency.
Error Handling Architect	Designs structured error hierarchies, domain error mapping, and resilient fallback/retry mechanisms across applications.
Graphql Schema Designer	Designs ergonomic, performant GraphQL schemas with Relay pagination, input validation, and N+1 prevention.
Memory Leak Detector	Identifies unclosed handles, event listener accumulation, retain cycles, and heap memory leak patterns.
Microservices Boundary Definer	Applies Domain-Driven Design (DDD) bounded contexts and event storming to decompose monoliths into clean services.
Performance Auditor	Looks for performance bottlenecks across frontend rendering, backend logic, database access, and network usage. Use when something is slow or before it needs to scale.
Pr Reviewer	Performs a pull-request-style review across an entire diff, organizing findings by severity and considering scope/intent, not just line-level code quality. Use when reviewing a full PR rather than a single function.
Refactor Expert	Identifies unnecessarily complicated code and proposes cleaner implementations while preserving behavior. Use when code works but is harder to read or change than it should be.
Security Auditor	Analyzes code and implementations for common security weaknesses and unsafe practices - injection, auth flaws, secrets handling, unsafe deserialization, and access control. Use before shipping anything handling user input, auth, or sensitive data.
Sql Query Optimizer	Analyzes SQL queries, execution plans, index usage, and lock contention to optimize database operations.
State Machine Designer	Designs deterministic Finite State Machines (FSMs) and statecharts for complex UI workflows and backend order lifecycles.
Typescript Guardian	Focuses specifically on TypeScript type safety - any usage, unsound generics, interface design, and type narrowing. Use for a deep type-system review, not general code quality.

🎨 UI / UX (`skills/ui-ux/`)

Skill	Description
Accessibility Auditor	Checks an interface against accessibility principles - keyboard navigation, semantic HTML, color contrast, labels, and screen-reader behavior. Use before shipping any user-facing UI, especially public-facing ones.
Color Palette Generator	Generates accessible, high-contrast, semantic design-system color tokens for light and dark modes.
Data Table Ux Designer	Designs dense data grids with sorting, filtering, column customization, sticky headers, and virtualization.',
Design System Guardian	Detects hardcoded colors, spacing, typography, widths, and other raw values that should use design-system tokens instead. Use when a project has an established design system/token set and you want to catch drift from it.
Empty And Error State Designer	Designs helpful, actionable zero-data states, 404/500 screens, and self-service error recovery interfaces.
Micro Interaction Designer	Designs subtle UI motion physics, state transitions, hover states, and haptic timings for polished user experiences.
Onboarding Flow Optimizer	Streamlines product onboarding, wizard steps, time-to-value, and progressive disclosure for new users.
Responsive Checker	Analyzes whether a UI will behave correctly across mobile, tablet, and desktop layouts. Use when reviewing responsive/adaptive layout code or before shipping a UI meant to work across screen sizes.
Ui Auditor	Reviews an interface implementation for visual consistency, spacing, hierarchy, and design-system compliance. Use after implementing or changing UI, before it ships.
Ui Text Formatter	Detects poorly formatted UI text and improves capitalization, spacing, hierarchy, and readability - labels, headings, button text, and messages. Use when reviewing user-facing copy for consistency.

📝 Documentation & Communication (`skills/documentation/`)

Skill	Description
Adr Generator	Formats Architecture Decision Records (ADRs) capturing problem context, considered alternatives, and consequences.
Changelog Generator	Converts commits or development updates into clean, categorized release notes and changelogs. Use when preparing a release and raw commit history needs to become human-readable notes.
Codebase Glossary Builder	Extracts domain terminology, business acronyms, and entity definitions into an ubiquitous language dictionary.
Commit Message Expert	Generates consistent, meaningful Git commit messages based on a diff or description of changes. Use when writing or reviewing a commit message, especially to follow Conventional Commits or a project's existing convention.
Contributor Guide Writer	Creates clear, welcoming CONTRIBUTING.md files, PR templates, and local dev onboarding guides for open source projects.
Documentation Writer	Creates structured technical documentation from code, requirements, or existing notes. Use when a feature, module, or system needs written docs and none exist yet, or existing ones are out of date.
Readme Builder	Creates professional README files for GitHub projects, covering purpose, installation, usage, and contribution info. Use when a repo has no README or an outdated/thin one.
Release Notes Writer	Converts git commits, PR summaries, and changelogs into engaging, user-facing product release notes.
Rfc Proposal Writer	Drafts formal technical Requests for Comments (RFCs) complete with motivation, architecture design, and rollout plan.
Runbook Generator	Generates structured, copy-pasteable operational runbooks and disaster recovery SOPs for on-call engineering teams.
Status Update Writer	Converts raw development notes into professional daily or weekly project status updates. Use when turning scattered notes/bullet points into a shareable update for a team or stakeholder.

🧪 Quality & Testing (`skills/testing/`)

Skill	Description
Chaos Experiment Designer	Designs chaos engineering experiments like network latency injection and node termination to validate resilience.
Contract Testing Designer	Establishes consumer-driven contract tests using Pact or OpenAPI to prevent breaking changes across services.
E2e Scenario Planner	Plans high-value end-to-end critical user journeys with Playwright or Cypress focusing on revenue-critical flows.
Edge Case Hunter	Focuses specifically on unusual inputs, boundary conditions, empty states, and unexpected user behavior that implementations commonly miss. Use to find what a normal test pass would skip over.
Flaky Test Diagnoser	Diagnoses why a test passes sometimes and fails others - timing, shared state, ordering dependence, or external dependencies - and proposes a fix. Use when a test fails intermittently.
Load Test Scenario Builder	Designs realistic load and performance testing scenarios with k6, Locust, or JMeter for traffic simulations.
Mock And Fixture Generator	Generates realistic, edge-case-rich mock fixtures and synthetic API payloads without leaking real PII.
Mutation Testing Advisor	Analyzes test suites to identify surviving mutants, weak assertions, and false confidence in line coverage.
Test Case Designer	Converts requirements into structured manual and automated test cases with clear steps and expected results. Use when you need a test plan/test case document, not code-level unit tests.
Test Coverage Analyzer	Identifies which behaviors are meaningfully untested and risk-ranks the gaps, rather than reporting line-coverage percentage. Use when deciding where to add tests next.
Test Generator	Creates meaningful unit, integration, and component tests based on implementation and requirements. Use when code needs test coverage and you want tests that verify behavior, not just tests that pad a coverage number.

🏗️ Project & Architecture (`skills/architecture/`)

Skill	Description
Adr Writer	Writes an Architecture Decision Record (ADR) documenting a decision, its context, the options considered, and its consequences. Use to record a decision that's already been made so future readers understand why.
Architecture Reviewer	Reviews application architecture for scalability, coupling, separation-of-concerns, and maintainability issues. Use for system-level review, not individual file/function-level code review.
Cache Strategy Planner	Designs multi-tier caching architectures (CDN, Redis, memory), invalidation policies, and stampede mitigations.
Cost Optimization Auditor	Analyzes cloud infrastructure and architectures to identify wasted spend and right-sizing opportunities.
Disaster Recovery Planner	Formulates RTO/RPO targets, cross-region failover, backup verification, and split-brain recovery procedures.
Event Driven Architect	Designs event-driven systems with CloudEvents schemas, message brokers, idempotency keys, and dead-letter queues.
Migration Planner	Plans a safe, incremental migration (framework, database, service, or platform) with rollback points and a dual-running strategy. Use when replacing something that's already in production and can't just be swapped in one step.
Project Planner	Converts an idea into a structured development plan with milestones, tasks, dependencies, and implementation phases. Use when an idea or feature needs to be broken into a plan before work starts.
Rate Limiting Architect	Designs distributed token bucket, leaky bucket, and tiered rate limiting architectures to prevent abuse.
Tech Debt Assessor	Inventories technical debt across a codebase and prioritizes it by cost-of-delay versus effort, producing a ranked paydown list. Use when debt is accumulating but it's unclear what to fix first.
Zero Downtime Migration Planner	Plans blue-green rollouts, canary deployments, and expand-and-contract schema migrations with zero downtime.

🔐 Security & Compliance (`skills/security/`)

Skill	Description
Auth Flow Reviewer	Deep review of authentication, authorization, session, and SSO flows specifically - token lifecycle, session fixation, logout behavior, and OAuth/SSO correctness. Use when reviewing or designing login, session, or SSO code specifically.
Compliance Privacy Reviewer	Reviews how a feature or system handles PII, data retention, and consent against common privacy-framework principles (GDPR-style). Use when a feature collects, stores, or processes personal data - not a substitute for legal advice.
Cors Csrf Auditor	Reviews Cross-Origin Resource Sharing configs, CSRF protections, SameSite cookies, and origin security.
Cryptographic Practices Auditor	Reviews cipher algorithms, key derivation parameters (Argon2, bcrypt), token signing keys, and TLS settings.
Data Anonymizer Specifier	Formulates redaction rules and masking strategies for PII, secrets, and customer data in logs and staging.
Dependency Vulnerability Triage	Triages CVEs and Dependabot/Snyk security alerts to assess real runtime exploitability and reduce alarm fatigue.
Incident Postmortem Writer	Structures raw incident notes into a blameless postmortem - timeline, root cause, impact, and action items. Use after an incident/outage once the immediate fire is out and it needs to be documented.
Rbac Abac Designer	Designs Role-Based and Attribute-Based Access Control models, permission bitmasks, and multi-tenant boundary checks.
Secrets Scanner	Narrowly scans code and config for hardcoded secrets, credentials, API keys, and tokens. Use before a commit/PR, or when auditing a codebase for accidentally-committed secrets.
Threat Modeler	Performs proactive, pre-implementation threat modeling (STRIDE-style) for a feature or system before it's built. Use when designing something new that touches user data, auth, money, or external input, before writing code.

⚡ Productivity & Workflow (`skills/productivity/`)

Skill	Description
Ci Cd Pipeline Optimizer	Audits CI/CD workflows (GitHub Actions, GitLab CI) to implement caching, parallelization, and cut build durations.
Context Window Optimizer	Curates and condenses codebase context, file contents, and prompts to optimize LLM token usage and response quality.
Interview Question Generator	Generates technical interview questions plus an evaluation rubric for a given role or skill area. Use when preparing to interview a candidate and need structured, fair questions rather than ad hoc ones.
Meeting Notes Distiller	Turns raw meeting notes or transcripts into structured decisions and action items. Use after a meeting when raw notes/transcript exist and need to become a shareable summary.
Monorepo Workflow Architect	Designs monorepo workspaces, dependency graphs, package sharing, and incremental build pipelines with Turborepo or Nx.
On Call Handover Writer	Formats structured end-of-shift summaries covering active incidents, degraded services, and pending follow-ups.
Onboarding Guide Generator	Generates a new-engineer onboarding guide from a codebase's actual structure - setup steps, architecture overview, key files, and where to start. Use when a project has no onboarding doc or an outdated one.
Prompt Enhancer	Refines vague, unstructured user prompts into clear, constraint-driven prompts with explicit formats and rules.
Retro Facilitator	Structures raw sprint retro notes into themes and concrete actions. Use after a retro when raw sticky-note-style input (what went well/poorly/to try) needs to become a clean summary with follow-through.
Task Breakdown Assistant	Breaks a single ticket or task into concrete, actionable subtasks. Use when one task feels too large or vague to just start on, at the individual-task level - not whole-project planning.

🛠️ Utilities & DevOps (`skills/utilities/`)

Skill	Description
Cron Expression Translator	Translates cron expressions to plain English and back. Use when a cron schedule in code/config is unclear, or when you know when something should run but not the cron syntax for it.
Dockerfile Optimizer	Audits Dockerfiles for multi-stage build efficiency, layer caching, non-root security, and minimal base image footprint.
Environment Config Auditor	Reviews .env/config files for consistency and missing required variables across environments. Use when comparing dev/staging/prod config, or debugging an "it works locally but not in prod" issue.
Helm K8s Manifest Reviewer	Checks Kubernetes manifests and Helm charts for resource limits, readiness probes, and security contexts.
Log Message Improver	Improves logging statements for observability - structured logging, appropriate log levels, and useful context. Use when logs are too sparse, too noisy, or missing the context needed to debug an incident from them alone.
Naming Consultant	Suggests consistent, well-reasoned names for variables, functions, files, or classes given context. Use when a name feels off, ambiguous, or inconsistent with surrounding conventions.
Openapi Spec Generator	Generates valid, expressive OpenAPI 3.1 specifications from code handlers, route declarations, and data schemas.
Regex Explainer	Explains what a regular expression does in plain English, or builds one from a plain-English description. Use when a regex is unreadable at a glance, or when you know what you want to match but not the regex syntax for it.
Semver Bump Advisor	Analyzes git commits and breaking changes to determine exact semantic version increments (PATCH vs MINOR vs MAJOR).
Terraform Iac Auditor	Inspects Terraform and OpenTofu Infrastructure-as-Code modules for drift resilience, security, and state locking.

Standard Skill Structure

Every skill follows the same layout:

skills/<category>/<skill-name>/
├── SKILL.md          # Instructions the AI agent actually reads (YAML frontmatter + body)
├── README.md          # Human-facing docs: what it does, when to use it, examples
└── examples/
    └── example.md     # A worked example of the skill in action

Full spec: docs/SKILL_SPEC.md. Contribution steps: CONTRIBUTING.md.

Using a Skill

Option 1 — CLI (recommended): install directly from this repo with npx, no clone or npm publish required.

# install one skill
npx github:codebygarv/Ai-skills add grill-me

# install several at once
npx github:codebygarv/Ai-skills add pr-reviewer security-auditor

# see everything available
npx github:codebygarv/Ai-skills list

# install for Antigravity, Cursor, Windsurf, or custom location
npx github:codebygarv/Ai-skills add grill-me --target .agents/skills
npx github:codebygarv/Ai-skills add grill-me --target .cursor/rules

By default this drops each skill into .claude/skills/<skill-name>/ in your current directory. Use --target (or -t) to install into any target folder for Google Antigravity, Cursor, Windsurf, GitHub Copilot, Aider, or custom setups.

Option 2 — manual: browse the catalogue above, open a skill's README.md, and copy the skill's folder into your agent's skills directory yourself.

Cloned this repo locally instead? Run the same commands with node bin/ai-skills.js in place of npx github:codebygarv/Ai-skills.

Composing Skills

Skills are designed to be composable — stack them for deeper workflows:

GrillMe + Architecture Reviewer + Security Auditor = Deep Technical Review

Development

No dependencies — the CLI and tests use only the Node standard library (Node 18+).

npm test     # run the test suite (Node's built-in runner)
npm run lint # validate every skill's structure and frontmatter
npm run check # both

Tests cover the CLI end-to-end (install, multi-install, --target, error paths, exit codes) and catalogue integrity — every skill matches docs/SKILL_SPEC.md, skill names are unique, and the README's catalogue links and skill counts stay in sync with what's actually on disk. Both run in CI on every push and PR.

Contributing

New skills, fixes, and improvements are welcome — see CONTRIBUTING.md for the process and quality bar.

Long-Term Vision

Instead of every developer maintaining their own private collection of prompts and agent instructions, they discover specialized, vetted skills from one shared ecosystem — the place you go whenever you think "I need my AI agent to be really good at this specific task."

AI Skills Hub

🌐 Universal Multi-Agent Compatibility (Not Just for Claude Code!)

See it in action

What is this?

Core Vision

What is an AI Skill?

The Catalogue

🧠 Reasoning & Thinking (skills/reasoning/)

💻 Development (skills/development/)

🎨 UI / UX (skills/ui-ux/)

📝 Documentation & Communication (skills/documentation/)

🧪 Quality & Testing (skills/testing/)

🏗️ Project & Architecture (skills/architecture/)

🔐 Security & Compliance (skills/security/)

⚡ Productivity & Workflow (skills/productivity/)

🛠️ Utilities & DevOps (skills/utilities/)