Skills

Skills are reusable knowledge and workflows that make AI coding agents dramatically more capable. They work across Claude Code, Gemini CLI, Codex, Cursor, GitHub Copilot, and any agentskills.io-compatible agent.

Each skill packages domain expertise into a portable format: install once, invoke anywhere with /skill-name.

Quick Install All

npx skills add wyattowalsh/agents --all -g

New to skills?

Skills extend your AI agent with domain expertise, structured workflows, and proven patterns. Install with npx skills add and invoke with /skill-name in any supported agent. See How it Works for a quick overview, or browse the full agentskills.io ecosystem.

36 User-Invocable4 Convention Skills

Understanding Skill Categories

This repository defines two built-in skill categories. You can also opt in to installed external skills.

Category	Count	How they work
User-Invocable	36	You trigger these manually with /skill-name. They appear in the autocomplete menu.
Convention	4	The agent auto-invokes these when it detects relevant context (e.g., editing Python files). Hidden from the / menu.

Generated docs vs hand-maintained guides

Skill pages under /skills/* are generated from each skill’s SKILL.md. If a deeper curated guide exists (for example, architecture or roadmap notes), the generated skill page links to it.

---

User-Invocable Skills (36)

Manual invocation Trigger these with /skill-name during a conversation. They appear in the autocomplete menu.

These skills are designed to be explicitly called when you want specialized domain knowledge or a structured workflow. They behave like focused teammates you can pull into the session on demand.

Featured: honest-reviewFeatured: skill-creatorFeatured: wargame

add-badges Detect stack and generate shields.io README badges with icons, colors, live endpoints. Use when adding or updating badges.

api-designer Contract-first API design for REST, GraphQL, gRPC. Design, spec, review, version, compat, sdk. Use for API architecture and OpenAPI specs.

changelog-writer Generate changelogs, release notes, and migration guides from git history. Parse conventional commits. Use for releases.

data-pipeline-architect Design batch and streaming data pipelines with contracts, lineage, reliability, and cost controls. Use for ingestion and transformation systems.

data-wizard Analyze data and guide ML: EDA, model selection, feature engineering, stats, visualization, MLOps. Use for data work.

database-architect Design schemas, plan migrations, and optimize queries. Six modes from modeling to evolution. Use for database architecture.

devops-engineer Design, optimize, and debug CI/CD pipelines. GitHub Actions and GitLab CI patterns. Use for pipeline work.

discover-skills Discover AI agent skills via gap analysis, registry search, and ideation. Use when expanding your collection systematically.

docs-steward Maintain docs across Starlight, Docusaurus, MkDocs. Sync, health checks, migrations, ADRs, runbooks. Use when docs change.

draw-thing Local AI image generation via Draw Things CLI. txt2img, img2img, upscale, inpaint, ControlNet, LoRA, batch. Use when you need local image work on macOS.

email-whiz Gmail copilot via MCP. Triage, inbox-zero, filters, analytics, labels, cleanup. Use when managing email or automating Gmail.

event-driven-architect Design event-driven systems: contracts, topics, consumers, retries, idempotency, and sagas. Use for asynchronous workflows. NOT for CRUD APIs or ETL pipelines.

files-buddy Safe filesystem organization, deduplication, renaming, and cleanup with cloud drive support. Delegates to best-in-class CLI tools. Use for file management.

frontend-designer Build frontends with React, Tailwind, shadcn/ui. Scaffold, create, theme, refactor, audit. Use when building or improving UI.

git-workflow Git operations: conventional commits, PR descriptions, branch strategy, conflict resolution, code archaeology, bisect. Use for git workflow tasks.

honest-review Confidence-scored code review with evidence validation. Session or full codebase audit. Use when reviewing changes or auditing quality.

host-panel Simulated expert panel discussions. Roundtable, Oxford-style, Socratic formats. Use when exploring topics from multiple perspectives.

incident-response-engineer Operational incident response for triage, containment, communications, recovery, and postmortems. Use during outages.

infrastructure-coder Infrastructure-as-Code: Terraform, Kubernetes, Docker. Generate, review, cost-compare, security-scan. Use for IaC work.

learn Capture corrections and patterns as reusable knowledge. Routes to the right instruction file. Use when patterns repeat 3+ times or to save insights.

mcp-creator Build MCP servers with FastMCP v3. Research, scaffold, implement, test, deploy. Use when creating MCP servers or integrating APIs via MCP.

namer Name anything: projects, products, companies, packages.

observability-advisor Design and review logs, metrics, traces, SLOs, and alerting for reliable systems. Use for telemetry strategy and coverage gaps.

orchestrator Parallel execution via subagent waves, teams, and pipelines. Use when 2+ independent actions need coordination. NOT for single-action tasks.

performance-profiler Performance analysis: complexity estimation, profiler output parsing, caching design, regression risk. Use for optimization guidance.

prompt-engineer Prompt engineering for any AI system. Craft, analyze, convert between models, evaluate with rubrics. Use for system prompts, agent prompts, tool defs.

reasoning-router Classify problems and route to optimal thinking MCP (11 available). Monitor confidence, re-route on stall. Use for complex reasoning.

release-pipeline-architect Release workflow architecture for versioning, artifact promotion, rollout safety, and rollback design. Use for release pipelines.

research Deep multi-source research with confidence scoring. Auto-classifies complexity. Use for technical investigation, fact-checking.

schema-evolution-planner Plan zero-downtime schema changes across code, data backfills, and cutovers. Use for expand-contract database changes. NOT for fresh schema design or DBA ops.

security-scanner Proactive security assessment with SAST, secrets detection, dependency scanning, and compliance checks. Use for pre-deployment audit.

shell-scripter Shell script generation, review, and dialect conversion. Makefile and justfile generation. ShellCheck rules. Use for shell work.

skill-creator Create, improve, and audit AI agent skills. 14 structural patterns, deterministic scoring. Use when building or reviewing skills.

tech-debt-analyzer Systematic tech debt inventory with complexity analysis, dead code detection, and remediation planning. Track debt over time.

test-architect Test strategy, coverage analysis, edge case identification, flaky test diagnosis. Use when designing test suites.

wargame Strategic decision analysis and wargaming. Auto-classifies complexity for analysis or simulation. Use for decisions under uncertainty.

Convention Skills (4)

Auto-invoked The agent loads these automatically when it detects relevant context — no manual invocation needed. They enforce consistency across the codebase.

Convention skills stay out of the / menu but remain available to the agent. When the repo context matches, they quietly apply the right rules, tooling, and formatting patterns.

agent-conventions Agent definition conventions. Validate frontmatter, update indexes. Use when creating or modifying agents. NOT for skills, MCP servers, or CLAUDE.md.

javascript-conventions JS/TS tooling conventions. Enforce pnpm. Use when working on JS/TS files or package.json. NOT for Python, backend-only, or shell scripts.

python-conventions Python tooling conventions. Enforce uv, ty. Use when working on .py files or pyproject.toml. NOT for JS/TS or shell scripts.

shell-conventions Shell tooling conventions. Enforce portable bash and sh practices, quoting, env usage, and Make or just patterns. Use when editing shell files.

How convention skills work

Convention skills set user-invocable: false in their frontmatter. This hides them from the / menu but keeps their descriptions in the agent’s context, allowing automatic discovery and invocation when the agent encounters matching file types or patterns.

---

Installing Individual Skills

You can also install specific skills rather than the full collection:

# Install a single skill globally
npx skills add wyattowalsh/agents --skill honest-review -g

# Install multiple specific skills
npx skills add wyattowalsh/agents --skill honest-review --skill wargame -g

# Install to a specific agent only
npx skills add wyattowalsh/agents --skill orchestrator -g -a claude-code

Creating your own skills

Want to build a custom skill? Use the skill-creator to scaffold, develop, audit, and package skills following proven structural patterns. Or run wagents new skill my-skill from the CLI.