Custom Skills

Browse repo-owned AI agent skills

These are the repo-owned skills in ./skills/. Detail pages live under /skills/catalog/custom/<name>/. See Skill Catalog for external skills.

Quick Install

npx skills add github:wyattowalsh/agents --all -y -g --agent antigravity --agent claude-code --agent codex --agent crush --agent cursor --agent gemini-cli --agent github-copilot --agent grok --agent opencode

npx skills add github:wyattowalsh/agents --skill review -y -g --agent antigravity --agent claude-code --agent codex --agent crush --agent cursor --agent gemini-cli --agent github-copilot --agent grok --agent opencode

69 Custom Skills62 User-Invocable7 Convention Skills

Skill Lanes

Review & QACode review, docs QA, test strategy, performance, or security scanning.

Build & DesignUse these when you are creating frontends, APIs, data systems, infra, or MCP servers.

Strategy & ResearchFuzzy problems, real trade-offs, or deeper investigation first.

Workflow & UtilityCoordinate work, review or simplify code, git flow, releases, or local file tasks.

User-Invocable Skills (62)

Manual invocation Call these when you want a specialist on demand. They appear in the autocomplete menu.

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

agent-runtime-governanceAudit runtime controls for tool permissions, approvals, memory, telemetry, evals, rollout, and containment. Use when reviewing tool-bearing agent systems.

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

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

cross-agent-install-smokePhase 1 dry-run JSON smoke and phase 2 temp-HOME install smoke for skills sync. Use when validating cross-harness install parity. NOT for live --apply installs.

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

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

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

designDesign, build, refactor, and audit user-facing interfaces.

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

docling-graphUse when designing/reviewing Docling Graph knowledge-graph workflows: templates, contracts, CLI/API configs, inspect reports, exports, traces.

docs-stewardMaintain docs across Starlight, Docusaurus, MkDocs. Sync, health checks, migrations, ADRs, runbooks, README, and AGENTS.md. Use when docs change.

draw-thingGenerate local AI images and short media with Draw Things CLI on macOS.

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

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

ffmpegProbe, trim, transcode, concat, and extract local A/V with ffmpeg/ffprobe. Use when converting or inspecting media files.

files-buddyUse when safely auditing, organizing, deduplicating, renaming, archiving, offloading, or reclaiming storage on macOS file systems and cloud-drive folders.

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

grok-delegateUse when delegating to native Grok CLI for default Tier-T trivial leaves or wave/tune nodes from parent harnesses. NOT for harness sync or wrappers.

harness-masterAudit harness configs, discover gaps, usage signals, apply approved fixes. Use when tuning Claude, Codex, Copilot, Cursor, Gemini, Grok, OpenCode, or Cherry.

host-panelFacilitate research-grounded panels in roundtable, Oxford, and Socratic formats. Use when exploring contested topics from multiple angles.

i18n-localizationPlan and review localization changes across app, docs, and web surfaces.

incident-response-engineerOperational incident response for triage, containment, communications, recovery, and postmortems. Use when coordinating outages or service degradation.

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

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

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

mcphub-operatorOperate MCPHub groups, endpoints, compression, and CLI from repo registry. Use for hub preflight, group picking, tunnel vs local exposure. NOT harness sync.

namerName anything: projects, products, companies, packages.

nerdbotUse when creating, repairing, querying, auditing, or migrating Obsidian-native git KBs with raw/wiki layers. NOT for docs sites or generic notes.

new-projectInitialize projects with safe, preference-driven scaffolds, docs, AI instructions, quality gates, GitHub setup, and design baselines.

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

opencode-ensembleUse when coordinating OpenCode Ensemble teams, delegating independent coding work, reviewing teammate output, or running staged parallel waves.

openspec-workflowUse when planning, applying, validating, or archiving OpenSpec changes in this repo, or when downstream AI tools need OpenSpec JSON status/instructions.

orchestratorReview and orchestrate parallel execution via subagent waves, teams, and pipelines. Use when 2+ independent actions need coordination.

pentestAuthorized pentest planning with mandatory ROE scope gate. Synthesizes phase checklists and findings.

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

prompt-engineerPrompt engineering. Craft, analyze, harden, convert, design tool prompts, and build PromptOps/eval plans. Use for system, agent, tool, RAG prompts.

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

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

researchDeep multi-source research with reviewable plans, source-support auditing, and confidence scoring.

reviewUse for session, scoped, PR, range, full audit, simplification, and source/provenance reviews with evidence-first findings.

schema-evolution-plannerPlan 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-scannerProactive security assessment with SAST, secrets detection, dependency scanning, and compliance checks. Use for pre-deployment audit.

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

skill-bundle-curatorSummarize bundle components from agent-bundle.json and repo skill/agent counts. Use when packaging or auditing distributable bundles.

skill-compat-matrixReport portable vs runtime-specific skill fields across supported harnesses. Use when auditing cross-agent compatibility. NOT for live installs or packaging.

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

skill-eval-scaffolderScaffold evals/evals.json manifests for repo skills with baseline cases. Use when adding behavioral eval coverage. NOT for live LLM eval execution.

skill-install-dry-run-plannerPlan cross-harness skills sync dry-run steps before any live install. Use when reconciling harness skill inventory. NOT for --apply or npx installs.

skill-lifecycle-managerReport skill lifecycle stage from frontmatter, eval coverage, and validators. Use when promoting, deprecating, or auditing repo skills. NOT for live installs.

skill-package-manifest-enricherEnrich portable skill ZIP manifests with compatibility and eval metadata. Use before packaging or catalog promotion. NOT for live installs.

skill-quality-dashboardAggregate generated maintainer reports into a skill-quality summary. Use when reviewing docs, link, and eval health. NOT for editing report sources.

skill-routerRoute tasks to local skills. Use when choosing skills, recovering omitted skills after context warnings, or preparing a small skill context packet.

skill-tag-taxonomistInfer and audit skill tags from names, descriptions, and catalog authoring rows. Use when organizing catalog taxonomies. NOT for live catalog index edits.

skill-token-budget-linterLint skill descriptions, body length, and reference bulk against token budgets. Use when tightening standing-context cost. NOT for DCP tuning or RTK hooks.

skill-trace-debuggerInspect eval manifests and portable validators for trace-friendly skill signals. Use when debugging skill invocation gaps. NOT for live LLM trace capture.

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

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

things-managerUse when reviewing/managing Things 3 via SupaThings MCP: tasks, projects, headings, tags, deadlines, triage, capture, cleanup, and GTD.

trafilaturaExtract clean article text and metadata from URLs or HTML with trafilatura CLI. Use for single-page extraction, piped/local HTML, bounded discovery.

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

yt-dlpProbe, transcript, and download video/audio with yt-dlp CLI on supported hosts. Use when you need metadata, captions, or local media.

Convention Skills (7)

Auto-invoked The agent loads these automatically when repo context matches. They stay out of the / menu.

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

javascript-conventionsConfigure and validate JS/TS tooling conventions. Enforce pnpm, TypeScript, ESLint, and Prettier defaults. Use when working on JS/TS files or package.json.

python-conventionsEnforce Python tooling conventions for uv, ty, Ruff, pytest, and pyproject.toml. Use when working on .py files or Python project config.

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

skill-localization-packagerScaffold for packaging localized skill variants (planned). Use when designing i18n skill bundles. NOT for live catalog edits.

skill-registry-lockScaffold for pinning curated skill registry lockfiles (planned). Use when designing reproducible sync locks. NOT for live --apply sync.

skill-signing-verifierScaffold for verifying skill package signatures and provenance (planned). Use when designing supply-chain checks. NOT for live signing or key management.

Installing Individual Skills

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

# Install a single skill globally
npx skills add github:wyattowalsh/agents --skill review -y -g --agent antigravity --agent claude-code --agent codex --agent crush --agent cursor --agent gemini-cli --agent github-copilot --agent grok --agent opencode

# Install multiple specific skills
npx skills add github:wyattowalsh/agents --skill review --skill wargame -y -g --agent antigravity --agent claude-code --agent codex --agent crush --agent cursor --agent gemini-cli --agent github-copilot --agent grok --agent opencode

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

Custom

External