Output rules
adhd
Parallel divergent ideation for coding agents.
The Agentsmith skill library
Find the skill for
your next task.
Reusable instructions for the work you do. Find a skill, read its source, and put it to work.
Explore 147 skills01 / THE COLLECTION
Small skills. Useful work.
Find your next tool.
Ctrl K
Search skill names, descriptions, and task groups. Press Control K or Command K to focus search.
147 skills in the collection
View text catalogTooling
agent-browser
Browser automation CLI for AI agents.
Ecosystem research
apply-grant
Prepare an Agentic Engineering Grant application by gathering project data, git history, and context files, then presenting all fields needed to fill the Solana Earn grant form.
Session control
ask-matt
Ask which skill or flow fits your situation.
De-slopping
avoid-ai-writing
Audit and rewrite content to remove AI writing patterns ("AI-isms").
Backend and databases
backend-specialist
Expert backend engineering playbook for APIs, databases, auth, distributed systems, observability, performance, and production hardening.
Spec-driven development
backprop
Bug → spec protocol.
Review and verification
bench-it
Benchmark a product claim against a named baseline or competitor.
Go to market
brand-design
Generate, preview, and apply a brand color palette (plus typography, gradients, and tone/voice) to a frontend project.
Spec-driven development
build
Plan-then-execute implementation against SPEC.md.
Solana build guides
build-data-pipeline
Guide a developer through building a Solana data pipeline or indexer.
Solana build guides
build-defi-protocol
Guide a developer through building a DeFi protocol on Solana.
Solana build guides
build-mobile
Guide a developer through building a Solana mobile app.
Solana build guides
build-with-claude
Guide a developer through building their Solana MVP step by step using Claude Code.
Output rules
cavecrew
Decision guide for delegating to caveman-style subagents.
Output rules
caveman
Ultra-compressed communication mode.
Output rules
caveman-commit
Ultra-compressed commit message generator.
Output rules
caveman-compress
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens.
Output rules
caveman-help
Quick-reference card for all caveman modes, skills, and commands.
Output rules
caveman-review
Ultra-compressed code review comments.
Output rules
caveman-stats
Show real token usage and estimated savings for the current session.
Spec-driven development
check
Read-only drift detector.
Session control
claude-handoff
Hand the current conversation off to a fresh background agent that picks up the work immediately.
Review and verification
code-review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating…
Architecture and domain modeling
codebase-design
Shared vocabulary for designing deep modules.
Tooling
collab-canvas
Control Collaborator's spatial canvas from the terminal.
Ecosystem research
colosseum-copilot
Search and analyze 5,400+ Solana hackathon projects using Colosseum Copilot.
Validation
competitive-landscape
Map the competitive landscape for a crypto product idea.
Go to market
create-pitch-deck
Create a structured pitch deck for a crypto project.
Review and verification
cso
Chief Security Officer mode.
Solana engineering
debug-program
Help a developer debug a failing Solana program or transaction.
Ecosystem research
defillama-research
Research DeFi protocols and market opportunities using DefiLlama data.
Solana engineering
deploy-to-mainnet
Guide a Solana project from devnet to mainnet production deployment.
Review and verification
deterministic-code-review
Reviews code changes with deterministic scope selection, isolated review units, evidence-backed findings, exact line anchoring, and a final falsification pass.
Go to market
devrel-strategist
Modern Developer Relations strategy for 2025-2026.
Review and verification
diagnose
Disciplined diagnosis loop for hard bugs and performance regressions.
Review and verification
diagnosing-bugs
Diagnosis loop for hard bugs and performance regressions.
Architecture and domain modeling
domain-modeling
Build and sharpen a project's domain model.
Drafting
edit-article
Edit and improve articles by restructuring sections, improving clarity, and tightening prose.
EVM
ethskills
Use when a request involves Ethereum, the EVM, or blockchain systems.
EVM
evm-fullstack-dev
Expert EVM full-stack development for Solidity contracts, Foundry tests, audits, gas optimization, L2 deployments, account abstraction, EIP-7702/4337 flows, viem/wagmi frontends, transaction UX, and production dApps.
Documentation lookup
find-docs
Retrieves up-to-date documentation, API references, and code examples for any developer technology.
Ecosystem research
find-next-crypto-idea
Interview users sharply to discover, rank, or validate what they should build in crypto.
Review and verification
followup-review
Re-review a pull request after the author has pushed fixes for your earlier findings.
Review and verification
fresh-eyes
Get a second opinion from a subagent that has none of your context, either to independently corroborate a diagnosis or to adversarially break your work.
Frontend
frontend-architect
Expert frontend architecture and UI engineering for React, Next.js/App Router, TypeScript, Tailwind, shadcn/ui, accessibility, performance, design systems, Web3 transaction UX, and production-quality interfaces.
Frontend
frontend-design-guidelines
Apply high-quality web interface design rules when building, reviewing, or styling frontend code.
Tooling
git-guardrails-claude-code
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute.
Tooling
git-worktree-runner
Manages isolated development worktrees with git gtr, including creation, validation, command execution, tool launch, and safe cleanup.
Planning and issue tracking
grill-me
A relentless interview to sharpen a plan or design.
Planning and issue tracking
grill-with-docs
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
Planning and issue tracking
grilling
Grill the user relentlessly about a plan, decision, or idea.
Session control
handoff
Compact the current conversation into a handoff document for another agent to pick up.
De-slopping
humanizer
Remove signs of AI-generated writing from text.
Output rules
i-have-adhd
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible.
Frontend
impeccable
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface.
Spec-driven development
implement
Implement a piece of work based on a spec or set of tickets.
Spec-driven development
implement-spec
Implement a specification in code.
Review and verification
improve
Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute.
Review and verification
improve-codebase-architecture
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
Tooling
janitor
Performs a read-only, platform-aware audit of cache and temporary storage, then reports cleanup candidates with measured sizes and risk notes.
Solana build guides
launch-token
Guide a developer through launching a token on Solana.
Session control
learn
Manage project learnings across sessions.
Planning and issue tracking
loop-me
Grill me about specs for the workflows I want to build, within this workspace.
Go to market
marketing-video
Create marketing videos for Solana projects using Remotion (code-driven) and Renoise (AI-generated).
Agent payment rails
masumi
Build AI agents with decentralized payments, identity, and marketplace integration on Masumi Network (Cardano blockchain).
Agent payment rails
masumi-ecosystem-developer
Concise Masumi Network developer guide for decentralized AI-agent payments, identity, registry, marketplace, and Cardano-backed decision logging.
Tooling
migrate-to-shoehorn
Migrate test files from `as` type assertions to @total-typescript/shoehorn.
Agent payment rails
mppx
TypeScript SDK for the Payment HTTP Authentication Scheme.
Session control
navigate-skills
Meta skill — browse all installed solana-new skills, repos, and MCPs to find the right tool for any task
Tooling
obsidian-vault
Search, create, and manage notes in the Obsidian vault with wikilinks and index notes.
Documentation lookup
openai-docs
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model…
Agent payment rails
pay
User-authorized paid HTTP/API access for agents through the Pay MCP server and a locally approved payment wallet.
Code minimalism
ponytail
Forces the laziest solution that actually works, simplest, shortest, most minimal.
Code minimalism
ponytail-audit
Whole-repo audit for over-engineering.
Code minimalism
ponytail-debt
Harvest every `ponytail:` comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals ponytail leaves behind get tracked instead of rotting into "later means never".
Code minimalism
ponytail-gain
Show ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians.
Code minimalism
ponytail-help
Quick-reference card for all ponytail modes, skills, and commands.
Code minimalism
ponytail-review
Code review focused exclusively on over-engineering.
Validation
product-review
Product quality review — UX flows, onboarding, feature completeness, and user value.
Planning and issue tracking
prototype
Build a throwaway prototype to answer a design question.
Review and verification
prove-it
Verify a change in both directions before claiming it works.
Deployment
render-background-workers
Sets up and configures background workers on Render for queue-based job processing.
Deployment
render-blueprints
Authors and validates render.yaml Blueprints for Render infrastructure.
Deployment
render-cli
Installs and uses the Render CLI for deploys, logs, SSH, psql, Blueprint validation, and automation.
Deployment
render-cron-jobs
Configures and troubleshoots scheduled tasks on Render using cron job services.
Deployment
render-debug
Debug failed Render deployments by analyzing logs, metrics, and database state.
Deployment
render-deploy
Deploy applications to Render by analyzing codebases, generating render.yaml Blueprints, and providing Dashboard deeplinks.
Deployment
render-disks
Attaches and manages persistent disks on Render services—mount paths, sizing, snapshots, file transfers, and single-instance constraints.
Deployment
render-docker
Builds and deploys Docker containers on Render—Dockerfiles, multi-stage builds, Blueprint Docker fields, private registries, layer caching, and platform constraints.
Deployment
render-domains
Configures custom domains and TLS certificates on Render—DNS setup, CNAME records, apex domains, wildcard domains, and certificate troubleshooting.
Deployment
render-env-vars
Configures environment variables, secrets, and env groups on Render.
Deployment
render-keyvalue
Provisions and configures Render Key Value (Redis-compatible Valkey 8) instances for caching, session storage, and job queues.
Deployment
render-mcp
Connects and configures the Render MCP server for AI coding tools—setup per tool (Cursor, Claude Code, Codex), authentication, workspace selection, tool catalog, and troubleshooting.
Deployment
render-migrate-from-heroku
Migrate from Heroku to Render by reading local project files and generating equivalent Render services.
Deployment
render-monitor
Monitor Render services in real-time.
Deployment
render-networking
Connects Render services over the private network—internal DNS, service discovery, and cross-service communication.
Deployment
render-postgres
Sets up and optimizes Managed PostgreSQL on Render—connection strings (internal vs external), creation constraints, storage autoscaling, connection limits, high availability, read replicas, backups, and MCP inspection.
Deployment
render-private-services
Configures Render private services—internal-only apps that accept traffic exclusively from other Render services over the private network.
Deployment
render-scaling
Scales Render services—configures autoscaling targets, chooses instance types, sets manual instance counts, and optimizes cost.
Deployment
render-static-sites
Deploys and configures static sites on Render's global CDN—build commands, publish paths, SPA routing, redirects, custom headers, and PR previews.
Deployment
render-web-services
Configures Render web services—port binding, TLS, health checks, custom domains, auto-deploy, PR previews, persistent disks, and deploy lifecycle.
Deployment
render-workflows
Sets up, develops, tests, and deploys Render Workflows.
Documentation lookup
research
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.
Session control
research-url
Research a URL (repo, gist, article, doc) with one dedicated subagent per URL, producing a fixed-format distilled report plus entries in the project learnings file.
Tooling
resolving-merge-conflicts
Use when you need to resolve an in-progress git merge/rebase conflict.
Session control
retro
Conduct a retrospective on a coding session.
Review and verification
review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating…
Review and verification
review-and-iterate
Review Solana project code for quality, security, and production readiness.
Validation
roast-my-product
Harsh, honest product critique — find every weakness before users do.
Tooling
scaffold-exercises
Create exercise directory structures with sections, problems, solutions, and explainers that pass linting.
Solana build guides
scaffold-project
Set up a complete Solana project workspace from a validated idea.
Skill authoring
setup-matt-pocock-skills
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout.
Tooling
setup-pre-commit
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo.
Architecture and domain modeling
setup-ts-deep-modules
Wire dependency-cruiser into a TypeScript repo so each package is a deep module, with implementation hidden in subfolders and reachable only through its entry-point files.
Skill authoring
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance.
Session control
skill-menu
Use when the user asks to list, choose, or explicitly invoke skills with skill:<name>; loads local skill files on demand.
Solana engineering
solana-beginner
Teach Solana fundamentals to developers new to the ecosystem.
Solana engineering
solana-dev
Use when user asks to "build a Solana dapp", "write an Anchor program", "create a token", "debug Solana errors", "set up wallet connection", "test my Solana program", "deploy to devnet", or "explain Solana concepts"…
Solana engineering
solana-dev-expert
Expert guidance on Solana blockchain development including Anchor framework, SPL token creation, NFT minting (Metaplex Core, cNFTs, Token-2022), DeFi protocol integration, wallet integration, PDA derivation, CPI…
Spec-driven development
spec
Create, amend, or backprop bugs into SPEC.md at repo root.
Ecosystem research
submit-to-hackathon
Prepare and optimize a hackathon submission for a Solana project.
Backend and databases
supabase
Use when doing ANY task involving Supabase.
Backend and databases
supabase-postgres-best-practices
Postgres performance optimization and best practices from Supabase.
Review and verification
tdd
Test-driven development.
Session control
teach
Teach the user a new skill or concept, within this workspace.
Agent payment rails
tempo
Use this skill when the user wants to call an API, make an HTTP request, discover available services, or access external data with automatic payments.
Agent payment rails
temprouter
Call tempRouter — a payable, end-to-end-encrypted LLM inference endpoint on MPP (Tempo).
Planning and issue tracking
to-issues
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.
Planning and issue tracking
to-prd
Turn the current conversation context into a PRD and publish it to the project issue tracker.
Planning and issue tracking
to-questionnaire
Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
Spec-driven development
to-spec
Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.
Planning and issue tracking
to-tickets
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native…
Planning and issue tracking
triage
Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.
Deployment
use-railway
Operate Railway infrastructure: create projects, provision services and databases, manage object storage buckets, deploy code, configure environments and variables, manage domains, troubleshoot failures, check status…
Session control
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Validation
validate-idea
Run a structured validation sprint on a crypto startup idea.
Solana engineering
virtual-solana-incubator
Deep technical Solana bootcamp — SVM architecture, Rust patterns, program development.
Output rules
wait-what
Stop.
Spec-driven development
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
Planning and issue tracking
wizard
Generate an interactive bash wizard that walks a human through steps only they can perform.
Skill authoring
write-a-skill
Create new agent skills with proper structure, progressive disclosure, and bundled resources.
Drafting
writing-beats
Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.
Skill authoring
writing-for-agents
Writing documents for agents.
Drafting
writing-fragments
Writing, explore: mine raw fragments, no structure yet.
Drafting
writing-shape
Writing, exploit: shape raw material into an article, paragraph by paragraph.
Session control
zoom-out
Tell the agent to zoom out and give broader context or a higher-level perspective.
No matching skills.
Try a different task or search across all categories.
02 / PUT IT TO WORK
Find. Read. Install.
A skill is a set of instructions your agent can follow for a specific task.
The skills CLI installs skills. Review and adapt rules, workflows, and harness settings separately.
Help improve the collectionStart with your task
Search for the work you need to do. Use a category to narrow the collection.
Read before you install
Open the skill source. Check its instructions, scripts, and source and license notes.
Add it to your setup
Copy a skill's install command and run it in your terminal. Follow the CLI prompts to choose your agent.