Skip to content
Directory

Agent skills

Skills for AI coding agents, each with what it costs to load, how much of it is scripts and what it touches on your machine.

1,192 skills27 categories Measured from their files, refreshed weekly

How to read a skill

Tokens

What it costs to keep

Idle in context, in use when it runs, and up to with its linked files.

Model dependence

Scripts or instructions

Script-led, mixed or model-led: how much the model has to work out itself.

Touches

What it can reach

Shell, network, file writes, git and credentials, declared or detected.

Scores

Quality, security, repo health

Out of 100, each with what it is made of. Turn a card over to see them.

Showing 62 of 1192 skillsSecurity Ctf And Reverse Engineering Developer Tools Network Shell Clear all
Model-led1,295 tokens in use

Codebase Design

329,112

Developer Tools · Software Architecture And Planning

Shared vocabulary for deep modules: a lot of behaviour behind a small interface, placed at a clean seam and testable through that interface.

Skill
57idle
1,295in use
2,451up to
Tokens, counted offlineView skill
Model-led106 tokens in use

Implement

329,112

Agent Workflows · Developer Tools

Builds the work in a spec or ticket by driving TDD at pre-agreed seams, then runs code-review and commits to the current branch.

Skill
16idle
106in use
106up to
Tokens, counted offlineView skill
Model-led572 tokens in use

Implement Spec

329,112

Agent Workflows · Developer Tools

Implements a whole spec on one integration branch by running implementer subagents in parallel across the ready tickets.

Skill
18idle
572in use
572up to
Tokens, counted offlineView skill
Model-led914 tokens in use

PR

329,112

Developer Tools

A pull request body template with a summary as the smallest useful visual, before and after evidence, and a merge-danger call.

Skill
9idle
914in use
914up to
Tokens, counted offlineView skill
Model-led1,340 tokens in use

dispatching-parallel-agents

322,961

Agent Workflows · Developer Tools

Splits two or more independent problems across focused subagents, each with its own scope, constraints and expected output.

Skill
26idle
1,340in use
1,340up to
Tokens, counted offlineView skill
Model-led815 tokens in use

verification-before-completion

322,961

Agent Workflows · Code Review And Quality · Developer Tools

Requires fresh command output as evidence before your agent claims work is done, fixed or passing.

Skill
43idle
815in use
815up to
Tokens, counted offlineView skill
Model-led1,871 tokens in use

frontend-design

198,136

Design And Visual Art · Developer Tools · Frontend And UI Engineering

Design guidance that pushes Claude toward distinctive, intentional UI instead of templated defaults, from palette and type to layout and copy.

Skill
41idle
1,871in use
1,871up to
Tokens, counted offlineView skill
Mixed2,375 tokens in use

mcp-builder

198,136

Developer Tools

Anthropic's skill for building MCP servers: research the API, implement tools in TypeScript or Python, test with the Inspector, then measure the server with an LLM evaluation harness.

Skill
61idle
2,375in use
29,563up to
Tokens, counted offlineView skill
Model-led559 tokens in use

competition-ad-certificate-abuse

44,998

Security Ctf And Reverse Engineering

A downstream CTF-sandbox skill for Active Directory certificate challenges: templates, enrollment rights, EKUs, SAN controls and where an issued cert is accepted.

Skill
122idle
559in use
794up to
Tokens, counted offlineView skill
Model-led676 tokens in use

competition-agent-cloud

44,998

Security Ctf And Reverse Engineering

A downstream CTF-sandbox skill for AI-agent, prompt-injection, MCP, cloud, container and CI/CD challenges, with a checklist for deployment truth and provenance.

Skill
110idle
676in use
894up to
Tokens, counted offlineView skill
Model-led541 tokens in use

competition-android-hooking

44,998

Security Ctf And Reverse Engineering

A downstream CTF-sandbox skill for Android APK analysis: static triage, hooks at the narrowest trust boundary, local storage checks and replay of an accepted request.

Skill
116idle
541in use
770up to
Tokens, counted offlineView skill
Model-led508 tokens in use

competition-browser-persistence

44,998

Security Ctf And Reverse Engineering

A downstream CTF-sandbox skill for browser-held state: cookies, web storage, IndexedDB, Cache Storage and service workers, tied to the behavior each one changes.

Skill
111idle
508in use
744up to
Tokens, counted offlineView skill
Model-led527 tokens in use

competition-bundle-sourcemap-recovery

44,998

Security Ctf And Reverse Engineering

A downstream CTF-sandbox skill for built frontends: it uses source maps, manifests and chunk tables to rebuild which served asset runs and what routes or APIs it reveals.

Skill
114idle
527in use
755up to
Tokens, counted offlineView skill
Model-led552 tokens in use

competition-cloud-metadata-path

44,998

Security Ctf And Reverse Engineering

A downstream CTF-sandbox skill for cloud metadata services: it traces how instance or workload identity becomes a credential and which downstream API accepts it.

Skill
118idle
552in use
799up to
Tokens, counted offlineView skill
Model-led572 tokens in use

competition-container-runtime

44,998

Security Ctf And Reverse Engineering

A downstream CTF-sandbox skill for live containers: it compares manifests with running mounts, sidecars and init output and traces which route reaches which container.

Skill
111idle
572in use
800up to
Tokens, counted offlineView skill
Model-led497 tokens in use

competition-crypto-mobile

44,998

Security Ctf And Reverse Engineering

A downstream CTF-sandbox skill for crypto, encoding, steganography and mobile challenges: recover each transform stage in order and hook the narrowest mobile boundary.

Skill
106idle
497in use
689up to
Tokens, counted offlineView skill
Model-led474 tokens in use

competition-custom-protocol-replay

44,998

Security Ctf And Reverse Engineering

A downstream CTF-sandbox skill for unknown protocols: it recovers framing, sequence and checksum rules and builds the smallest replay that reaches an accepted state.

Skill
118idle
474in use
684up to
Tokens, counted offlineView skill
Model-led577 tokens in use

competition-dpapi-credential-chain

44,998

Security Ctf And Reverse Engineering

A downstream CTF-sandbox skill for Windows DPAPI challenges: it tracks a protected blob, its masterkey and decrypting context, and the service that accepts the recovered secret.

Skill
118idle
577in use
817up to
Tokens, counted offlineView skill
Model-led500 tokens in use

competition-file-parser-chain

44,998

Security Ctf And Reverse Engineering

A downstream CTF-sandbox skill for upload and import paths: it follows a file through extraction, conversion, parser and deserializer steps to the backend effect it produces.

Skill
111idle
500in use
720up to
Tokens, counted offlineView skill
Model-led529 tokens in use

competition-firmware-layout

44,998

Security Ctf And Reverse Engineering

A downstream CTF-sandbox skill for firmware images: it maps partitions, boot and update chains and extracted filesystems to the device behavior or artifact they lead to.

Skill
111idle
529in use
756up to
Tokens, counted offlineView skill
Model-led563 tokens in use

Competition Forensic Timeline

44,998

Security Ctf And Reverse Engineering

A downstream CTF-sandbox skill for building one replayable incident chronology from EVTX, PCAP, registry, disk, memory, mailbox and browser artifacts.

Skill
113idle
563in use
829up to
Tokens, counted offlineView skill
Model-led521 tokens in use

Competition GraphQL RPC Drift

44,998

Security Ctf And Reverse Engineering

A downstream CTF-sandbox skill for comparing declared GraphQL, RPC and OpenAPI contracts with live handler behavior to explain hidden operations.

Skill
114idle
521in use
747up to
Tokens, counted offlineView skill
Model-led727 tokens in use

Competition Identity Windows

44,998

Security Ctf And Reverse Engineering

A downstream CTF-sandbox skill for Active Directory, Kerberos, Windows host evidence and enterprise mail challenges, with routing to eight narrower skills.

Skill
112idle
727in use
1,006up to
Tokens, counted offlineView skill
Model-led557 tokens in use

Competition iOS Runtime

44,998

Security Ctf And Reverse Engineering

A downstream CTF-sandbox skill for iOS app runtime analysis: IPA triage, Frida hooks, Keychain and plist inspection, trust checks and request signing.

Skill
123idle
557in use
804up to
Tokens, counted offlineView skill

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers