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.
How to read a skill
What it costs to keep
Idle in context, in use when it runs, and up to with its linked files.
Scripts or instructions
Script-led, mixed or model-led: how much the model has to work out itself.
What it can reach
Shell, network, file writes, git and credentials, declared or detected.
Quality, security, repo health
Out of 100, each with what it is made of. Turn a card over to see them.
Codebase Design
329,112Developer 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.
Implement
329,112Agent 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.
Implement Spec
329,112Agent Workflows · Developer Tools
Implements a whole spec on one integration branch by running implementer subagents in parallel across the ready tickets.
PR
329,112Developer Tools
A pull request body template with a summary as the smallest useful visual, before and after evidence, and a merge-danger call.
dispatching-parallel-agents
322,961Agent Workflows · Developer Tools
Splits two or more independent problems across focused subagents, each with its own scope, constraints and expected output.
verification-before-completion
322,961Agent Workflows · Code Review And Quality · Developer Tools
Requires fresh command output as evidence before your agent claims work is done, fixed or passing.
academy-guide
198,136AI Fluency
When someone asks how to use Claude or a Claude product, Claude answers first, then points to one or two strongly matching Claude Academy courses, tutorials or use cases.
claude-api
198,136Developer Tools
Anthropic's reference skill for building with the Claude API: current model IDs and pricing, SDK patterns in seven languages and cURL, Managed Agents, migrations and evals.
discernment-nudge
198,136AI Fluency
After a substantive answer the user may act on, Claude appends two or three specific follow-up questions that help check facts, probe reasoning and notice missing context.
frontend-design
198,136Design 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.
mcp-builder
198,136Developer 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.
competition-ad-certificate-abuse
44,998Security 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.
competition-agent-cloud
44,998Security 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.
competition-android-hooking
44,998Security 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.
competition-browser-persistence
44,998Security 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.
competition-bundle-sourcemap-recovery
44,998Security 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.
competition-cloud-metadata-path
44,998Security 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.
competition-container-runtime
44,998Security 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.
competition-crypto-mobile
44,998Security 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.
competition-custom-protocol-replay
44,998Security 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.
competition-dpapi-credential-chain
44,998Security 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.
competition-file-parser-chain
44,998Security 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.
competition-firmware-layout
44,998Security 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.
Competition Forensic Timeline
44,998Security 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.