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.
Software Factory
3,862Agent Workflows
Let coding agents ship fixes through reviewed pull requests, capped merges at a pinned commit, dated backups and a 24 hour rollback watch.
vault-skill-factory
3,794Agent Workflows
Generates a portable, reviewable agent skill from a cluster of mature wiki pages or from one narrated recording of a job, and stops before installing it.
ctf-ai-ml
3,754Security Ctf And Reverse Engineering
A quick reference for AI and machine learning CTF challenges, covering model weights, adversarial examples, LLM prompt attacks and model extraction.
ctf-crypto
3,754Security Ctf And Reverse Engineering
A quick reference for cryptography CTF challenges: RSA, AES, elliptic curves, lattices, PRNG state recovery, padding oracles and classic ciphers.
ctf-forensics
3,754Security Ctf And Reverse Engineering
A quick reference for forensics CTF challenges: disk and memory images, Windows logs, packet captures, steganography, PDFs, signals and blockchain tracing.
ctf-malware
3,754Security Ctf And Reverse Engineering
A quick reference for malware analysis CTF challenges: obfuscated scripts, PE and .NET samples, C2 traffic, YARA rules, shellcode and memory forensics.
ctf-misc
3,754Security Ctf And Reverse Engineering
A quick reference for CTF challenges that fit no single category: jails, encoding puzzles, audio and QR tricks, RF signals and constraint solving.
ctf-osint
3,754Security Ctf And Reverse Engineering
A quick reference for open source intelligence CTF challenges: geolocation, image search, username and social media research, DNS records and web archives.
ctf-pwn
3,754Security Ctf And Reverse Engineering
A quick reference for binary exploitation CTF challenges: stack and heap bugs, ROP, format strings, kernel and sandbox topics, with pwntools templates.
ctf-reverse
3,754Security Ctf And Reverse Engineering
A quick reference for reverse engineering CTF challenges: native binaries, APKs, WASM, custom VMs, anti-debug logic and obfuscated code.
ctf-similar-search
3,754Security Ctf And Reverse Engineering
Searches for similar CTF challenge writeups through the Tavily API and extracts page content, to find reference solutions when you are stuck.
ctf-web
3,754Security Ctf And Reverse Engineering
A quick reference for web CTF challenges: injection, XSS, SSTI, SSRF, JWT, OAuth, file uploads, deserialization and a request fuzzer for lab targets.
ctf-writeup
3,754Security Ctf And Reverse Engineering
Generates a short submission-style writeup for a solved CTF challenge, with metadata, a few steps, one complete solving script and the flag.
solve-challenge
3,754Security Ctf And Reverse Engineering
The entry point of the ctf-skills collection: triages a CTF challenge, picks its category and routes it to the matching specialist skill.
Agent Instructions
687Agent Workflows
Write and maintain the AGENTS.md or CLAUDE.md every session reads, so each rule is met at the moment it applies.
Claude Agents
687Agent Workflows
Drive headless Claude Code (claude -p) from another agent as a peer, a builder or a fresh reviewer, through a wrapper that keeps sessions and modes.
Codex Agents
687Agent Workflows
Use the Codex CLI as a peer, a builder or a fresh reviewer, through a wrapper that remembers the session, model and sandbox across turns.
Delegation
687Agent Workflows
Brief the goal, keep decisions with you, run parallel delegates safely and verify the handoff before you trust a subagent's report.
Flight Deck
687Agent Workflows
A status board for long agent work: STATUS.md, LOG.md and an owner page that survive compaction and show only what needs you.
Gemini Agents
687Agent Workflows
Drive Google's Antigravity CLI as a requested peer, builder or second reviewer, only after the user has agreed and heard the support status.
Grok Agents
687Agent Workflows
Drive the headless Grok CLI from another agent as a peer, a builder or a fresh reviewer from a different model family.
Guardrail Hooks
687Agent Workflows
Turn a rule an agent keeps breaking into a permission rule, hook or script, with templates for a one-way-door guard and a commit-identity guard.
Handover
687Agent Workflows
Write the one note a fresh agent session starts from, after checking the disk, the running jobs and git against what the session remembers.
Retro
687Agent Workflows
At the end of a session, list the friction, find its cause and build a checked fix into your agent setup, or conclude that no change is warranted.