Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Filter by category
70,705 results · page 1519 of 2,357
- View details
re-shellcodeSkillDev tools
Lets your agent extract, decode, and emulate shellcode from binaries during malware analysis.
Ready to connect★ 117
- View details
re-stegoSkillFiles & storage
Lets your agent detect and extract hidden data in files, like appended data or image LSB steganography.
Ready to connect★ 117
- View details
re-swiftSkillDev tools
A swift claude skill that helps your agent analyze compiled Swift binaries, decoding symbols and closure captures.
Ready to connect★ 117
- View details
re-teeSkillFiles & storage
Lets your agent answer questions about TEE and TrustZone internals like OP-TEE, trusted apps, and secure storage.
Ready to connect★ 117
- View details
re-tlsSkillDev tools
Lets your agent analyze encrypted TLS traffic, fingerprint clients, and inspect certificates.
Ready to connect★ 117
- View details
re-tracingSkillMonitoring & ops
Lets your agent trace system and library calls of a program using strace or ltrace to see what it does.
Ready to connect★ 117
- View details
re-triageSkillFiles & storage
Lets your agent inspect an unknown file's type, hashes, entropy, and architecture before deeper analysis.
Ready to connect★ 117
- View details
re-uefiSkillDev tools
Helps your agent analyze UEFI and BIOS firmware, identifying boot phases, DXE drivers, modules, and bootkits.
Ready to connect★ 117
- View details
re-unpack-advancedSkillDev tools
Lets your agent unpack Windows programs protected with VMProtect or Themida so they can be analyzed.
Ready to connect★ 117
- View details
re-unpack-simpleSkillDev tools
Lets your agent unpack compressed executables packed with UPX, ASPack, or FSG so they can be analyzed.
Ready to connect★ 117
- View details
re-variantSkillMonitoring & ops
Lets your agent compare binaries and find how two versions differ, including patch and variant analysis.
Ready to connect★ 117
- View details
re-vulnSkillSecurity
Lets your agent find software vulnerabilities by fuzzing targets, analyzing crashes, and producing reports.
Ready to connect★ 117
- View details
re-whiteboxSkillCommerce & finance
Lets your agent analyze white-box cryptography implementations and extract hidden encryption keys.
Ready to connect★ 117
- View details
re-windbgSkillDev tools
Lets your agent debug Windows programs and kernel crashes using WinDbg commands.
Ready to connect★ 117
- View details
re-x64dbgSkillDev tools
Lets your agent debug Windows programs with x64dbg by attaching to processes, setting breakpoints, and using Scylla.
Ready to connect★ 117
- View details
re-z3SkillDev tools
Lets your agent model constraints and solve them with Z3 to derive keys or flags.
Ready to connect★ 117
- View details
re-zigSkillDev tools
Lets your agent analyze Zig build artifacts, identifying code, comptime expansions, and error handling paths.
★ 117
- View details
reconcile-code-reviewSkillAI & models
Lets your agent merge code review findings from specialists, bots, and human comments into one final classified list.
Ready to connect★ 117
- View details
recursive-debuggingSkillAI & models
Guides your agent to find the root cause of a bug or failing test before trying any fixes.
Ready to connect★ 117
- View details
recursive-modeSkillDocs & knowledge
Lets your agent run staged coding workflows, lock completed phases, and verify those locks.
Ready to connect★ 117
- View details
recursive-review-bundleSkillAI & models
Lets your agent create a reproducible review bundle to hand off delegated code or test reviews for auditing.
Ready to connect★ 117
- View details
recursive-routerSkillAI & models
Lets your agent route delegated audit, review, and implementation tasks to external tools and models with verification.
Ready to connect★ 117
- View details
recursive-specSkillAI & models
Lets your agent write plans, specs, and requirements for new work, with approval steps before proceeding.
Ready to connect★ 117
- View details
recursive-subagentSkillDocs & knowledge
Lets your agent delegate audit, review, and testing checks to subagents, with a self-audit fallback.
Ready to connect★ 117
- View details
recursive-tddSkillAI & models
Makes your agent write code test-first, requiring a failing test before any production code is written.
Ready to connect★ 117
- View details
recursive-trainingSkillDocs & knowledge
Lets your agent save lessons learned from past runs into a memory folder and reuse them in future runs.
Ready to connect★ 117
- View details
recursive-worktreeSkillAI & models
Lets your agent set up an isolated git workspace so code changes stay off the main branch.
Ready to connect★ 117
- View details
render-evidenceSkillMedia
Lets your agent capture before/after rendered PNG screenshots as visual evidence for UI-affecting pull requests.
Ready to connect★ 117
- View details
ribaoSkillDev tools
Lets your agent write daily, weekly, or status reports from your work facts and existing templates.
Ready to connect★ 117
- View details
role-modelSkillAI & models
Lets your agent use a locally running role-model runtime for its AI tasks.
Ready to connect★ 117
Popular skills lists
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
- Best Claude skills for superpowers
- Best Claude skills for obsidian
- Best Claude skills for frontend design
- All best lists
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
68,575 of the 70,705 skills listed here can be served through Ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your workspace and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.