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.
Category: Dev tools
16,902 results · page 301 of 564
- View details
skin-screenshotsSkillDev tools
Capture one centred main-window screenshot per skin across every skin system (Classic, Original, Original-Metal, Modern/.wal) and assemble them into a fixed-duration slideshow GIF. Use when producing marketing imagery, a skin gallery, or any before/after visual comparison across the skin corpus.
Ready to connect★ 119
- View details
spectrum-analyzer-windowSkillDev tools
The dedicated Metal-based spectrum analyzer window — 84-bar mode list, window geometry, docking behavior, the cropped analyzer curve used by Classic/Enhanced/Ultra, vis_classic exact mode and its waveform demand. Use when modifying the spectrum window chrome, mode list, controls, or analyzer curve.
Ready to connect★ 119
- View details
stream-ripperSkillDev tools
Rip a media URL to FLAC/MP3/MP4 via yt-dlp — quality-first format selection, metadata tagging, cover art, metadata-based filenames, .cue from chapters, and the main-window activity band. Use when working on the Stream Ripper, yt-dlp/ffmpeg integration, or the Output → Streaming menu.
Ready to connect★ 119
- View details
user-guideSkillDev tools
User-facing features, menus, keyboard shortcuts, and functionality overview. Use when documenting features, understanding user workflows, or explaining capabilities to users.
Ready to connect★ 119
- View details
visualizationsSkillDev tools
Index of NullPlayer's visualization systems. Use this to discover which sub-skill covers the specific visualizer you're working on (main window vis, spectrum window, album art, ProjectM/MilkDrop, Geiss, Tripex, vis_classic, Metal mode internals).
Ready to connect★ 119
- View details
wal-skin-reportSkillDev tools
Produce a structured compatibility report for one Winamp Modern (.wal) skin — capabilities, supported/unsupported features, per-surface implementation status, open questions, and a grade.
Ready to connect★ 119
- View details
weekly-reviewSkillDev tools
Run a structured weekly review covering projects, habits, goals, and planning. Use when asked for a weekly review, week summary, or weekly planning session.
Ready to connect★ 119
- View details
janitor-fixSkillDev tools
Automatically fix skill problems (safe preview first). Also use with --prune to find and remove broken symlinks, empty directories, and orphaned skills. Trigger with '/janitor-fix'.
Ready to connect★ 118
- View details
janitor-reportSkillDev tools
Full health check of all your skills in one report. Use when the user wants to check for errors, find duplicates, detect broken skills, or get a complete overview of skill health. Pass --brief for inventory only. Trigger with '/janitor-report'.
Ready to connect★ 118
- View details
janitor-valueSkillDev tools
Show whether each skill is earning its context-window cost — combined tokens-used view sorted by waste. Use when the user asks 'are my skills worth it', 'what's my context budget', 'which skills are dead weight', or wants to audit skill value, token cost, or usage. Trigger with '/janitor-value'.
Ready to connect★ 118
- View details
like-perspectiveSkillDev tools
Thinking operating system of master TCM physician Li Ke (1930–2013). Distilled from 13 sources (11 books + 2 interviews), containing 423 medical cases, 120+ formulas, 92 symptom routings, and 24 false-pattern identifications. Core capabilities: emergency and critical-care treatment (heart failure/st
Ready to connect★ 118
- View details
modern-pythonSkillDev tools
Sets up your agent to create and configure Python projects using modern tools like uv, ruff, and ty.
Ready to connect★ 118
- View details
roastSkillDev tools
Lets your agent put an idea through a five-person critical panel and get one honest GO, RESHAPE, or KILL verdict.
Ready to connect★ 118
- View details
wildcardSkillDev tools
Generate one contrarian, non-obvious insight on whatever the user is thinking about. The thing nobody else would say.
Ready to connect★ 118
- View details
accountSkillDev tools
Create or inspect Convex accounts. Use when the user wants to set up a new account, check account details, or manage keys.
Ready to connect★ 117
- View details
agentic-a11ySkillDev tools
Use when auditing a user-facing app — web, mobile (iOS/Android/React Native/Flutter), desktop, CLI, or games — for accessibility barriers or WCAG 2.2 conformance, before shipping UI changes, or in response to concerns about screen-reader, keyboard, low-vision, motor, cognitive, or photosensitive use
Ready to connect★ 117
- View details
agentic-architectureSkillDev tools
Use when assessing the architectural health of a codebase — before a major refactor, when onboarding to an unfamiliar repo, after rapid growth, when planning a redesign, or to surface structural strengths and risks before they become expensive. Not for fixing what it finds, and not for reviewing a b
Ready to connect★ 117
- View details
agentic-dedupSkillDev tools
EXPERIMENTAL. Use when looking for meaningfully duplicated logic in a codebase, especially duplicate behavior hidden behind different names, different syntax, different control flow, or independently evolved implementations. Not for style issues, not for syntactic clone detection, and not for fixing
Ready to connect★ 117
- View details
ardot-useSkillDev tools
**Mandatory prerequisite** — this skill must be invoked before every call to the `batch_edit` tool. Never call `batch_edit` directly without loading this skill first.
Ready to connect★ 117
- View details
backlogSkillDev tools
EXPERIMENTAL. Use when working the project-wide out-of-scope backlog at paad/code-reviews/backlog.md — cleaning it of entries that are already fixed or gone, or picking the next entry and fixing it end-to-end. Not for producing backlog entries — that is /agentic-review — and not for reviewing a bran
Ready to connect★ 117
- View details
build-convexSkillDev tools
Build the Convex project from source. Use when a contributor wants to compile, test, or package Convex.
Ready to connect★ 117
- View details
cad3-encodingSkillDev tools
CAD3 encoding format — cells, embedded vs branch references, value IDs, validity rules. Use when working on encoders, decoders, serialisation, hashing or anything that reads or writes cell encodings.
Ready to connect★ 117
- View details
cnsSkillDev tools
Resolve or register Convex Name System (CNS) names. Use when the user wants to look up a CNS name, register a new name, or update a name's target.
Ready to connect★ 117
- View details
convex-lispSkillDev tools
Convex Lisp language reference — CVM conventions, calling library code, actor definitions, juice and error codes. Use when writing or debugging CVM source for queries, transactions or actors.
Ready to connect★ 117
- View details
dependency-confusionSkillDev tools
Supply-chain testing via package-manager dependency confusion. Use when
Ready to connect★ 117
- View details
ecosystemSkillDev tools
Orientation in the Convex ecosystem — what lives in which repository, where the specs and docs are, and which client libraries exist. Use when you need context that is not in this repository.
Ready to connect★ 117
- View details
fix-architectureSkillDev tools
Use when working through architectural flaws documented in a paad/architecture-reviews/ report — selecting which flaws to fix, resuming a partial fix session across multiple sittings, or applying structural changes that need to be tracked back to a report. Not for producing that report — run /agenti
Ready to connect★ 117
- View details
intranet-penetration-testingSkillDev tools
Deep specialized skill for intranet penetration testing: local information gathering and credential theft (mimikatz/LSASS/ntds.dit), intranet reconnaissance and hidden tunneling (frp/Chisel/DNS/ICMP), Windows/Linux privilege escalation, lateral movement matrix (IPC/WMI/DCOM/PSEXEC), AD domain penetr
Ready to connect★ 117
- View details
jndi-injectionSkillDev tools
JNDI injection playbook. Use when Java applications perform JNDI lookups with attacker-controlled names, especially via Log4j2, Spring, or any code path reaching InitialContext.lookup().
Ready to connect★ 117
- View details
local-networkSkillDev tools
Run isolated local Convex networks and in-process lattice node networks for development. Use when testing against local peers, reproducing peer or P2P replication issues, exercising NodeServer or P2PNode sync, or when no remote network is configured.
Ready to connect★ 117
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.
53,789 of the 54,221 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 gateway 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.