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.
setup-ts-deep-modules
328,764Wire dependency-cruiser into a TypeScript repo so each package is a deep module reachable only through its entry points.
slack-gif-creator
197,764Design And Visual Art
Anthropic's skill for Slack GIFs: Claude draws frames with Pillow, eases the motion and saves a size-optimized emoji or message GIF that meets Slack's limits.
algorithmic-art
197,763Design And Visual Art
Anthropic's generative art skill: Claude writes an algorithmic philosophy, then builds it as a seeded p5.js sketch in an interactive HTML viewer.
dbs-human-dispatch
11,518Hands a task to an employee or collaborator with a written brief, follows replies and progress, and checks the delivered work against fixed criteria.
replica-brand
10,140Names and rebrands an app clone: candidate names with checks to run, a new palette, a logo brief, a voice guide and a sweep for leftovers.
replica-design
10,140Rebuilds an app's design system for a clone as tokens and component specs, with open icons and fonts and a WCAG contrast checker.
replica-launch
10,140Writes the launch for an app clone: a landing page from your angle, pricing set against the original, and store listings linted by script.
replica-test
10,140Tests an app clone end to end: a test plan from the recon flows, Playwright and axe specs, manual click-throughs and severity-rated bug reports.
defold-core
9,684Helps an agent build and debug Defold 1.14 games in Lua: collections, input focus, messages, factories, proxies, a project checker and Bob builds.
steam-publish
9,684Ship a game on Steam with Steamworks and SteamPipe: depots, app_build scripts, a script checker, steamcmd uploads, beta branches and release steps.
tower-defense
9,684Designs tower defense games in any engine: paths, waves, targeting and gold economy, with a script that checks the wave curve before playtesting.
unity-csharp-scripting
9,684Helps an agent write and fix Unity 6.3 C# gameplay scripts: MonoBehaviour lifecycle, serialization, .meta and GUID discipline, and command-line compile and tests.
platformer
9,683Designs 2D platformer jump feel in any engine: coyote time, jump buffering, variable height, fall gravity and corner correction, with a calculator that derives and checks the numbers.
Create Game Assets
9,682Plans, generates or sources and validates consistent game art: style guides, sprites, pixel art, tilesets, icons and textures, with Pillow QA scripts and licence records.
Browser CDP
8,793Start a debug copy of your Chrome with its saved logins and drive it through agent-browser: open pages, run JavaScript, click and read page text.
story-publish
8,793Prepares the book-creation sheet for Fanqie Novel from your settings and outline: title, pen name, categories, tags, synopsis and cover.
CVSS v4.0 Scoring
8,319Produces a CVSS v4.0 vector string from a written vulnerability description by scoring base metrics in a fixed order, and links the FIRST.org calculator.
let-fate-decide
8,319Draws a 12-house Tarot spread with cryptographic randomness to add entropy to vague or casually delegated prompts.
skill-designer
7,430Builds a prompt from a JSON skill idea that tells Claude CLI to create a full skill folder with SKILL.md, references, scripts and tests.
US Market Bubble Detector
7,430Scores US market bubble risk from six measured indicators and a capped qualitative adjustment, then labels a phase from Normal to Critical with a stated risk budget.
Options Strategy Advisor
7,428An educational options toolkit: a Black-Scholes pricing and Greeks library plus a nine-step workflow for simulating profit and loss across 18 strategies, including earnings plays.
Market Environment Analysis
7,427Builds a global market briefing from web search covering indices, forex, commodities, Treasury yields and VIX, with a risk-on or risk-off read.
Breadth Chart Analyst
7,426Reads S&P 500 breadth and uptrend stock ratio data from public CSV files, optionally checks chart images, and writes a Markdown breadth report.
AI Writing Detector
5,770Runs a detect-only review of text for AI writing patterns, using a local Node detector when the host can run it, and reports findings without rewriting.