Skip to content
Directory

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.

1,117 skills5 categories Measured from their files, refreshed weekly

How to read a skill

Tokens

What it costs to keep

Idle in context, in use when it runs, and up to with its linked files.

Model dependence

Scripts or instructions

Script-led, mixed or model-led: how much the model has to work out itself.

Touches

What it can reach

Shell, network, file writes, git and credentials, declared or detected.

Scores

Quality, security, repo health

Out of 100, each with what it is made of. Turn a card over to see them.

Showing 547 of 1117 skillsShell Writes Files Network Git Credentials Clear all
Model-led559 tokens in use

competition-ad-certificate-abuse

44,996

A downstream CTF-sandbox skill for Active Directory certificate challenges: templates, enrollment rights, EKUs, SAN controls and where an issued cert is accepted.

Skill
122idle
559in use
794up to
Tokens, counted offlineView skill
Model-led676 tokens in use

competition-agent-cloud

44,996

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.

Skill
110idle
676in use
894up to
Tokens, counted offlineView skill
Model-led541 tokens in use

competition-android-hooking

44,996

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.

Skill
116idle
541in use
770up to
Tokens, counted offlineView skill
Model-led508 tokens in use

competition-browser-persistence

44,996

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.

Skill
111idle
508in use
744up to
Tokens, counted offlineView skill
Model-led527 tokens in use

competition-bundle-sourcemap-recovery

44,996

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.

Skill
114idle
527in use
755up to
Tokens, counted offlineView skill
Model-led3,291 tokens in use

seo-hreflang

31,136

Validate hreflang on a multi-language site, or generate correct tags as HTML, HTTP headers or sitemap XML, with content parity and locale checks.

Skill
66idle
3,291in use
7,618up to
Tokens, counted offlineView skill
Model-led4,176 tokens in use

seo-local

31,136

Score a local business site on Google Business Profile signals, reviews, NAP consistency, citations, local schema and location page quality.

Skill
63idle
4,176in use
4,176up to
Tokens, counted offlineView skill
Model-led2,959 tokens in use

seo-maps

31,136

Analyze a business on map platforms: geo-grid rank scans, GBP field audit, cross-platform reviews and NAP checks, and competitor radius mapping.

Skill
105idle
2,959in use
2,959up to
Tokens, counted offlineView skill
Model-led2,129 tokens in use

seo-page

31,136

Review one URL end to end: a scripted set of on-page checks first, then judgment on content, schema, images and Core Web Vitals risks.

Skill
32idle
2,129in use
2,129up to
Tokens, counted offlineView skill
Model-led951 tokens in use

seo-plan

31,136

Plan SEO for a new or existing site: competitor analysis, architecture, content calendar and a four-phase roadmap from six industry templates.

Skill
64idle
951in use
951up to
Tokens, counted offlineView skill
Model-led2,082 tokens in use

seo-programmatic

31,136

Plan and audit SEO pages generated at scale from data, with quality gates against thin content, scaled content abuse and index bloat.

Skill
72idle
2,082in use
2,082up to
Tokens, counted offlineView skill
Model-led1,821 tokens in use

seo-schema

31,136

Detect, validate and generate Schema.org JSON-LD for a page, with current rich result status and warnings on deprecated types.

Skill
33idle
1,821in use
3,095up to
Tokens, counted offlineView skill
Model-led2,490 tokens in use

seo-sxo

31,136

Find out why a technically sound page does not rank: compare its page type with the SERP, derive user stories, score personas and draw wireframes.

Skill
38idle
2,490in use
8,545up to
Tokens, counted offlineView skill
Model-led3,305 tokens in use

seo-cluster

31,135

Cluster keywords by how Google ranks them, plan hub-and-spoke content with an internal link matrix, and open an interactive cluster map in the browser.

Skill
56idle
3,305in use
12,801up to
Tokens, counted offlineView skill
Model-led1,751 tokens in use

seo-competitor-pages

31,135

Create X vs Y, alternatives and best-of pages with feature matrices, matching schema markup, title formulas and conversion-minded layouts.

Skill
82idle
1,751in use
1,751up to
Tokens, counted offlineView skill
Model-led2,377 tokens in use

seo-content-brief

31,135

Write research-backed content briefs with competitor gap scoring, a winning outline, per-section word counts, keyword placement and meta tag guidance.

Skill
85idle
2,377in use
5,575up to
Tokens, counted offlineView skill
Model-led5,421 tokens in use

seo-geo

31,135

Audit a page for AI Overviews, AI Mode, ChatGPT and Perplexity citations: passage citability, AI crawler access, llms.txt, brand signals and rendering.

Skill
64idle
5,421in use
7,963up to
Tokens, counted offlineView skill
Model-led592 tokens in use

seo-ahrefs

31,134

Pull live Ahrefs referring domains, backlinks, organic keywords and Content Explorer data into Claude Code through a pinned Ahrefs MCP server.

Skill
55idle
592in use
592up to
Tokens, counted offlineView skill
Model-led688 tokens in use

seo-bing

31,134

Read Bing Webmaster link data and submit fresh URLs through IndexNow from Claude Code, for Bing, Copilot citations and other non-Google engines.

Skill
42idle
688in use
688up to
Tokens, counted offlineView skill
Model-led873 tokens in use

seo-posthog

31,134

Use the PostHog MCP server to report organic visits, landing pages, devices, countries and referrers from Claude Code with read-only HogQL queries.

Skill
69idle
873in use
873up to
Tokens, counted offlineView skill
Model-led418 tokens in use

seo-profound

31,134

Read Profound citation rates for your brand across ChatGPT, Perplexity and other LLMs, with top prompts, competitors and spike or drop alerts.

Skill
46idle
418in use
418up to
Tokens, counted offlineView skill
Model-led563 tokens in use

seo-seranking

31,134

Measure brand share of voice across ChatGPT, Gemini, Perplexity, AI Overviews and AI Mode with SE Ranking, plus SERP and backlink data, in Claude Code.

Skill
41idle
563in use
563up to
Tokens, counted offlineView skill
Model-led604 tokens in use

seo-unlighthouse

31,134

Run Lighthouse across up to 200 routes with the Unlighthouse CLI from Claude Code, with no API quota, and get median scores per category.

Skill
42idle
604in use
604up to
Tokens, counted offlineView skill
Model-led806 tokens in use

ab-test-analysis

28,201

Analyze A/B test results for significance, sample size and guardrail metrics, and get a ship, extend, stop or investigate recommendation.

Skill
55idle
806in use
806up to
Tokens, counted offlineView skill

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers