Skills

The Anomity Catalog lists 35 skills, each scored 0–100 from declared trust, declared capabilities, and matched dangerous combinations. 4 score in the high or critical band; the median score is 40. Discrete agent workflows — brainstorming, debugging, TDD. Some are pure process; some touch files, run commands, or call out.

Entries
35
High or critical
4
Median score
40
Officially published
13
Dangerous combos
8
Most-declared capabilities: network:outbound 17 filesystem:read 14 filesystem:write 9 browser:control 7 credentials:access 7
Skill 100

AI Research Reproduction

lllllllama

Orchestrates end-to-end reproduction of a deep-learning repository — reading the README, setting up the environment, ru…

community 4 caps ⚠ 3 combos
Skill 95

Browser Act

browser-act

A CLI for browser automation that includes stealth features and CAPTCHA solving, aimed at driving sites that actively r…

unknown 3 caps ⚠ 1 combo
Skill 70

Anti-Detect Browser

antibrow

Launches browsers with distinct fingerprints so multiple accounts can be operated without the sites involved correlatin…

unknown 2 caps
Skill 65

Using Git Worktrees

obra/superpowers

Using Git Worktrees is a workspace-management skill from the Superpowers plugin that creates isolated git worktrees for…

community 3 caps ⚠ 1 combo
Skill 50

Best Practices

addyosmani

Applies modern web development practices across security, performance, and code quality — the accumulated "you should p…

community 2 caps
Skill 50

Check

tw93

Reviews code diffs, pull requests, and overall release readiness — pulling the change under review and reporting what l…

community 2 caps
Skill 50

Test-Driven Development

obra/superpowers

Test-Driven Development is a rigid process skill from the Superpowers plugin that enforces a strict red-green-refactor …

community 2 caps
Skill 50

Writing Skills

obra/superpowers

Writing Skills is the meta-skill from the Superpowers plugin: it is the skill the agent uses when the task is to create…

community 2 caps
Skill 45

Azure Deploy

Microsoft

Microsoft's skill for executing Azure deployments with validation and error recovery — provisioning resources, handling…

official 3 caps ⚠ 1 combo
Skill 45

Azure Diagnostics

Microsoft

Diagnoses and remediates Azure production issues systematically — reading resource health, correlating logs, and propos…

official 3 caps ⚠ 1 combo
Skill 40

A/B Testing

coreyhaines31

Plans and designs experiments — hypothesis, metric selection, sample size, and the analysis plan — before anything is s…

community
Skill 40

Accessibility

addyosmani

Audits and improves web accessibility against WCAG 2.2, checking contrast, focus order, labelling, and semantics, then …

community 2 caps
Skill 40

Agent Pulse

jane-o-o-o-o

Inspects local AI-agent activity logs across multiple platforms, reporting sessions, token usage, and estimated cost — …

community 1 cap
Skill 40

AI SEO

coreyhaines31

Optimises content for AI search engines and LLM citation — structuring pages so a model can extract a clean answer and …

community 1 cap
Skill 40

Ask Matt

mattpocock

A router skill: it reads the user's situation and points them at the skill that actually fits, instead of every skill c…

community
Skill 40

Audit Website

squirrelscan

Runs a large rule set — reportedly 249+ checks — over a site covering SEO, performance, security headers, and accessibi…

community 2 caps
Skill 40

Brainstorming

obra/superpowers

Brainstorming is a process skill from the Superpowers plugin that runs before any creative or generative work — buildin…

community
Skill 40

Browser Testing with DevTools

addyosmani

Tests in a real browser via Chrome DevTools — inspecting the DOM, watching network activity, and reproducing behaviour …

community 1 cap
Skill 40

Caveman

juliusbrussee

An ultra-compressed communication mode that strips agent output to essentials, reportedly cutting token usage by around…

community
Skill 40

Caveman Commit

juliusbrussee

Generates compressed commit messages in Conventional Commits format from the staged diff, aiming for a parseable subjec…

community 2 caps
Skill 40

Deep Research

samber

Conducts parallel web searches with multi-source validation and produces a cited report, deliberately cross-checking cl…

community 1 cap
Skill 40

NotebookLM Skill

PleasePrompto

Lets an agent query NotebookLM for source-grounded answers over documents already uploaded there, so responses are anch…

community 2 caps
Skill 40

Systematic Debugging

obra/superpowers

Systematic Debugging is a process skill from the Superpowers plugin that runs before the agent is allowed to propose an…

community 1 cap
Skill 40

YouTube Transcript Downloader

michalparkola

Retrieves and processes transcripts from YouTube URLs so an agent can work with the contents of a talk or tutorial as t…

community 1 cap
Skill 35

Convex Migrate

get-convex

Performs schema migration and data backfill on deployed Convex applications, with a companion rehearsal skill that test…

official 3 caps ⚠ 1 combo
Skill 20

Angular Developer

Angular

Generates Angular code and architectural guidance from the framework team — component structure, signals, dependency in…

official 2 caps
Skill 20

App Insights Instrumentation

Microsoft

Guides Azure Application Insights SDK setup for web applications — adding the SDK, configuring sampling and correlation…

official 2 caps
Skill 20

Azure Compliance

Microsoft

Audits Azure compliance posture and monitors Key Vault expiry — surfacing misconfigured resources and secrets approachi…

official 2 caps
Skill 20

Azure Cost

Microsoft

Manages Azure spend — forecasting, attributing cost to resources, and identifying waste such as idle capacity and overs…

official 2 caps
Skill 20

Cloudflare One

Cloudflare

Cloudflare's skill for configuring Zero Trust and SASE across its product line — access policies, tunnels, gateway rule…

official 2 caps
Skill 20

Convex Advisor

get-convex

Analyses a deployed Convex application's performance and returns evidence-backed optimisation findings — slow queries, …

official 2 caps
Skill 20

ElevenLabs Agents

ElevenLabs

Builds voice AI agents — assistants and interactive characters — wiring speech synthesis, turn-taking, and tool calls i…

official 2 caps
Skill 20

Frontend Design

Anthropic

An Anthropic-published skill that steers an agent away from the generic, templated look that AI-generated interfaces de…

official 2 caps
Skill 20

React Best Practices

Vercel

Vercel's skill encoding performance and correctness guidance for React and Next.js — server versus client components, d…

official 2 caps
Skill 10

Agent Browser

Vercel

Navigates pages, interacts with elements, takes screenshots, and records video — a general-purpose browser-driving skil…

official 2 caps
Machine-readable

This listing is available as Markdown, as JSON, and in the full catalog dump. Every score is a pure function of published inputs — read the formula.