Trending Agent Skills

1084 skills
skills-101/superpowers
p-video

Generate videos with Pruna P-Video and WAN models via inference.sh CLI, supporting text-to-video, image-to-video, audio sync, and 720p/1080p resolutions.

Installs · 279
lilmgenius/paperthin
feynman

Press a decision you just made until you can explain it to a skeptic in your own words, or surface the gap where you can't.

Installs · 370
skills-101/superpowers
p-video-avatar

Generate realistic talking head avatar videos from a portrait image with Pruna P-Video-Avatar via inference.sh CLI, featuring built-in text-to-speech.

Installs · 279
lilmgenius/paperthin
modelchk

Size a task's run before spending it: the cheapest sufficient capability tier (fast, standard, frontier) and the reasoning effort within it.

Installs · 369
momentic-ai/skills
momentic-mobile-test

Create, run, and maintain Momentic mobile E2E tests and modules for Android and iOS.

Installs · 278
stripe/link-cli
create-payment-credential

Gets secure, one-time-use payment credentials (cards, tokens) from a Link wallet so agents can complete purchases on behalf of users.

Installs · 278
momentic-ai/skills
momentic-maintain

Diagnose, classify, triage, and repair failing Momentic tests with MCP run tools, the Momentic CLI, and manual run artifacts.

Installs · 277
lilmgenius/paperthin
sip

After creating or changing any artifact or skill, taste-test it with our own skills instead of trusting your in-session judgment — recursive self-improvement, made automatic.

Installs · 368
momentic-ai/skills
momentic-explore-prompt

Generate an explore-prompt.md file that gives Momentic's explore agent repo-specific context—which apps to test, the URLs tests must target, how to authenticate, where to save generated tests, and repo quirks.

Installs · 277
lilmgenius/paperthin
reorder

Realign a listing whose order has gone arbitrary — a list, table, catalog, sections, an enum — into a logical sequence under one stated principle, moving items only.

Installs · 367
momentic-ai/skills
momentic-result-classification

Classify or explain Momentic test run results using Momentic MCP tools to understand failures and triage test outcomes.

Installs · 277
momentic-ai/skills
momentic-spec

Improve code correctness using Momentic specs in the feature development process.

Installs · 277
lilmgenius/paperthin
aim

When data arrives with a thin ask, read it and propose the user's intent as a proposal to confirm, not a question.

Installs · 367
momentic-ai/skills
momentic-test

Create, run, and maintain Momentic browser E2E tests and modules stored as *.test.yaml and *.module.yaml files.

Installs · 277
greensock/gsap-skills
gsap-utils

Official GSAP skill for gsap.utils — clamp, mapRange, normalize, interpolate, random, snap, toArray, wrap, pipe, and more.

Installs · 276
anthropics/skills
canvas-design

The canvas-design skill creates beautiful visual art in .png and .pdf documents using design philosophy, suitable for posters, art, and other static designs.

Installs · 270
lilmgenius/paperthin
detool

Make durable artifacts portable by replacing incidental stack, vendor, model, CLI, path, quota, or harness nouns with the mechanism they mean, while keeping provenance, runbooks, and tool-subject claims concrete.

Installs · 366
kotot/vision
vision

Enables models without native vision to see, read, describe, or OCR images by delegating to a configurable OpenAI-compatible vision model.

Installs · 269
greensock/gsap-skills
gsap-frameworks

Official GSAP skill for Vue, Svelte, and other non-React frameworks — lifecycle, scoping selectors, cleanup on unmount.

Installs · 268
jakubkrehel/skills
better-writing

UX writing and interface copy skill for writing or reviewing any user-facing text.

Installs · 267
jakubkrehel/skills
better-accessibility

Accessibility engineering for product interfaces, used when building or reviewing UI components and custom widgets, or when users report keyboard or screen-reader issues.

Installs · 267
jakubkrehel/skills
better-interface

Cross-discipline interface review skill that routes a screen or flow to domain skills and consolidates a ranked verdict.

Installs · 264
dietrichgebert/ponytail
ponytail-review

The ponytail-review skill focuses on identifying over-engineering in code and suggesting deletions of unnecessary complexity.

Installs · 263
lilmgenius/paperthin
autobahn

Carve guardrail-adjacent items out of scope with safe alternatives before risk-adjacent work starts, then run the safe remainder at full strength in a fresh subagent that only ever sees the carved prompt.

Installs · 364
better-auth/skills
better-auth-best-practices

Configure Better Auth server and client, set up database adapters, manage sessions, add plugins, and handle environment variables.

Installs · 259
expo/skills
expo-dev-client

expo-dev-client is an open-source framework for building and distributing Expo development clients, either locally or via TestFlight for internal testing.

Installs · 257
lilmgenius/paperthin
re0-git

Rewrite a finished commit's message into a clean, handoff-ready form so git log alone tells the story.

Installs · 364
magentosh/superpowers
agent-browser

Browser automation for AI agents via inference.sh.

Installs · 257
lilmgenius/paperthin
re0-memo

Turn a finished, failed, or disappointing work cycle into portable lessons, anti-patterns, quality gates, and next-cycle vocabulary.

Installs · 363
wind-information-co-ltd/wind-skills
wind-find-finance-skill

Wind financial capability discovery and installation router that identifies and installs required data and workflow skills for tasks like market data, analysis, and decision-making.

Installs · 257
expo/skills
expo-native-ui

Build beautiful, native-feeling Expo screens covering Apple HIG styling, semantic colors, native controls, SF Symbols, media, animations, visual effects, gradients, storage, and responsive layout.

Installs · 254
lilmgenius/paperthin
re0-work

Restart a project or artifact from v0 while preserving only proven lessons, contracts, gates, vocabulary, real-surface tests, and negative corpus.

Installs · 362
riekelt/multi-agent-review
multi-agent-review

Review a spec or plan with a panel of six reviewers across two model tiers and three topics, gating the next workflow step with a Blockers/Warnings/Observations verdict.

Installs · 251
lilmgenius/paperthin
re0-plan

Open a paperthin iteration's casebook before re0-loop's first turn, seeding it with real content the moment the folder exists so it is never empty.

Installs · 362
riekelt/principal-engineer
grounding-before-coding

Before writing any non-trivial change, investigating a bug, or working in unfamiliar code, map the real code and data, quote evidence, and never guess conventions.

Installs · 247
riekelt/principal-engineer
principal-engineering

Foundation skill for any non-trivial engineering work, encoding evidence-over-theory discipline, hard safety rules, and a pre-change checkpoint.

Installs · 247
lilmgenius/paperthin
re0-merge

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing.

Installs · 362
riekelt/principal-engineer
guarding-architecture

Encodes structural invariants as named, enforced contracts to protect module boundaries and critical paths.

Installs · 247
lilmgenius/paperthin
re0-loop

re0-loop runs repeated build -> QA -> re0-memo -> re0-work cycles while preserving learning and letting code die, for long agentic projects.

Installs · 362
riekelt/principal-engineer
keeping-one-source-of-truth

Ensure every fact has exactly one authoritative source, preventing data inconsistency by deriving, extending owners, and absorbing duplicates.

Installs · 247
lilmgenius/paperthin
re0-release

Walk a pending change through this repo's shipping and releasing checklist end to end, then tag and publish once confirmed.

Installs · 362
riekelt/principal-engineer
verifying-before-done

Before claiming "done", "fixed", "passing", or "shipped", verify: drive the change at its surface, run the verify command, report faithfully, distrust green suites, and own failing gates.

Installs · 247
riekelt/principal-engineer
writing-unit-tests

Use when writing or refactoring unit tests, emphasizing behavior-first, contract testing, determinism, and mocking only at boundaries you do not own.

Installs · 247
riekelt/principal-engineer
scoping-changes

Size fixes to their trigger, decompose rather than descope, and drive work to completion.

Installs · 246
riekelt/principal-engineer
operating-safely

Provides destructive-operation guards, secrets hygiene, and concurrent-session safety for actions touching live systems, shared state, or irreversible operations.

Installs · 246
riekelt/principal-engineer
handling-failures

Enforces the no-silent-swallows contract and fail-loud discipline when writing or touching any error path, catch block, fallback, default value, retry, or degraded mode.

Installs · 246
riekelt/principal-engineer
adding-dependencies

Use when about to add, update, vet, or remove a dependency - a package, library, SDK, GitHub action, base image, or vendored code - or when a project's dependency posture needs declaring.

Installs · 246
dietrichgebert/ponytail
ponytail-audit

Whole-repo audit for over-engineering, listing what to delete, simplify, or replace with stdlib/native equivalents.

Installs · 246