AI Skills

coverage

Analyze test coverage gaps

eval

Evaluate and rank agent results by metric or LLM judge for an AgentHub session

extract

Turn a proven pattern or debugging solution into a standalone reusable skill

finance-skills

Router/index for the 2 finance skills bundled in this plugin: financial-analyst

fix

Fix failing or flaky Playwright tests

generate

Generate Playwright tests

grill-me

Interview the user relentlessly about a plan or design until reaching shared

hard-call

/em:hard-call — Framework for decisions with no good options

init

Set up Playwright in a project

loop

Start an autonomous experiment loop with user-selected interval

marketing-skills

Directory and router for the marketing skills library

merge

Merge the winning agent's branch into base, archive losers

migrate

Migrate from Cypress or Selenium to Playwright

pm-skills

Coordinating project-delivery work across the 8 project-management sub-skills

postmortem

/em:postmortem — Honest analysis of what went wrong

product-skills

Coordinating product work across the 12 bundled product sub-skills

ra-qm-skills

Router/index for the 15 regulatory & quality-management skills bundled in this

remember

Explicitly save important knowledge to auto-memory with timestamp and context

report

Generate test report

research-summarizer

Structured research summarization agent skill for non-dev users

resume

Resume a paused experiment

review

Review Playwright tests for quality

run

Run a single experiment iteration

senior-backend

Designs and implements backend systems including REST APIs, microservices

senior-frontend

Frontend development skill for React, Next.js, TypeScript

senior-fullstack

Fullstack development toolkit

senior-qa

Generates unit tests, integration tests

senior-security

For STRIDE threat modeling, DREAD risk scoring

setup

Set up a new autoresearch experiment interactively

social-media-analyzer

Social media campaign analysis and performance tracking

social-media-manager

Develop social media strategy, plan content calendars

spawn

Launch N parallel subagents in isolated git worktrees

status

Show experiment dashboard with results, active loops, and progress

stress-test

/em:stress-test — Business assumption stress testing

testrail

Sync tests with TestRail

cli-creator

Build a composable CLI for Codex from API docs, an OpenAPI spec

define-goal

Help the user define a concrete, measurable goal before starting work

hatch-pet

Create, repair, validate, visually QA

migrate-to-codex

Migrate supported instruction files, skills, agents

plugin-creator

Create and scaffold plugin directories for Codex

skill-installer

Install Codex skills into $CODEX_HOME/skills

beads

Dolt-powered issue tracker for multi-session work

expo/upgrading-expo

Upgrade Expo SDK versions

pi-planning-with-files

Persistent file-based planning for multi-step AI-agent work

planning-with-files

File-based task organization and progress tracking

planning-with-files-zh

Manus-style file-based planning system

ai-sdk

AI SDK documentation and guidance for building AI-powered features

migrate-ai-sdk-v6-to-v7

Migrate applications from AI SDK 6.x to AI SDK 7.0

ahujasid/blender-mcp

Connect AI assistants to Blender

ab-test-analysis

Analyze A/B test results with statistical significance, sample size validation