Extract
Turn a proven pattern or debugging solution into a standalone reusable skill with SKILL.md, reference docs, and examples.
AI skills for your next project. Explore real workflows, with clear explainers and links to the people who built them.
skills to explore
PUBLIC SKILLS, ONE SEARCHABLE SHELFIndexed 25 Sep 2026 ↗
25–48 of 94 skills
Turn a proven pattern or debugging solution into a standalone reusable skill with SKILL.md, reference docs, and examples.
Adding, retiring, or auditing feature flags. Triggers on "add a flag", "ship behind a flag", "rollout plan", "kill switch", "stale flags", "flag debt", "LaunchDarkly", "GrowthBook", "Statsig", "Unleash", "Flipt", or any progressive-delivery question.
Fix failing or flaky Playwright tests.
Fix, debug, or make a specific feature/module/area work end-to-end.
Capture a full-page screenshot, long screenshot, or complete page capture of a web page. Handles SPA scroll containers, lazy-loaded images, and very tall pages via Chrome DevTools Protocol with zero external dependencies.
Generate Playwright end-to-end tests for web pages, components, and user interactions.
A user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use gh to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval.
Run parallel feature work safely with Git worktrees. Standardizes branch isolation, port allocation, environment sync, and cleanup so each worktree behaves like an independent local app.
Google Workspace administration via the gws CLI (github.com/googleworkspace/cli). Install, authenticate, and automate Gmail, Drive, Sheets, Calendar, Docs, Chat, and Tasks.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.
Docs-anchored grilling session — challenges a plan against the project's existing language (CONTEXT.md) and recorded decisions (docs/adr/), and updates those files inline as terminology and decisions crystallise.
Compact the current conversation into a handoff document for another agent to pick up. References existing artifacts (PRDs, plans, ADRs, issues, commits, diffs) by path or URL instead of duplicating them.
Create, repair, validate, visually QA, and package Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual references.
Orchestrate free opencode workers from Claude Code to cut token costs.
Create a new AgentHub collaboration session with task, agent count, and evaluation criteria.
Show DAG state, agent progress, and branch status for an AgentHub session.
Runs the human-verification lane of an agent loop, and proves review happened before work is called done.
Comprehensive incident response framework from detection through resolution and post-incident review.
Writing, reviewing, or committing code to enforce Karpathy's 4 coding principles — surface assumptions before coding, keep it simple, make surgical changes, define verifiable goals.
Designing, reviewing, or paying for an agent memory system — adding memory to an agent, choosing between long-context / RAG / graph / agentic memory, auditing what a CLAUDE.md or memory directory actually holds, deciding what to keep and what to expire, or when a memory store keeps growing and nobody has said what leaves it.
Analyze auto-memory for promotion candidates, stale entries, consolidation opportunities, and health metrics.
Memory health dashboard showing line counts, topic files, capacity, stale entries, and recommendations.
Merge the winning agent's branch into base, archive losers, and clean up worktrees.
Migrate from Cypress or Selenium to Playwright.
Source-linked, not execution-tested. Check the publisher’s setup instructions and permissions before use.