Skills

A shared agent skill that produces structured pull request review feedback from local diff artifacts, part of Warp's common-skills collection of reusable development workflows.

Identifies and fixes web accessibility issues to meet WCAG guidelines, analyzing HTML, CSS, and JavaScript for compliance.

A shared agent skill that writes user-facing PRODUCT.md specification documents for features, part of Warp's common-skills collection of reusable spec workflow skills.

A shared agent skill that writes implementation-oriented TECH.md specification documents for features, part of Warp's common-skills collection of reusable spec workflow skills.

A shared agent skill that provides guidance for fixing build, lint, formatting, and test failures, part of Warp's common-skills collection of reusable development workflows.

A shared agent skill that provides a workflow and helper script for resolving git merge conflicts with compact context, part of Warp's common-skills collection of reusable development workflows.

A shared agent skill that implements approved PRODUCT.md and TECH.md specification files while keeping specs and code aligned, part of Warp's common-skills collection.

from remotion-dev/skills

A shared agent skill that provides guidance for preparing and opening pull requests, part of Warp's common-skills collection of reusable development workflows.

A shared agent skill that provides guidance for creating and maintaining skill directories and SKILL.md files, part of Warp's common-skills collection for skill authoring.

A shared agent skill that provides a workflow for inspecting GitHub CI failures and producing a fix plan, part of Warp's common-skills collection of reusable development workflows.

Safe, documented, reversible releases.

Automates browser interactions, debugging, and performance analysis using Chrome DevTools for comprehensive web page inspection and control.

Part of a shared collection of reusable agent skills for common development workflows, including spec writing, implementation planning, PR preparation, CI failure diagnosis, and merge conflict resolution across multiple repositories.

Production-grade engineering skills for AI coding agents that encode senior-engineer workflows, quality gates, and best practices across the full software development lifecycle from spec to shipping.

from ai-design-layers/agent-skills

Quality gates before merge.

A shared repository of reusable agent skills for cross-repo workflows, covering spec writing, PR creation, CI failure diagnosis, code review, merge conflict resolution, and skill authoring.

Transforms AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Features WAL Protocol for corrections, Working Buffer for context survival, and Compaction Recovery.

A production-grade agent skill from addyosmani/agent-skills that activates the /code-simplify command to guide AI agents toward clarity over cleverness when refactoring code.

Contact (通讯录) skill of the WeCom (企业微信) CLI — lets humans and AI agents fetch the visible-scope member list and search members by name or alias from the terminal via `wecom-cli contact ...` commands.

Small slices, right context, clean interfaces.

A Flutter animation skill from the MAD Agents Skills collection, providing structured knowledge on animation APIs, patterns, and best practices based on official Flutter documentation for AI-assisted development.

Automatically diagnoses and repairs broken OpenCLI adapters when a site's DOM, API, or response schema changes — only touches the adapter at `RepairContext.adapter.sourcePath`, enforces hard stops for AUTH_REQUIRED / BROWSER_CONNECT / CAPTCHA, a 3-round repair budget, and files an upstream GitHub issue after a verified fix.

Optimizes SQL query performance across all databases with indexing strategies, query tuning, and execution plan analysis.

Prove it works with tests and real browser data.

A Tavily skill that extracts clean markdown and text content from specific URLs, capable of handling JavaScript-rendered pages to provide agents with accurate web content for processing.

Xiaohongshu (小红书) title formula skill that picks the right formula from 75 verified viral templates across 12 psychological-trigger categories (cognitive conflict, curiosity gap, fear/loss, identity, number anchoring, outcome promise, social proof, controversy, context, call-to-action, authority, interaction). Generates 5–8 tailored titles per topic, each traceable back to a specific formula ID with the original viral reference and rationale.

A hand-maintained Claude Code skill by Anthony Fu encoding his personal preferences and best practices for ESLint, pnpm, Vitest, and Vue across app and library projects.

Diagnoses and resolves Vue 3 runtime errors, async failures, hydration issues, and common component debugging challenges.