Parallel Review by Independent Specialist Models. Multi-agent review protocol that deploys 5+ specialist reviewers in parallel to eliminate confirmation bias...
Install, authenticate, and use Claude Code CLI as a native coding tool for any OpenClaw agent system.
Build, deploy, and host websites for free with full CMS. Create a live website from scratch, deploy it to the cloud with free hosting, free SSL, and custom d...
Helps teams achieve WCAG 2.1 AA compliance by auditing and guiding inclusive design for web, mobile, desktop, and other digital products.
16 production-hardened patterns for OpenClaw agents. WAL Protocol, anti-hallucination, ambiguity gate, compaction survival, QA gates, multi-agent handoffs, s...
Format commit message theo Conventional Commits standard (Conventional Commits v1.0.0). Input là git diff hoặc mô tả thay đổi, output là commit message có ty...
Call real humans to test your product (URL or app). Get structured usability feedback with screen recordings, NPS scores, and AI-aggregated findings.
Autonomously inspects a live OpenClaw instance across 5 health domains (hardware, config, security, skills, autonomy) and delivers a quantified traffic-light...
Universal release workflow. Auto-detects version files and changelogs. Supports Node.js, Python, Rust, Claude Plugin, and generic projects. Use when user say...
Beamer LaTeX slide workflow: create, compile, review, and polish academic presentations. Use this skill whenever the user works on Beamer .tex slide decks, o...
The master coordinator for AI skills. Discovers skills from multiple sources (SkillsMP.com, SkillHub, and ClawHub), manages installation, and synchronization...
Use when executing implementation plans with independent tasks in the current session. Features domain-specialist routing, independent verification gates, an...
--- name: swiftlint emoji: "\U0001F9F9" requires: swiftlint install: brew install swiftlint description: Swift linting and style enforcement via CLI --- # SwiftLint Enforce Swift style and conventio
Standardized Git commit message templates using changelog-style categories. Use when creating Git commits with structured format - Added (new features), Chan...
The complete operating system for building software with AI. From first prompt to production deployment — prompting frameworks, architecture patterns, testin...
General-purpose AI workflow framework for OpenClaw. Build custom multi-step workflows for any task — dev, ops, research, content, or automation. Ships with dev workflow examples.
Final code review and quality gate — run tests, check coverage, audit security, verify acceptance criteria from spec, and generate ship-ready report. Use whe...
Product changelog and release notes that users actually read. Covers categorization, user-facing language, visuals, and distribution. Use for: release notes,...
All-in-One AI creation: images (SeeDream 4.5, Midjourney, Nano Banana 2), videos (Wan 2.6, Kling, Veo 3.1, Sora, Pixverse, Hailuo, SeeDance, Vidu), music (Su...
Deep code audit + documentation sync + release preparation for Python packages. Use when preparing a release, checking code quality before publishing, auditi...
Generates a detailed receipt of everything you accomplished in a coding session — files changed, problems solved, decisions made, debt incurred, and what's l...
Pre-ingestion verification for epistemic quality in RAG systems. Ensures documents are properly qualified before entering knowledge bases. Produces CGD (Clar...
When users encounter OpenClaw-related issues or errors, search official docs and GitHub issues first, then provide solutions. Use for: feature malfunctions,...
Your agent says 'done' — but did it check? Superpowers turns any OpenClaw agent into a disciplined engineer. Verification iron law (evidence before claims),...