AI Skills
Installable SKILL.md packages that extend AI coding agents with reliable workflows and domain-specific judgment — ranked by installs, sourced from skills.sh.
lark-markdown
View, create, upload, edit and compare Markdown files in Lark Drive.
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns that infer design direction and avoid templated output.
caveman-commit
Ultra-compressed commit messages in Conventional Commits format—terse, exact, why-focused.
find-skills
Search every major skill registry at once to find the right agent skill for any task.
caveman-review
Ultra-compressed code review comments: location, problem, fix. One line per finding.
caveman-compress
Compress memory files into caveman-speak to save input tokens while preserving code and structure.
caveman-help
Quick-reference card for caveman modes, skills, and commands—display on demand.
lark-vc-agent
Real-time meeting participation and event monitoring for Lark video conferences.
impeccable
Design and iterate production-grade frontend interfaces with real working code and exceptional craft.
airunway-aks-setup
Set up AI Runway on AKS from bare cluster to running model in six steps.
systematic-debugging
Find root cause before fixing—systematic debugging prevents wasted effort and masked problems.
writing-plans
Create detailed implementation plans for multi-step tasks before writing code.
using-superpowers
Establish skill-first workflow—invoke relevant skills before any response, even with 1% applicability.
pptx
Create, read, edit, and manipulate PowerPoint presentations programmatically.
high-end-visual-design
Design like a $150k+ agency with premium fonts, haptic depth, and fluid motion—blocks cheap defaults.
redesign-existing-projects
Audit and upgrade existing websites to premium quality by eliminating generic AI patterns and applying high-end design standards.
vercel-react-native-skills
React Native and Expo best practices for performant mobile apps, animations, and native integrations.
seo-audit
Diagnose and fix SEO issues: crawlability, indexation, speed, mobile-friendliness, and technical foundations.
requesting-code-review
Dispatch a code reviewer subagent to catch issues before they cascade.
test-driven-development
Write tests first, watch them fail, then implement—the disciplined way to build reliable code.
minimalist-ui
Clean editorial-style interfaces with warm monochrome palette, typographic contrast, and flat bento grids.
Read, extract, merge, split, and create PDF files with Python and command-line tools.
cavecrew
Delegate to compressed subagents—investigator, builder, reviewer—to keep main context lean across long sessions.
caveman-stats
Display real token usage and estimated savings for your Claude Code session.
hyperframes
Router and entry skill for video authoring—renders video from HTML with intent-based workflow selection.
supabase
Complete Supabase backend integration for databases, auth, storage, and real-time features.
entra-agent-id
Provision OAuth 2.0-capable identities for AI agents with per-instance audit trails via Microsoft Entra and Microsoft Graph.
hyperframes-cli
CLI for HyperFrames video composition: scaffold, lint, validate, render locally or on AWS Lambda.
full-output-enforcement
Enforce complete, unabridged LLM output—no truncation, no placeholders, no shortcuts.
paper-context-resolver
Resolve reproduction-critical paper details when README and repo files leave gaps.