Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
ostikwhy-blip/claude-code-handoff-skill
Skill Claude CodeCodex
Use when ending or pausing a Claude Code session whose work must continue in a fresh session — user says "create a handoff", "write a handoff", "I'm ending this session", "prepare for a fresh session", "hand this off", or "/handoff" — or when starting a session in a project that already contains a HANDOFF.md at the…
Skill Claude CodeCodex
Run diagnostic scripts in sandbox with human approval (MCP tool).
Skill Claude CodeCodex
Create distinctive, production-grade HTML/CSS frontends with exceptional design quality.
Skill Claude CodeCodex
Audit a company's website from a buyer's perspective — positioning, funnel, proof, and differentiation. Use when user says 'audit this site', 'review my website', 'marketing audit', 'homepage critique', 'site teardown', 'why isn't my site converting', 'what does my site say about us', or 'what does a visitor see in 5…
Skill Claude CodeCodex
The framework's single design engine: craft-first selection of an intentional visual direction, a stable token system, and UI continuity across screens. A blank designskill resolves to it; only a project-forged skill (site-forge or hybrid output) that designskill names explicitly replaces it. Never combined with…
Skill Claude Code
Use when: executing or resuming one nearest evidence-backed bounded work-pack task or SWU end to end, or routing explicit until-blocker series intent to its owning spell.
Skill Claude CodeCodex
Add WhatsApp as a chat channel for the agent, routing inbound WhatsApp messages into the chat engine and replies back out. Use when the user wants to talk to the bot over WhatsApp, set up a WhatsApp number, or bridge WhatsApp into the existing multi-platform chat interface.
Skill Claude CodeCodex
/xdev-full-dev [--no-menxia] [--skip-design].
Skill Claude CodeCodex
Keep notes, memories, plans, to-dos, and documents in SurrealFS — a persistent filesystem the user can read too. Use when you learn something worth remembering, when you produce anything the user should be able to open later, or before writing a file so it lands in the right folder.
Skill Claude CodeCodex
How to work inside an ai-pod container — running commands on the host and adjusting the container environment.
Skill Claude CodeCodex
Index and search code repositories, documentation, research papers, HuggingFace datasets, local folders, Slack workspaces, Google Drive, X (Twitter), and packages with Nia AI. Includes auth bootstrapping, Oracle autonomous research, GitHub live search, Tracer agent, dependency analysis, context sharing, code advisor…
Skill Claude CodeCodex
Use when working with naive-ui components, or troubleshooting naive-ui usage issues.
Skill Claude CodeCodex
Use to inventory and risk-classify every API key and user-managed service-account key across all accessible GCP projects. READ-ONLY — does not mutate cloud state. Use standalone, or as Phase 1a of the gcp-ironclad driver.
Koomook/claude-skill-youtube-kr-subtitle
Skill Claude Code
Download YouTube videos, extract English subtitles, translate them to Korean using Claude's own translation capabilities (with video context and web search), and burn Korean subtitles into the video. Use this skill when the user requests Korean subtitle insertion for YouTube videos or asks to translate YouTube content…
Skill Claude Code
Scan Dockerfile(s) in the current directory and generate a draft app.yaml for the gateway app store.
Skill Claude CodeCodex
Validates and scores SKILL.md files against the agentskills.io specification; use when linting skills for cross-agent compatibility, description quality, or capability graph structure.
Skill Claude CodeCodex
Inject secrets into subprocesses via environment variables. You never see secret values — authy run injects them directly. Use for any command that needs API keys, credentials, or tokens.
Skill Claude CodeCodex
Use when extracting a codebase's implementation decisions into Metatron with an LLM/agent instead of metatron ingest — authoring candidate decisions as Open Knowledge Format (OKF) markdown files locally for review.
Skill Codex
Use when studying, reverse-engineering, comparing, reviewing, or learning from AI skill packages, SKILL.md files, Claude/Codex skills, prompt workflows, or agent playbooks; use when the user wants reusable skill design patterns, a keep/cut review, Markdown report, structured pattern notes, or multi-page web handbook.…
Skill Claude Code
Add a new agent (tool) support to agent-command-sync following the registry pattern.
Skill Claude CodeCodex
Task management patterns and best practices for the gur CLI tool.
Skill Claude CodeCodex
Complete Run402 onboarding for a managed Buzz agent with a dedicated wallet/public identity link, report independent human-adoption and community-installation state, offer bounded per-agent enrollment before provisioning, and stop only at a real approval or repair boundary. Use when a managed Buzz user says "install…
Skill Claude CodeCodex
Helps debug Python errors and exceptions.
TSS-Blue-AI-Lab/ai-lab-agent-skills
Skill Claude CodeCodex
Optimize an agent skill through bounded repeated trials, binary evaluations, targeted prompt mutations, and auditable keep/discard decisions. Use when asked to optimize, benchmark, evaluate, or systematically improve an existing skill. Produces an improved candidate skill, run artifacts, a results log, and a mutation…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: