deepline-plays-review
Use this skill when a human needs to review a Deepline Play result and hand feedback, labels, or approval back to the agent for revision, evaluation,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,648 results
worktree-pr-review
Finish standalone or recovery work from a dedicated git worktree by spawning a publishing sub-agent to commit, push, open a GitHub PR, then running…
agentic-workflows
Route gh-aw workflow design/create/debug/upgrade requests to the right prompts.
bigquery-ai-ml
Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform…
grey-haven-evaluation
Evaluate LLM outputs with multi-dimensional rubrics, handle non-determinism, and implement LLM-as-judge patterns. Essential for production LLM systems. Use…
grey-haven-plugin-audit
Comprehensive Claude Code plugin auditing skill for validating structure, detecting deprecated patterns, and recommending best practices based on the latest…
grey-haven-skill-creator
Guide for creating effective skills that extend Claude's capabilities. Use when users want to create a new skill, update an existing skill, or need guidance on…
grey-haven-suite-audit
Meta-level plugin suite auditor that uses subagents to analyze any plugin for usability improvements, missing agents, duplication, and workflow optimizations.…
intentline-audit
Audit exact frozen Intentline acceptance and original sources without editing or approving them.
intentline-plan
From one request, save and return a concise source-bound acceptance draft using your existing host and Intentline's offline CLI.
intentline-slice
Prefer NO SPLIT, or propose the smallest source-bound allocation of an existing Intentline parent without approving or delivering it.
ai-governance
AI governance, EU AI Act compliance, OWASP LLM security, responsible AI practices for GitHub Copilot agents
mcp-gateway-configuration
MCP gateway setup for multi-server integration, security configuration, tool routing, and access control
openclaw-skill-creator
Create OpenClaw-compatible skills with proper metadata, structure, and packaging. Use when building skills for OpenClaw agents, including: (1) Initializing new…
skill-compare
Compare two versions of a skill side-by-side. Shows metrics diff (satisfaction, tokens, corrections) and line-level changes between versions.
claud
What Claude can do and where (Chat, Claude Code, Code web, Cowork, Chrome), with the exact how. What Claude can do & where, across surfaces. Use /claud or…
ton-tact
Tact language for TON blockchain smart contracts — types, contracts, messages, send/receive, stdlib, and security.
agent-browser
Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web…
agent-browser
Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web…
agent-tools
Run AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance,…
The Standard Ethical Skill
The ethical constitution of an agent, the topmost immutable rules that bind every action, above every skill, tool, and memory. Duty of care and…
agents-pair
Pair with a peer AI agent. Use when the user asks to pair with Codex or Claude, delegate a scoped slice, request peer review, run an adversarial challenge,…
prompt-tuning
Methodology for iteratively improving agent-facing instructions (skills / slash commands / CLAUDE.md / code-gen prompts) by having a bias-free executor run…
acrobatics
Use this skill when the work is a choreography problem: brittle sequencing, async handoffs, or constrained flows that must stay upright end to end. It shines…