steel-skill-creator
Use this skill when the user wants to turn a recurring browser workflow into a reusable, parameterized agent skill, especially when the task has concrete…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-17 00:11
Agents & models
23,994 results
behavioral-modes
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
unsloth
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
gsd-ai-integration-phase
Generate an AI-SPEC.md design contract for phases that involve building AI systems.
gsd-manager
Interactive command center for managing multiple phases from one terminal
exploring-llm-costs
Investigate LLM spend in PostHog — total cost over time, cost by model, provider, user, trace, or custom dimension, token and cache-hit economics, and cost…
afk-loop
How the team runs AFK agents — which work to hand to Copilot versus Claude Code, what makes a complete agent brief, how to review the pull request that comes…
parallel-agents
Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires…
gsd-eval-review
Audit an executed AI phase's evaluation coverage and produce an EVAL-REVIEW.md remediation plan.
gsd-ultraplan-phase
[BETA] Offload plan phase to Claude Code's ultraplan cloud; review in browser and import back.
feature-usage-feed
Set up an LLM-judge evaluation that extracts canonical use cases for a PostHog feature at scale and streams the results to a Slack channel as a live feed. Use…
agent-workflow
Use when any Maestro command is invoked — provides foundational workflow design principles across prompt engineering, context management, tool orchestration,…
genmedia-workflow
Design and execute multi-step media workflows with genmedia. Use this for pipelines that combine planning, generation, editing, image or video utilities,…
team-live-ops
Orchestrate the live-ops team — live-ops-designer, economy-designer, analytics-engineer, community-manager, writer — for a season or live event.
vault-cleanup-auditor
Audit your Obsidian vault in Claude Code — finds stale drafts, empty folders, duplicate filenames, and incomplete files. Saves a dated report.
aris-autonomous-ml-research
Autonomous ML research workflows using ARIS (Auto-Research-In-Sleep) — Markdown-only skills for cross-model paper review, idea discovery, experiment automation, and paper writing with Claude Code, Codex, or any LLM agent.
mobile-audit
Audit iOS and Android mobile applications against OWASP MASVS / MASTG — insecure storage, weak crypto, certificate pinning, deeplinks, IPC, jailbreak/root…
outlines
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize…
anthropic-claude-code-extend
Reference for Claude Code (code.claude.com) extensions. Agent Skills (SKILL.md), slash commands, output styles, subagents, agent teams, agent view, workflows, routines,…
openai-agents
Build AI applications with OpenAI Agents SDK - text agents, voice agents, multi-agent handoffs, tools with Zod schemas, guardrails, and streaming. Prevents 11…
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring…
agent-dx-cli-scale
A scoring scale for evaluating how well a CLI is designed for AI agents, based on the "Rewrite Your CLI for AI Agents" principles.
resource-scout
Search and discover Claude Code skills and MCP servers from marketplaces, GitHub repositories, and registries. Use when (1) user asks to find skills for a…
auto-updater
Automatically apply improvements to skills and the ecosystem based on system-reviewer findings and best-practices-learner insights. Workflow for automated…