shadcn-management
Manage shadcn/ui components using MCP tools. Use when user needs to: (1) Add new shadcn components to a project (2) Build complex UI features requiring…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,653 results
stable-baselines3
Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating custom Gym environments,…
torch-geometric
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for…
accessibility-coverage-matrix
Build, refresh, report, or probe an accessibility coverage matrix across criteria, surfaces, and evidence methods. Use when assessing coverage with the…
engagement-report-council-critique
Run one independent Council critique against engagement-report research evidence. Use as the manual separate-session fallback when independent critic agents…
boot
Shorthand alias for the /promptkit skill. Use this when the user wants to assemble a task-specific prompt using PromptKit, or says "boot" to start the…
ax-practitioner
This skill should be used when the user asks about AX (agent experience) or the AX Practitioner Playbook, for example "how do I evaluate my technology's agent…
goal
Set, inspect, or control a durable goal — the agent keeps iterating across turns until the stop condition is met.
setup-task-tracking
Install Argo's standing task-tracking instruction into a project's agent-facing docs.
tooluniverse-connect
How to use ToolUniverse Connect (connect.aiscientist.tools), the hosted ToolUniverse service, and when to use it instead of ToolUniverse installed on this…
migrate-skill-agent
Find the skill or agent specified in skills-store, git pull it, and install it into the Claude/Codex skills/agents of the home directory or the current project.
mizchi-blog-style
Style guide and AI-smell criteria for writing and reviewing blog posts (zenn / dev.to, etc.) under the mizchi name. Includes a procedure for evaluating on both axes via subagent dispatch: "does it look like mizchi wrote it" and "does it smell like AI." Used in the revision iteration for style matching after drafting an article.
delegating-to-deepseek
Use DeepSeek for bounded, objective worker tasks when the work requires multi-step or cross-file search, repetitive inspection, large-output evidence…
moai-foundation-claude
Canonical Claude Code authoring kit covering Skills, sub-agents, plugins, slash commands, hooks, memory, settings, sandboxing, headless mode, and advanced…
moai-foundation-context
Manages context window optimization, session state persistence, and token budget allocation for multi-agent workflows. Use when dealing with token budget…
moai-ref-llm-security
AI/LLM defensive security reference: prompt-injection defense, OWASP LLM Top 10 defensive mapping, MCP and agentic tool-call hardening, training-data poisoning…
llm-cost-latency-budget
Model the cost and latency of an LLM feature before it ships and surprises the bill. Use when asked to estimate LLM API costs, set a latency/token budget,…
optimize-accuracy-first
Investigate performance bottlenecks and validate optimizations without weakening retrieval quality or correctness.
kelly-finance
Build, analyze, repair, and audit finance three-statement models and operating forecasts. Use when the user invokes $kelly-finance, asks for 财务三表, 三表模型, income…
kelly-invest-webull
Busabase-backed, read-only App-in-Skill portfolio dashboard that aggregates Webull brokerage holdings (accounts, positions, cash/margin, market value,…
kelly-launch
Product-launch command desk (Busabase App-in-Skill) built on the RAMP discipline — Research / Assemble / Mobilize / Prove. The agent assembles the launch…
mb-analysis
Optional Analysis before PRD: route vague ideas through facilitated brainstorming and a concise product brief without creating tasks.
pr-quiz
Use when a PR/MR explanation was just delivered (e.g. right after the explain-pr skill finishes) and the change was substantially agent-written, or whenever…
session-review
Review all AI sessions (Claude Code plus Codex) across one or more projects, and produce an interactive HTML report containing a skill usage ranking chart, a converged workflow diagram, how the user communicates with AI during feature development and debugging, repetitive processes that could be turned into custom skills, and for each suggestion whether it should go in user or project…