skill-creator
Create, edit, and package skills that extend Claude's capabilities with specialized knowledge, workflows, or tool integrations. This skill should be used when…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,657 results
pm-deep-talk
Use when: The user already has a product idea, proposal, plan, or set of options to choose from, and wants to analyze pros and cons, sort out selection criteria, fill in key considerations, or get decision advice The user explicitly asks to "talk in depth," "analyze this proposal," "help me sort out the trade-offs," or "how should I choose" After selecting a direction in pm-brainstorm, the user proactively asks to further discuss its feasibility and trade-offs Do NOT use when: …
act-when-ready
Stop Claude Fable 5 / 5.1 from over-planning, re-deriving settled facts, or surveying options it will never pursue. Use in any interactive or agentic session…
effort-calibrator
Choose and tune the effort setting for Claude Fable 5 / 5.1 workloads. Use whenever the user asks which effort level to use ("what effort should this batch job…
skill-refactorer
Audit and rewrite existing agent skills, system prompts, and CLAUDE.md files for Claude Fable 5 / 5.1. Use whenever the user mentions migrating, upgrading,…
krea-core
Shared Krea agent contract and router. Use first for Krea tasks to apply Krea's core tone, avoid overthinking simple generation requests, and route to…
browser
Automates and inspects live web pages using agent-browser CLI — navigate, screenshot, check console errors, analyze network, measure performance, diff pages,…
kubesense-apm
Query and analyze distributed traces (APM) from Kubernetes clusters using KubeSense MCP tools. Covers field discovery, raw span search, latency/error analysis,…
plan-eng-review
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues…
lancedb
Use when writing, reviewing, debugging, or documenting LanceDB pipelines in Python or TypeScript, especially code that should work across local LanceDB OSS…
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…
mcp server management
Install and configure Model Context Protocol (MCP) servers for Claude Code projects. Use when you want to add or enable an MCP server, connect a tool or…
agent-authority-charter-builder-arkadiy-miteiko
Creates an Agent Authority Charter for enterprise or regulated AI agents before deployment. Use this Skill when a user needs to define what an AI agent is…
epistemic-fault-line-audit-ignacio-adrian-lerer
Audits legal AI outputs, prompts, skills, workflows and MCP/tool instructions for fluent but unsupported reasoning, missing evidence, overconfidence, hidden…
irac-prompt-stephane-boghossian
Restructure any rough build, research, or legal-drafting request into an IRAC-shaped prompt — Issue, Rule, Analysis, Conclusion — optimized for a frontier…
lawve-agentic-delegation-audit-ignacio-adrian-lerer
Use when a lawyer, legal team, or client needs to assess AI agents that can act on someone's behalf: send messages, search, draft, file, pay, delete, connect…
legal-analysis-forge-oliver-schmidt-prietz
EU Digital Regulation Legal Analysis Forge — generates a tailored expert prompt for structured legal analysis of an EU digital-regulation document, optionally…
runtime-admissibility-review
Determines whether a specific AI-agent action, output, recommendation, or proposed commitment remains admissible for execution or institutional reliance under…
action-continuity-choreography-by-15zo1bq
Apply an evidence-derived Action continuity choreography workflow observed across published GoodCase examples by itxabdullaa. Use when planning, storyboarding,…
lwy-prompt-optimizer
Use this skill on every user message that contains a prompt or AI instruction — analyze its weaknesses and suggest improvements before executing. Score across…
dspy-codeact
Build agents that write and execute Python code using dspy.CodeAct. Use when the task requires computation, data transformation, or multi-step logic better…
dspy-rlm
Recursive Language Model (dspy.RLM) that explores large contexts via a sandboxed Python REPL -- the LM writes code, queries sub-LMs, and iterates until it…
dspy-simba
Optimize a DSPy program in small conservative steps using dspy.SIMBA (Stochastic Introspective Mini-Batch Ascent). Use when your program already works and you…
dspy-tools
Wraps Python functions as dspy.Tool objects and configures dspy.PythonInterpreter for sandboxed code execution in DSPy agents. Use when you need to give DSPy…