Loading...
Loading...
Found 1,281 Skills
Effective communication strategies for AI-assisted development. Learn context-first prompting, phased interactions, iterative refinement, and validation techniques to get better results from Claude and other AI coding assistants.
Authoritative meta-skill for creating, auditing, and improving Agent Skills. Combines skill-coach expertise with skill-creator workflows. Use for skill creation, validation, improvement, activation debugging, and progressive disclosure design. NOT for general Claude Code features, runtime debugging, or non-skill coding.
Configure a repo's agent instruction files (AGENTS.md, CLAUDE.md, etc.) to auto-apply Devvit skill guidance. Trigger phrases: "configure skills", "setup skills", "add devvit docs rule".
Track Clawdbot AI model usage and estimate costs. Use when reporting daily/weekly costs, analyzing token usage across sessions, or monitoring AI spending. Supports Claude (opus/sonnet), GPT, and Codex models.
Helps Claude Code understand Sui blockchain keypair and cryptography operations, providing guidelines and examples for key generation, signing, verification, address derivation, and multi-signature scheme support. Use when working with cryptography in Sui development or when the user mentions keypairs, cryptography, signing, or verification.
Helps Claude Code understand Sui blockchain's BCS (Binary Canonical Serialization) encoding, providing usage guidelines and examples for primitive types, composite types, Sui-specific types, serialization patterns, and transformation support. Use when working with BCS serialization in Sui development or when the user mentions BCS, binary serialization, or Move data encoding.
Helps Claude Code understand Sui blockchain transaction building, providing guidelines and examples for Transaction class, commands, input types, gas configuration, and serialization. Use when building blockchain transactions on Sui or when the user mentions transaction building, Transaction class, or Move calls.
Docusaurus build health validation and deployment safety for Claude Skills showcase. Pre-commit MDX validation (Liquid syntax, angle brackets, prop mismatches), pre-build link checking, post-build health reports. Activate on 'build errors', 'commit hooks', 'deployment safety', 'site health', 'MDX validation'. NOT for general DevOps (use deployment-engineer), Kubernetes/cloud infrastructure (use kubernetes-architect), runtime monitoring (use observability-engineer), or non-Docusaurus projects.
Model Context Protocol expert for building MCP servers, tools, resources, and client integrationsUse when "mcp server, model context protocol, claude code extension, building ai tools, tool definition, mcp transport, stdio transport, sse transport, resource provider, prompt template, mcp, model-context-protocol, claude-code, ai-tools, llm-integration, anthropic, server, protocol" mentioned.
Use this skill when the user asks to "humanize this text", "make this sound less like AI", "fix AI writing patterns", "make this more natural", "rewrite to sound human", or mentions AI-sounding text, robotic writing, or Claude-speak.
Jira API operations via Python CLI scripts. AUTOMATICALLY TRIGGER when user mentions Jira URLs (https://jira.*/browse/*, https://*.atlassian.net/browse/*), issue keys (PROJ-123), or asks about Jira issues. Use when Claude needs to: (1) Search issues with JQL queries, (2) Get or update issue details, (3) Create new issues, (4) Transition issue status (e.g., "To Do" → "Done"), (5) Add comments, (6) Log work time (worklogs), (7) List sprints and sprint issues, (8) List boards and board issues, (9) Create or list issue links, (10) Discover available Jira fields, (11) Get user profile information, (12) Download attachments from issues. If authentication fails, offer interactive credential setup via jira-setup.py. Supports both Jira Cloud and Server/Data Center with automatic auth detection.
Analyzes and improves LLM prompts and agent instructions for token efficiency, determinism, and clarity. Use when (1) writing a new system prompt, skill, or CLAUDE.md file, (2) reviewing or improving an existing prompt for clarity and efficiency, (3) diagnosing why a prompt produces inconsistent or unexpected results, (4) converting natural language instructions into imperative LLM directives, or (5) evaluating prompt anti-patterns and suggesting fixes. Applies to all LLM platforms (Claude, GPT, Gemini, Llama).