Prompts
Prompt engineering and templates
claude-docs-consultant
by Zpankz
Consult official Claude Code documentation from docs.claude.com using selective fetching. Use this skill when working on Claude Code hooks, skills, subagents, MCP servers, or any Claude Code feature that requires referencing official documentation for accurate implementation. Fetches only the specific documentation needed rather than loading all docs upfront.
multi-model-meta-analysis
by petekp
Synthesize outputs from multiple AI models into a comprehensive, verified assessment. Use when: (1) User pastes feedback/analysis from multiple LLMs (Claude, GPT, Gemini, etc.) about code or a project, (2) User wants to consolidate model outputs into a single reliable document, (3) User needs conflicting model claims resolved against actual source code. This skill verifies model claims against the codebase, resolves contradictions with evidence, and produces a more reliable assessment than any single model.
manual-testing
by petekp
Guide users step-by-step through manually testing whatever is currently being worked on. Use when asked to "test this", "verify it works", "let's test", "manual testing", "QA this", "check if it works", or after implementing a feature that needs verification before proceeding.
shape-up
by petekp
Guided Shape Up workflow for taking projects from idea to working software. Orchestrates the /shaping and /breadboarding skills through a structured process: Frame, Shape, Breadboard, Slice, Build. Works for both greenfield (0-1) and existing projects. Use when: starting a new project or feature, planning a significant change to an existing codebase, user says "shape this", "let's shape", "shape up", or wants to go from idea to implementation with structured problem/solution separation. Proactively guides each phase and suggests next steps.
hwpx_writer
by leedonwoo2827-ship-it
"마크다운 텍스트 또는 MD 파일을 proposal-styles.json 스타일이 적용된 HWPX 한글 문서로 변환하는 MCP 스킬."
component
by Zpankz
Generate syntactically correct Claude Code configuration components (commands, subagents, skills, output styles) with optimal cross-component integration. Triggers on requests to create slash commands, agents, subagents, skills, output styles, Claude Code plugins, agentic workflows, or multi-agent pipelines. Ensures parameter validity per component type and semantic coherence across component references.
record-todos
by petekp
Enter todo recording mode to capture ideas without acting on them. Use when the user says "record todos", "let's capture some todos", "brainstorm mode", or wants to dump ideas without immediate execution. Captures thoughts to .claude/todos/, then organizes and prioritizes on exit.
agent-evaluation
by Zpankz
Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.
delegate-router
by Zpankz
Unified router for agent delegation and skill routing. Absorbs agents-router + skills-router. Triggers on complex tasks, multi-step operations, research, exploration, or specialized skill needs.
Documentation Management Skill
by Zpankz
BAIME Methodology
agent-observability
by Zpankz
Real-time observability dashboard for multi-agent Claude Code sessions. Visualize agent interactions, tool usage, and session flows in real-time through a web dashboard. Track multiple agents running in parallel with swim lane visualization, event filtering, and live charts. Key Features: - 🔴 Real-time event streaming via WebSocket - 📊 Agent swim lanes showing parallel execution - 🔍 Event filtering by agent, session, event type - 📈 Live charts for tool usage patterns - 💾 Filesystem-based (no database required) Inspired by @indydevdan's work on multi-agent observability. Our approach: Filesystem + in-memory streaming vs. indydevdan's SQLite database approach.
baoyu-danger-gemini-web
by xuanxuan1983
Image generation skill using Gemini Web. Generates images from text prompts via Google Gemini. Also supports text generation. Use as the image generation backend for other skills like cover-image, xhs-images, article-illustrator.
Edit Image
by b-open-io
This skill should be used when the user asks to "edit an image", "modify a photo", "inpaint", "outpaint", "extend an image", "replace object in image", "add element to image", "resize image for social media", "crop image", "adapt image for Twitter", "convert image to OG format", or needs AI-powered image editing with masks.
gepa-demo
by raveeshbhalla
Guide users who want to optimize their LLM prompts. We will interact with them, understanding their datasets and grader requirements, and finally writing DSPy code to optimize their prompt (using a custom implementation of the GEPA algorithm).
cache-audit
by ussumant
Audit your Claude Code setup against prompt caching best practices. Checks ordering, tool stability, dynamic content handling, and hook injection patterns. Returns a scored report with specific fixes.
evaluation-harness
by patricio0312rev
Builds repeatable evaluation systems with golden datasets, scoring rubrics, pass/fail thresholds, and regression reports. Use for "LLM evaluation", "testing AI systems", "quality assurance", or "model benchmarking".
cost-latency-optimizer
by patricio0312rev
Reduces LLM costs and improves response times through caching, model selection, batching, and prompt optimization. Provides cost breakdowns, latency hotspots, and configuration recommendations. Use for "cost reduction", "performance optimization", "latency improvement", or "efficiency".
prompt-template-builder
by patricio0312rev
Creates reusable prompt templates with strict output contracts, style rules, few-shot examples, and do/don't guidelines. Provides system/user prompt files, variable placeholders, output formatting instructions, and quality criteria. Use when building "prompt templates", "LLM prompts", "AI system prompts", or "prompt engineering".
langchain-workflow-builder
by patricio0312rev
Builds LLM applications with LangChain including chains, agents, memory, tools, and RAG pipelines. Use when users request "LangChain setup", "LLM chain", "AI workflow", "conversational AI", or "RAG pipeline".
prompt-regression-tester
by patricio0312rev
Compares old vs new prompts across test cases with diff summaries, stability metrics, breakage analysis, and fix suggestions. Use for "prompt testing", "A/B testing prompts", "prompt versioning", or "quality regression".
llm-debugger
by patricio0312rev
Diagnoses LLM output failures including hallucinations, constraint violations, format errors, and reasoning issues. Provides root cause classification, prompt fixes, tool improvements, and new test cases. Use for "debugging AI", "fixing prompts", "quality issues", or "output errors".
create-meta-prompts
by cfircoo
Create optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages. Use when building prompts that produce outputs for other prompts to consume, or when running multi-stage workflows (research -> plan -> implement).
git
by cfircoo
Git operations for committing, pushing, and opening PRs using gh CLI. Use when performing version control tasks.
generate-images
by cfircoo
Generate and edit images using Nano Banana (Google Gemini image generation). Use whenever Claude Code needs to create new images, edit existing images, generate icons, diagrams, mockups, or any visual content.