Prompts
Prompt engineering and templates
aiconfig-variations
by launchdarkly
Guide for experimenting with AI configurations. Helps you test different models, prompts, and parameters to find what works best through systematic experimentation.
planner
by solatis
Interactive planning and execution for complex tasks. IMMEDIATELY invoke when user asks to use planner.
skill-creator
by boisenoise
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Music Faculty — Expression
by acnlabs
Instrumental for ambiance â Use --instrumental for background mood music
prompt-engineering
by sabahattinkalkan
Comprehensive prompt engineering framework for designing, optimizing, and iterating LLM prompts. Use when creating prompts, optimizing existing prompts, or improving AI instructions.
ralph-loop
by belumume
Activate autonomous Ralph Wiggum loop mode for iterative task completion. Use when you have a well-defined task with clear completion criteria that benefits from persistent, autonomous execution.
docx-template-filling
by belumume
Fill DOCX template forms preserving 100% original structure - logos, footers, styles, metadata. Zero-artifact insertion. Output indistinguishable from manual entry.
rlm-orchestrator
by belumume
Implement RLM-style (Recursive Language Model) orchestration for complex tasks. This skill should be used when facing large context requirements, multi-part tasks that would benefit from parallel execution, or when context rot is a concern. Automatically decomposes tasks, spawns parallel subagents, aggregates results, and iterates until completion. Inspired by the RLM research paper (arXiv:2512.24601).
skill-creator
by ynulihao
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 capabilities with specialized knowledge, workflows, or tool integrations.
ai-discovery-expert
by nguyenthienthanh
"AI Discovery and LLM search optimization expert. PROACTIVELY use when optimizing for Perplexity, ChatGPT Search, Gemini, Claude, AI crawlers. Triggers: AI search, Perplexity, ChatGPT, AI discovery, LLM citation"
visual-pixel-perfect
by nguyenthienthanh
"Pixel-perfect visual testing with auto-fix loop. Implement → Render → Snapshot → Compare → Fix until pass."
stitch-design
by nguyenthienthanh
Generate UI designs using Google Stitch AI with optimized prompts
chapter3-guide
by orientpine
"Chapter 3 (사업 목표 및 추진 전략) 작성 가이드 - 템플릿 및 요구사항 통합"
financial-metrics-analysis
by OctagonAI
Analyze year-over-year growth in income statement items and financial metrics using Octagon MCP. Use when retrieving YoY Revenue Growth, Cost of Revenue Growth, Gross Profit Growth, Operating Income Growth, Net Income Growth, or comparing financial performance across fiscal periods for any public company.
company-market-cap
by OctagonAI
Retrieve market capitalization data for a single company using Octagon MCP. Use when you need the current market value, valuation context, or size classification for any publicly traded stock.
gif-splitter
by isjiamu
GIF动图切分工具，将超过指定帧数的GIF文件自动拆分成多个小文件。适用于微信公众号等平台上传GIF时遇到"帧数超限"的问题。
Sweep all disciplines
by melodic-software
"Compose this plugin's discipline correctors into ONE batched pass — requires conversation-inheriting fork subagents (subagent_type: fork); when fork mode is unavailable the skill emits SWEEP-ALL: DEGRADED (fork-unavailable) and runs the posture digest only (no audits, no corrections, no inline sequential fallback). At conversation start it instead reports a cheap posture digest (which disciplines are in scope) with no audit. Use when: 'sweep all disciplines', 'ground ourselves', 're-anchor everything', 'run the whole re-anchor bundle', 'posture batch', 'set our posture before we start', 'batch the correctors', or at conversation start to set posture across every standing discipline at once. Membership is each corrector's own tier metadata; for a single discipline, invoke that corrector directly."
claude-code-plugins
by melodic-software
"Verify the computer-use plugin's prerequisites and report the environment settings that end a screen-control session mid-run. Use when: 'set up computer use', 'is computer use working', 'why did my computer use session die', 'check computer use', 'computer use preflight', or before a long unattended screen-control run. Action: check (read-only, default) — probes the surface, the tool availability, and the idle/screensaver/sleep timeouts that no amount of Claude activity can hold off, then reports PASS/FAIL/INFO with one remediation line each. Check-only by contract: every prerequisite is external or a system setting this plugin must not write."
claude-code-plugins
by melodic-software
"Validate the discipline plugin's configuration — the posture-batch overlay and do-your-research-deep's verification depth — and explain how to change it through Claude Code's plugin configuration prompt. Use when: 'set up discipline', 'configure discipline', 'discipline setup', 'is discipline configured', 'set up re-anchor', 'configure re-anchor', 're-anchor setup', 'is re-anchor configured', 'what's in my posture batch', 'what's my deep-research depth', or you want to adjust which correctors the batch runs or how deeply the research fan-out verifies. Actions: check (read-only verification, default and only action — this plugin's entire configuration is native userConfig, so there is nothing an apply could write)."
claude-agent-sdk-ruby
by ya-luotao
Use when writing or refactoring Ruby code that integrates Claude Code via the claude-agent-sdk gem (ClaudeAgentSDK.query, ClaudeAgentSDK::Client, streaming input, ClaudeAgentOptions configuration including global defaults via ClaudeAgentSDK.configure, tools/permissions, MCP servers, hooks, structured output, budgets, sandboxing, betas/tools presets, control-timeout handling, session resumption/rewind, and Rails patterns like jobs or ActionCable).
agent-native-architecture
by petekp
Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.
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.
capture-learning
by petekp
Analyze recent conversation context and capture learnings to project knowledge files (for project-specific insights) or skills/commands/subagents (for cross-project patterns). Use when the user asks to "capture this learning", "update the docs with this", "remember this for next time", "document this issue", "add this to CLAUDE.md", "save this knowledge", or "update project knowledge". Also triggers after resolving build/setup issues, discovering non-obvious patterns, or completing debugging sessions with valuable insights.
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.