Prompts
Prompt engineering and templates
hook-management
by melodic-software
Central authority for Claude Code hooks management in this repository. Automates enforcement of critical repository rules through hooks. Use when adding hooks, managing hooks, configuring hooks, troubleshooting hooks, or understanding hook behavior. Delegates to docs-management skill for official hooks documentation. Provides organization-specific patterns, configuration management, and workflow guidance.
audit-hooks
by melodic-software
Audit Claude Code hooks for quality, compliance, and maintainability. Use after creating hooks, before releases, or for periodic quality checks.
audit-rules
by melodic-software
Audit Claude Code rule files for quality and compliance. Use when creating or validating .claude/rules/*.md files, or troubleshooting rule loading issues.
audit-memory
by melodic-software
Audit Claude Code CLAUDE.md memory files for quality, compliance, and organization. Use to validate import syntax, detect circular imports, and check hierarchy compliance.
hook-schema-audit
by melodic-software
Audit hook event schema for drift. Compares implementation against official docs.
audit-output-styles
by melodic-software
Audit Claude Code output styles for quality, compliance, and usability. Use when creating custom styles or validating existing ones.
audit-docs-delegation
by melodic-software
Audit skills and memory files for docs-management delegation compliance. Detects hardcoded Claude Code data and verifies proper delegation patterns.
claude-desktop
by melodic-software
Central authority for Claude Desktop application - the native desktop app for running Claude Code sessions. Covers installation (macOS/Windows), Git worktrees for parallel sessions, .worktreeinclude file configuration, cloud session launch, environment configuration, MCP Desktop Extensions (.mcpb), and Desktop vs CLI comparison. Assists with Desktop setup, worktree configuration, cloud sessions, and troubleshooting. Delegates 100% to docs-management skill for official documentation.
clear-plugin-cache
by melodic-software
Clear cached plugin copies (requires reinstall after)
improve-prompt
by melodic-software
Improve and optimize prompts using Anthropic's 4-step prompt improvement workflow
agent-sdk-development
by melodic-software
Central authority for Claude Agent SDK (TypeScript and Python SDKs). Covers SDK installation, authentication (Anthropic key, Bedrock, Vertex), sessions and resumption, forking sessions, streaming vs single mode, custom tools, permissions (allowedTools, disallowedTools, permissionMode), MCP integration, system prompts (CLAUDE.md, appendSystemPrompt, outputStyle), cost tracking, todo tracking, structured outputs, hosting patterns, plugins, and SDK branding guidelines. Assists with building custom agents, configuring SDK options, and troubleshooting SDK issues. Delegates 100% to docs-management skill for official documentation.
create-skill
by melodic-software
Create new skill scaffold with required structure. Use when starting a new skill from scratch or need proper YAML frontmatter template.
bpmn-generator
by Stieges
Enterprise BPMN 2.0 diagram generator — converts natural language process descriptions into OMG-compliant BPMN 2.0 XML files and SVG previews via a 4-phase pipeline: Intent Extraction (LLM → JSON Logic-Core) → Validation (deadlock detection, structural soundness) → ElkJS Auto-Layout → BPMN XML + SVG output. Supports: multi-pool collaborations, message flows, boundary events (timer/error/signal), loop/multi-instance markers, data objects, all gateway types with correct gatewayDirection, and all BPMN 2.0 task types. Use this skill whenever the user wants to create, generate, or model a BPMN diagram, process flow, or workflow — even if they say "draw a process", "model this workflow", "make a BPMN for...", "create a Prozessmodell", "visualize this process", or describe a business process in natural language. Also use for editing or extending existing BPMN Logic-Core JSON.
forge
by saadshahd
Create a persistent expert agent file. Use when "create an agent", "make an agent", "design an agent", "forge an agent", "agent for [task]", "I need a specialist", "build a [role] agent".
observe
by saadshahd
On-demand codebase health check. Use when "observe", "health check", "is the codebase healthy", "check for drift", "system status", or before starting a large feature.
consumption-tax
by kazukinagata
This skill should be used when the user needs to calculate consumption tax (消費税) or determine their tax method (2割特例, 簡易課税, or 本則課税). Trigger phrases include: "消費税を計算", "消費税の申告", "消費税申告書", "2割特例", "簡易課税", "本則課税", "課税売上", "消費税額", "インボイス", "みなし仕入率", "課税仕入".
ask
by doodledood
Single-model consultation using consultant agent. Defaults to gpt-5.2-pro.
update-claude-md
by doodledood
Create or update CLAUDE.md with best practices - brevity, universal applicability, progressive disclosure
optimize-prompt-token-efficiency
by doodledood
'Iteratively optimizes prompts for token efficiency by maximizing information density - reduces verbosity, removes redundancy, tightens phrasing while preserving semantic content. Use when asked to compress, shorten, reduce tokens, tighten, maximize density, increase information density, or make a prompt more concise.'
solo-factory
by fortunto2
Install the full Solo Factory toolkit — 23 startup skills + solograph MCP server for code intelligence, KB search, and web search. Use when user says "install solo factory", "set up solo", "install all solo skills", "startup toolkit", or "solo factory setup". This is the one-command entry point for the entire startup pipeline.
solo-scaffold
by fortunto2
Generate complete project from PRD + stack template — directory structure, configs, CLAUDE.md, git repo, and GitHub push. Use when user says "scaffold project", "create new project", "start new app", "bootstrap project", or "set up from PRD". Uses SoloGraph for patterns and Context7 for latest versions. Do NOT use for planning features (use /plan) or PRD generation (use /validate).
ask-council
by doodledood
Multi-model ensemble consultation. Runs 3 models in parallel for diverse perspectives.
prompt-engineering
by doodledood
'Craft or update LLM prompts from first principles. Use when creating new prompts, updating existing ones, or reviewing prompt structure. Ensures prompts define WHAT and WHY, not HOW.'
auto-optimize-prompt
by doodledood
'Iteratively auto-optimize a prompt until no issues remain. Uses prompt-reviewer in a loop, asks user for ambiguities, applies fixes via prompt-engineering skill. Runs until converged.'