Context & AI engineering
25,815 rows, by stacks then stars
1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid
s-hiraoku/synapse-a2a/.agents/skills/synapse-a2a Skill
no license19★ repoSynapse A2A agent communication -- sending messages, spawning agents, delegating tasks, sharing memory, managing the LLM wiki, and coordinating file edits. Use this skill when: running synapse send/reply/broadcast/interrupt, spawning agents with synapse spawn or synapse team start, sharing knowledge with synapse memory, managing wiki pages with synapse wiki, locking files with synapse file-safety, checking agent status with synapse list/status, or orchestrating any multi-agent workflow. For AI/programmatic use, prefer synapse list --json, synapse status <target> --json, or the MCP list_agents tool instead of interactive synapse list.
s-hiraoku/synapse-a2a/.agents/skills/synapse-manager Skill
no license19★ repoMulti-agent management workflow — task delegation, progress monitoring, quality verification with regression testing, feedback delivery, and cross-review orchestration. Use this skill when coordinating multiple agents on a shared task, monitoring delegated work, ensuring quality across agent outputs, or implementing a multi-phase plan (3+ phases or 10+ file changes).
s-hiraoku/synapse-a2a/plugins/synapse-a2a/skills/anthropic-skill-creator Skill
no license19★ repoDesign, review, and improve Claude/Codex skills based on Anthropic's "The Complete Guide to Building Skills for Claude". Use when creating a new skill, rewriting SKILL.md frontmatter and workflows, fixing under-triggering or over-triggering, designing scripts/references/assets, building test cases, or preparing a skill for upload/distribution.
s-hiraoku/synapse-a2a/plugins/synapse-a2a/skills/skill-creator Skill
no license19★ repoCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update 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.
s-hiraoku/synapse-a2a/plugins/synapse-a2a/skills/synapse-a2a Skill
no license19★ repoSynapse A2A agent communication -- sending messages, spawning agents, delegating tasks, sharing memory, managing the LLM wiki, and coordinating file edits. Use this skill when: running synapse send/reply/broadcast/interrupt, spawning agents with synapse spawn or synapse team start, sharing knowledge with synapse memory, managing wiki pages with synapse wiki, locking files with synapse file-safety, checking agent status with synapse list/status, or orchestrating any multi-agent workflow. For AI/programmatic use, prefer synapse list --json, synapse status <target> --json, or the MCP list_agents tool instead of interactive synapse list.
s-hiraoku/synapse-a2a/plugins/synapse-a2a/skills/synapse-manager Skill
no license19★ repoMulti-agent management workflow — task delegation, progress monitoring, quality verification with regression testing, feedback delivery, and cross-review orchestration. Use this skill when coordinating multiple agents on a shared task, monitoring delegated work, ensuring quality across agent outputs, or implementing a multi-phase plan (3+ phases or 10+ file changes).
Lykhoyda/ask-llm/io.github.Lykhoyda/ask-llm MCP server
19★ repoUnified MCP server — auto-detects Gemini, Codex, Claude, Ollama, and Antigravity providers
chrisallenlane/claude-swe-workflows/skills/pre-compact Skill
18★ repoPre-compaction housekeeping. Walks a checklist (persistent memory updates, git hygiene, trash cleanup) plus an open-judgment audit, produces an SBAR with a go/no-go recommendation, and emits a copy-pasteable resume prompt for the post-compaction agent if work remains. Run this immediately before /compact.
The same file is in 2 other repositories
wei18/apple-dev-skills/collaboration-skills/skills/agent-impl-notes-log Skill
18★ repoMaintain a running `meetings/{date}_{topic}.impl-notes.md` *during* subagent task execution to capture in-flight design decisions, intentional deviations from spec, considered alternatives, and open questions for Leader/User. Distinct from the post-hoc phase meeting log; this file is updated incrementally as decisions are made. Invoke at the start of any non-trivial subagent dispatch, when ambiguity is encountered mid-task, or when about to deviate from spec.
wei18/apple-dev-skills/collaboration-skills/skills/claude-skill-plugin-packaging Skill
18★ repoHow to distribute Claude Code skills for reuse across repos and how to install them — as a plugin via a marketplace, a pinned git-submodule with committed project-scope settings, or globally. Covers the depth-1 discovery rule (why a bare folder/submodule of skills is NOT found), the `settings.json` schema, aggregating other skill repos, and the gotchas. Invoke when sharing skills across projects, wiring a skill plugin into a repo, choosing flat-skills vs plugin, or asked "why aren't my submodule'd skills showing up / how do I install project skills".
Leader developer handoff contract
wei18/apple-dev-skills/collaboration-skills/skills/leader-developer-handoff-contract Skill
18★ repoWhen the main agent dispatches a sub-agent, the prompt MUST include 5 elements — (1) task scope with verifiable target, (2) files / docs the sub-agent should read, (3) explicit skill list to invoke, (4) expected return format (diff / markdown section / decision text), (5) verification criteria. Invoke when about to dispatch a sub-agent (Developer / Designer / Code Reviewer), writing the dispatch prompt, or when asked "what should the sub-agent prompt include".
wei18/apple-dev-skills/collaboration-skills/skills/skill-authoring-patterns Skill
18★ repoReusable Claude Code skills for AI-agent-driven Swift / Apple-platform development — composable via git submodule; aggregates other specialist skill repos
wei18/apple-dev-skills/collaboration-skills/skills/spec-phase-orchestration Skill
18★ repoThe pre-implementation document pipeline — 5 files + `meetings/` directory (README.md + docs/design.md + docs/foundations.md + docs/plan.md + docs/methodology.md + meetings/), section-by-section approval (§What before §How), prerequisite checklist with Unconfirmed / Resolved gates, "no implementation code before design.md and plan.md approved" rule. Invoke when starting a new project that needs spec-first development, deciding doc structure, or when asked "which documents go in the spec phase".
wei18/apple-dev-skills/collaboration-skills/skills/subagent-conflict-detection Skill
18★ repoUse before dispatching a subagent (especially `isolation:"worktree"`) to avoid three dispatch hazards — file-scope overlap with an in-flight subagent, a stale dispatch base, and collisions with another live agent/session editing the same checkout or git-submodule path. Invoke when about to call the Agent tool with `isolation:"worktree"`; when another subagent is running; right after a merge or branch switch (verify the dispatch base first); or when another Claude session is editing a shared repo/submodule path.
wei18/apple-dev-skills/collaboration-skills/skills/subagent-review-cycles Skill
18★ repoThe Leader / Developer / Code-Reviewer triad pattern — Leader dispatches Developer for proposal → Code Reviewer for adversarial review (with WebSearch, no CLI) → Leader accepts/rejects with specific reasons → iterate up to `limit(N)` rounds. Round-1 cosmetic-grade fixes get inline-applied by Leader instead of consuming a round. Invoke when planning multi-round review on a document, dispatching a Code Reviewer subagent, or when asked "how many review rounds / what skills should the Code Reviewer carry".
mahmoud20138/Tradecraft/plugins/tradecraft/skills/ai-agent-builder Skill
18★ repoExpert guide for building AI-powered coding agents that produce professional-quality output. Trigger whenever the user asks to build an AI agent, coding assistant, automation pipeline, tool-using LLM system, or says "agent", "agentic", "tool use", "function calling", "LLM pipeline", "AI workflow", "coding bot", or "autonomous AI". Covers agent architecture, tool design, skill loading, prompt engineering, context management, evaluation loops, and multi-step orchestration using the Claude API or any LLM API.
mahmoud20138/Tradecraft/plugins/tradecraft/skills/autohedge-swarm Skill
18★ repoAutoHedge — enterprise-grade autonomous hedge fund using swarm agent architecture. Sequential pipeline: Director → Quant → Risk Manager → Execution agents. Risk-first design: position sizing before any trade execution. Currently supports Solana; Coin
mahmoud20138/Tradecraft/plugins/tradecraft/skills/brain-ecosystem-mcp Skill
18★ repoBrain Ecosystem — 3 autonomous self-learning AI brains as MCP servers for Claude Code. Brain (280 tools): error memory, code intelligence, autonomous research. Trading Brain (181 tools): adaptive trading, paper trading, signal learning, backtesting.
mahmoud20138/Tradecraft/plugins/tradecraft/skills/claude-automation-recommender Skill
18★ repoAnalyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.
mahmoud20138/Tradecraft/plugins/tradecraft/skills/claude-md-improver Skill
18★ repoAudit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project memory optimization".
mahmoud20138/Tradecraft/plugins/tradecraft/skills/context-memory Skill
18★ repoPersist and recall state between skill invocations. Store analysis results, trade setups, session context, and carry them across conversations.
mahmoud20138/Tradecraft/plugins/tradecraft/skills/few-shot-quality-prompting Skill
18★ repoMaster guide for crafting prompts that make AI models produce professional-quality code and UI consistently. Trigger whenever the user asks about prompt engineering, improving AI output quality, building system prompts, few-shot examples, making AI write better code, prompt optimization, or says "how to prompt", "better results", "improve output", "stop getting slop". Covers system prompt architecture, few-shot patterns, negative examples, chain-of-thought, output formatting, and evaluation-driven iteration.
mahmoud20138/Tradecraft/plugins/tradecraft/skills/hook-development Skill
18★ repoThis skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.
mahmoud20138/Tradecraft/plugins/tradecraft/skills/mcp-integration Skill
18★ repoThis skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
mahmoud20138/Tradecraft/plugins/tradecraft/skills/multi-strategy-orchestration Skill
18★ repoPipeline for running multiple trading strategies simultaneously. Signal arbitration, conflict resolution, capital allocation per strategy, risk aggregation, and regime switchover logic. The brain that coordinates all strategy agents. USE FOR: multi-strategy, strategy orchestration, signal conflict, strategy pipeline, run multiple strategies, strategy coordination, risk aggregation, portfolio heat, regime switchover, strategy agent, trading pipeline, strategy conflict resolution, how to combine strategies, which strategy wins, signal weighting.
mahmoud20138/Tradecraft/plugins/tradecraft/skills/openalice-trading-agent Skill
18★ repoOpenAlice — experimental file-driven autonomous AI trading agent running locally. "Your research desk, quant team, trading floor, and risk manager on your laptop 24/7." Uses "Trading-as-Git" workflow (stage → commit → push to execute). Natively integ
mahmoud20138/Tradecraft/plugins/tradecraft/skills/polymarket-prediction-agents Skill
18★ repoAI agent framework for autonomous trading on Polymarket prediction markets. Connects LLMs to Polymarket's DEX via Gamma API, supports RAG with Chroma DB, integrates news/betting/web-search data sources. Uses py-clob-client for on-chain order executio
mahmoud20138/Tradecraft/plugins/tradecraft/skills/ritmex-crypto-agent Skill
18★ reporitmex-ai-trader — multi-agent crypto trading research platform for Binance. Automated market data ingestion, PineScript-based technical analysis, signal generation, risk management, and compliance reporting. Built on Bun (TypeScript). Agents: data p
mahmoud20138/Tradecraft/plugins/tradecraft/skills/trading-agents-llm Skill
18★ repoMulti-agent LLM trading framework that mirrors real-world trading firm dynamics. Specialized agents (Fundamentals, Sentiment, News, Technical analysts + Researcher debate + Trader + Risk Manager) collaborate to analyze markets and make trading decisi
Chipagosfinest/enterprise-team/enterprise-team/skills/handoff-protocol Skill
no license18★ repoTransport-neutral Interaction Records and risk-class evidence bundles for agent-to-agent communication. Replaces ad-hoc handoffs with a single canonical artifact that works identically in Agent Teams mode (via SendMessage) and fallback mode (via Task prompts). Triggers: handoff, hand off, pass to, route to, transfer, quality gate, QA review, escalate, sprint boundary, incident, phase gate, consultation, peer review, capability request, risk classification, scope expansion.
rudderlabs/rudder-agent-skills/plugins/rudder-mcp/skills/rudder-mcp-setup Skill
18★ repoConfigures Claude Code to connect to RudderStack's MCP server at mcp.rudderstack.com. Use when setting up MCP for rudderstack, connecting claude to rudderstack, or configuring the rudderstack MCP server
rudderlabs/rudder-agent-skills/plugins/rudder-mcp/skills/rudder-mcp-workflow Skill
18★ repoConnects AI agents to RudderStack via MCP tool calls for catalog, sources, destinations, transformations, and live events. Use when connecting an AI agent to RudderStack's MCP server, driving RudderStack via MCP, or mentions of mcp.rudderstack.com.
Suggest awesome github copilot instructions
archubbuck/workspace-architect/assets/plugins/awesome-copilot/skills/suggest-awesome-github-copilot-instructions Skill
18★ repoSuggest relevant GitHub Copilot instruction files from the awesome-copilot repository based on current repository context and chat history, avoiding duplicates with existing instructions in this repository, and identifying outdated instructions that need updates.
The same file is in 1 other repository
Suggest awesome github copilot prompts
archubbuck/workspace-architect/assets/plugins/awesome-copilot/skills/suggest-awesome-github-copilot-prompts Skill
18★ repoSuggest relevant GitHub Copilot prompt files from the awesome-copilot repository based on current repository context and chat history, avoiding duplicates with existing prompts in this repository, and identifying outdated prompts that need updates.
Suggest awesome github copilot skills
archubbuck/workspace-architect/assets/plugins/awesome-copilot/skills/suggest-awesome-github-copilot-skills Skill
18★ repoSuggest relevant GitHub Copilot skills from the awesome-copilot repository based on current repository context and chat history, avoiding duplicates with existing skills in this repository, and identifying outdated skills that need updates.
The same file is in 1 other repository
Remember interactive programming
archubbuck/workspace-architect/assets/plugins/clojure-interactive-programming/skills/remember-interactive-programming Skill
18★ repoA micro-prompt that reminds the agent that it is an interactive programmer. Works great in Clojure when Copilot has access to the REPL (probably via Backseat Driver). Will work with any system that has a live REPL that the agent can use. Adapt the prompt with any specific reminders in your workflow and/or workspace.
The same file is in 1 other repository
archubbuck/workspace-architect/assets/plugins/copilot-sdk/skills/copilot-sdk Skill
18★ repoBuild agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or creating custom agents. Triggers on Copilot SDK, GitHub SDK, agentic app, embed Copilot, programmable agent, MCP server, custom agent.
The same file is in 2 other repositories
archubbuck/workspace-architect/assets/skills/claude-api Skill
18★ repoReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).
The same file is in 2 other repositories
archubbuck/workspace-architect/assets/skills/mcp-builder Skill
18★ repoGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
The same file is in 42 other repositories
archubbuck/workspace-architect/assets/skills/skill-creator Skill
18★ repoCreate 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.
The same file is in 66 other repositories
KirKruglov/claude-skills-kit/skills/prompts-and-memory/memory-auditor-chat Skill
18★ repoAudit and clean up Claude's native memory in Claude.ai: find contradictions, outdated entries, duplicates, and noise across all memory layers. Adapts scope to the current context (general chat / project). Trigger with: audit memory, check memory, memory audit, clean up memory, review memory, memory health check, what's in my memory, аудит памяти, проверь память, почисти память, разбери память, ревью памяти, что у меня в памяти.
KirKruglov/claude-skills-kit/skills/prompts-and-memory/memory-auditor-cowork Skill
18★ repoAudit and clean up Claude's file-based memory in Cowork: find contradictions, outdated entries, duplicates, and noise across auto-memory, CLAUDE.md, User Preferences, and Project Instructions. Adapts scope to the current Cowork environment. Trigger with: audit memory, check memory, memory audit, clean up memory, review memory, memory health check, what's in my memory, аудит памяти, проверь память, почисти память, разбери память, ревью памяти, что у меня в памяти.
KirKruglov/claude-skills-kit/skills/prompts-and-memory/prompt-builder Skill
18★ repoInteractive structured prompt generator for Claude based on the user's task description. Asks 7 questions and assembles a ready-to-use prompt from a universal template. EN triggers: 'create a prompt', 'write a prompt', 'prompt builder'. RU triggers: 'создай промпт', 'напиши промпт', 'prompt builder'.
KirKruglov/claude-skills-kit/skills/prompts-and-memory/prompt-library-curator Skill
18★ repoOrganize and tag your personal prompt collection into a structured markdown catalog with an index table. Use when you have accumulated saved prompts and want to structure, deduplicate, and label them for reuse. Triggers: 'organize my prompts', 'prompt library', 'tag my prompts', 'structure my prompt collection', 'организуй мои промпты', 'библиотека промптов', 'структурируй промпты'.
KirKruglov/claude-skills-kit/skills/sessions-and-context/context-window-health-check Skill
18★ repoAssess the health of your current Claude session context and get a clear action recommendation — no technical metrics needed. Use when your session feels long, Claude seems to be forgetting earlier details, or you are unsure whether to continue or start fresh. Triggers: 'check my context', 'context health check', 'is my context running out', 'should I start a new session', 'проверь мой контекст', 'оценка контекста', 'контекст заканчивается'.
KirKruglov/claude-skills-kit/skills/sessions-and-context/session-handoff-composer Skill
18★ repoCompose a structured handoff document when your chat session fills up. Extracts decisions, in-progress tasks, open questions, and next steps into a ready-to-paste block for a new session. Triggers: 'compose handoff', 'session handoff', 'составь хэндофф', 'подготовь handoff-документ'.
KirKruglov/claude-skills-kit/skills/team-leadership/delegation-brief Skill
18★ repoInteractive skill for Cowork that generates a structured delegation brief by asking the user up to 5 targeted questions: what to do, expected result, files involved, what not to touch, and success criteria. Outputs a ready-to-use task instruction for a new Cowork session. Use when delegating tasks to an AI assistant, structuring a vague request, or preparing clear instructions before starting work. Triggers RU: «бриф», «составь бриф», «помоги делегировать», «структурируй задачу». Triggers EN: 'brief', 'delegation brief', 'help me delegate', 'structure my task'.
martinemde/skillet/testdata/claude-spec-skill Skill
18★ repoA skill demonstrating all Claude Code spec fields.
pariyar07/ariadne/skills/vault Skill
18★ repoBootstrap an agentic Markdown knowledge vault for projects, research, learning, life systems, and other long-running knowledge work. Use when creating a new vault, installing the base folder structure, templates, AGENTS.md, CLAUDE.md, Agent navigation files, and optional Obsidian-compatible Bases.
pariyar07/ariadne/skills/workspace-instructions Skill
18★ repoCreate or update workspace-level instruction files for code repositories or ordinary project folders, including AGENTS.md, CLAUDE.md, GEMINI.md, local override files, and Ariadne vault-link blocks. Use when a user wants to initialize, repair, or refresh workspace instructions, connect a workspace to a registered Ariadne vault or scope, or make instructions portable across Codex, Claude Code, Gemini CLI, and other agent runtimes without duplicating global discovery.
JinNing6/Noosphere/shared_skills/active/agent-debug-memory Skill
18★ repoUse when debugging code, tests, builds, deployments, CI failures, runtime errors, framework issues, API migrations, or UI state bugs where a coding Agent should consult Noosphere shared memory before fixing and upload the verified lesson afterward.
JinNing6/Noosphere/shared_skills/active/upload-debug-memory Skill
18★ repoUse after resolving a bug, test failure, build failure, CI issue, deployment issue, or framework/API pitfall when the verified lesson should be published to Noosphere for future agents.
JinNing6/Noosphere/shared_skills/releases/1.0.0/agent-debug-memory Skill
18★ repoUse when debugging code, tests, builds, deployments, CI failures, runtime errors, framework issues, API migrations, or UI state bugs where a coding Agent should consult Noosphere shared memory before fixing and upload the verified lesson afterward.
JinNing6/Noosphere/shared_skills/releases/1.0.0/upload-debug-memory Skill
18★ repoUse after resolving a bug, test failure, build failure, CI issue, deployment issue, or framework/API pitfall when the verified lesson should be published to Noosphere for future agents.
JinNing6/Noosphere/shared_skills/releases/1.0.1/upload-debug-memory Skill
18★ repoUse after resolving a bug, test failure, build failure, CI issue, deployment issue, or framework/API pitfall when the verified lesson should be published to Noosphere for future agents.
arvindand/agent-skills/skills/maven-tools Skill
18★ repoJVM dependency intelligence via Maven Tools MCP server. Use when the user asks about Maven or Gradle dependencies, safe upgrades, CVEs, license risks, release history, or project dependency health. Use when reviewing `pom.xml`, `build.gradle`, `build.gradle.kts`, or Maven coordinates. Use when the user says 'check my dependencies', 'should I upgrade X', 'what can I safely bump', or 'is this version safe'. Use even when the user just pastes a `groupId:artifactId` coordinate without a verb.
shinpr/rashomon/skills/prompt-optimization Skill
18★ repoAnalyzes and optimizes prompts using BP-001~009 patterns and a gated 3-step flow. Use when "optimize this prompt", "review prompt quality", "analyze prompt issues", or creating/reviewing rashomon skill content.
shinpr/rashomon/skills/recipe-eval-prompt Skill
18★ repoCompares original and optimized prompts through repeated blind paired execution in git worktrees. Use when evaluating prompt improvement effects or learning prompt engineering through concrete examples.
shinpr/rashomon/skills/recipe-eval-skill Skill
18★ repoCreates or updates Claude Code skills through interactive dialog, then evaluates effectiveness with sequential paired comparisons. Use when creating new skills, updating existing skills, or evaluating skill quality.
shinpr/rashomon/skills/worktree-execution Skill
18★ repoGit worktree management for isolated parallel prompt execution. Use when creating isolated environments for prompt comparison or managing worktree lifecycle. Provides creation, cleanup, and orphan detection scripts.