Agent Workflow Claude Skills
4 122 agent workflow skills from 665 authors. They configure the agents themselves: memory, prompts, context and other skills. Half of them fit into 1 844 tokens or less — that is what one costs your context window when the agent loads it. 778 ship runnable scripts rather than instructions alone. 5 of them cannot work without an MCP server, most often task. We also found 589 copies of these same skills sitting in other people's repositories — counted once here, not 589 times.
4 122 unique 665 authors 4 updated this month 506 from vendors
Replace with description of the skill and when Claude should use it.
Generates a repo-specific orientation.md resource for the learning-opportunities skill. Only invoke via slash command (/orient:orient). Do not trigger automatically.
When the user wants to improve their app's star rating, increase ratings volume, optimize when and how they prompt users for a review, or recover from a bad rating period. Use when the user mentions "app rating", "star rating", "review prompt", "SKStoreReviewRequest", "In-App Review API", "ask for review", "low rating", "rating drop", "get more reviews", or "recover from 1-star". For responding to reviews, see review-management. For overall ASO health, see aso-audit.
>- Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
> Creates new AI agent skills following the Agent Skills spec.
Skill for creating auth layers in TypeScript/JavaScript apps using Better Auth.
INVOKE THIS SKILL at the START of any LangChain/LangGraph/Deep Agents project, before writing any agent code. Determines which framework layer is right for the task: LangChain, LangGraph, Deep Agents, or a combination. Must be consulted before other agent skills.
INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2) Defining Run Functions - how to capture outputs and trajectories from your agent; (3) Running Evaluations - locally with evaluate() or auto-run via LangSmith. Uses the langsmith CLI tool.
Optimizes AI skills for activation, clarity, and cross-model reliability. Use when creating or editing skill packs, diagnosing weak skill uptake, reducing regressions, tuning instruction salience, improving examples, shrinking context cost, or setting benchmark/release gates for skills. Trigger terms: skill optimization, activation gap, benchmark skill, with/without skill delta, regression, context budget, prompt salience.
Foundational "High-Density" standard for token-optimized agent instructions and CLI-based automated activation.
Techniques to maximize context window efficiency, reduce latency, and prevent 'lost in middle' issues through strategic masking and compaction. (triggers: *.log, chat-history.json, reduce tokens, optimize context, summarize history, clear output)
Analyze conversation corrections to detect skill gaps and auto-improve the skills library. Use after any session with user corrections, rework, or retrospective requests. (triggers: **/*.spec.ts, **/*.test.ts, SKILL.md, AGENTS.md, retrospective, self-learning, improve skills, session review, correction, rework)
Standards for creating, testing, and optimizing Agent Skills for any AI Agent (Claude, Cursor, Windsurf, Copilot). Use when: writing SKILL.md, auditing a skill, improving trigger accuracy, checking size limits, structuring references/, writing anti-patterns, starting a new skill from scratch, or reviewing skill quality.
Techniques to maximize context window efficiency, reduce latency, and prevent 'lost in middle' issues through strategic masking and compaction.
Expert standards for session drivers, security headers, and middleware logic. Use when configuring session drivers, security headers, or custom middleware in Laravel. (triggers: app/Http/Middleware/**/*.php, config/session.php, session, driver, handle, headers, csrf)
Analyze conversation corrections to detect skill gaps and auto-improve the skills library. Use after any session with user corrections, rework, or retrospective requests.
Standards for creating, testing, and optimizing Agent Skills. Use when creating, improving, catching regressions, measuring trigger rates, or writing eval cases for any skill.
Build Codex-native workflows for open-source maintenance. Use when creating AGENTS.md guidance, maintainer skills, issue triage flows, PR review prompts, release-note routines, or repository verification scripts.
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
>- Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects. Each step has a self-contained context brief so a fresh agent can execute it cold. Includes adversarial review gate, dependency graph, parallel step detection, anti-pattern catalog, and plan mutation protocol. complex multi-PR task, or describes work that needs multiple sessions. than 3 tool calls, or user says "just do it".
通过Claude DevFleet协调多智能体编码任务——规划项目、在隔离的工作树中并行调度智能体、监控进度并读取结构化报告。
Interactive installer for Everything Claude Code — guides users through selecting and installing skills and rules to user-level or project-level directories, verifies paths, and optionally optimizes installed files.
Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.
Operate long-lived agent workloads with observability, security boundaries, and lifecycle management.
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.
Pattern for progressively refining context retrieval to solve the subagent context problem
使用Node/TypeScript SDK构建MCP服务器——工具、资源、提示、Zod验证、stdio与可流式HTTP对比。使用Context7或官方MCP文档获取最新API信息。
>- Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. "how to write a prompt for", "help me prompt", "rewrite this prompt", or explicitly asks to enhance prompt quality. Also triggers on Chinese "just do it" / "直接做". DO NOT TRIGGER when user says "优化代码", "优化性能", "optimize performance", "optimize this code" — those are refactoring/performance tasks, not prompt optimization.
Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.
Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines
Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.
A comprehensive verification system for Claude Code sessions.
Use when testing agent without context validation
Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. Validates agent configuration files against 230 rules.
Use when testing context without agent validation
Use when testing invalid agent validation