Agents
AI agents and automation
reviewing-prs
by Ataraxy-Labs
"Agent-powered GitHub PR reviews with smart semantic triage. Categorizes changes as MECHANICAL (skip), NEW LOGIC (read), or BEHAVIORAL (verify) — so agents never waste tokens reading lock files or formatting diffs. Includes remote file reading, text/AST search across PR or full repo, and comment posting. No local clone needed. Use when asked to review a PR, check a pull request, look at PR changes, or given a PR number/URL to review."
executing-workflow
by amogha-dalvi
Use when the user wants to execute a marketing skill workflow end-to-end. Triggers on "run the workflow", "execute reducing-cac", "run the CAC optimizer", or any request to execute a skill with a workflow-spec.yaml. This skill orchestrates multi-phase workflows with data connections, checkpoints, and structured outputs.
better-skill-review
by psylch
"Review a agent skill by combining automated linting with structured semantic analysis. Runs hard-rule validation, evaluates contextual findings, then performs deep review against best practices (description quality, workflow design, runtime robustness, script conventions, UX patterns). Produces actionable improvement suggestions with before/after examples. This skill should be used when reviewing a skill, validating skill structure, improving skill quality, checking skill conventions, or when the user says 'review skill', 'validate skill', 'check skill', 'improve skill', 'iterate on skill', '走查技能', '验证技能', '检查 skill', '改进技能', '优化 skill'."
gitops-apply
by meriley
Guide proper GitOps workflow for Kubernetes changes instead of direct kubectl mutations. Identifies resources, locates/creates manifests, commits to git, and syncs via ArgoCD/Flux. Use when kubectl mutation is blocked.
skill-factory
by lambda610
Create skills compatible with both OpenClaw and Claude Code (Agent Skills). Use when: (1) Building a new skill that supports dual platforms, (2) Need unified YAML frontmatter with proper validation. Not for: Single-platform skills that don't need cross-compatibility.
prompt-engineering
by LKB-99
"Use this skill for advanced prompt engineering techniques. Triggers: prompt engineering, chain-of-thought, few-shot learning, prompt optimization, otimização de prompt, engenharia de prompt."
chrome-webstore-release-blueprint
by iannuttall
Guide a user end-to-end through setting up Chrome Web Store API release automation in any repository. Use when asked to walk someone through OAuth/CWS credential setup, refresh token creation, local/CI secret setup, version-based publish automation, and submission status checks.
freshservice-manager
by krishagel
Manage Freshservice tickets, approvals, and get team performance reports across all workspaces
arcblock-context
by ArcBlock
Load ArcBlock company context (products, technical architecture, strategy) on demand. Use /arcblock-context to see available topics, or /arcblock-context <topic> to load specific context.
drupal-intent-testing
by scottfalconer
Exploratory, intent-focused UI testing for Drupal sites using the agent-browser CLI (accessibility-tree based; no vision model required). Use to “poke around like a human”: create/edit content, change module configuration, build Canvas pages, and verify the intended UX/output. Supports guided testing, seeded fuzz/monkey testing, and paired before/after comparisons with artifacts (snapshots, screenshots, console/errors).
multi-agent-composition
by basher83
This skill should be used when the user asks to "choose between skill and agent", "compose multi-agent system", "orchestrate agents", "manage agent context", "design component architecture", "should I use a skill or agent", "when to use hooks vs MCP", "build orchestrator workflow", needs decision frameworks for Claude Code components (skills, sub-agents, hooks, MCP servers, slash commands), context management patterns, or wants to build effective multi-component agentic systems with proper orchestration and anti-patterns guidance.
ai-agents-builder
by LKB-99
"Create autonomous AI agents with LangChain, AutoGPT, and CrewAI. Use this skill to build, customize, or deploy AI agents, intelligent applications, or multi-agent systems. Triggers: AI agent, autonomous agent, LangChain, AutoGPT, CrewAI, multi-agent system, agentic AI, criar agente de IA, agente autônomo."
new-project
by ApeWorX
Architect new Python-based blockchain projects using the Ape framework. Use when users want to start a new blockchain project and need guidance on proper project structure, architecture patterns, configuration, and foundational setup. Supports SDK development, plugin creation, bot development with Silverback, protocol development, and complex blockchain applications. Determines project type and guides users through establishing the correct architectural foundation.
code-reviewing
by taptap
AI 驱动的代码审查能力，当用户提到代码审查、code review、审查代码、查看代码质量等关键词时自动触发。使用 9 个并行 Agent 进行全维度分析（Bug/质量/安全/性能）。
obra-verification-before-completion
by faulkdev
Use before finalizing answers or PRs: confirm requirements met, run checks, and avoid “looks good” without evidence in VS Code Copilot Agent mode.
agent-evaluation
by eyadsibai
Use when evaluating agent performance, building test frameworks, measuring quality, or asking about "agent evaluation", "LLM-as-judge", "agent testing", "quality metrics", "evaluation rubrics", "agent benchmarks"
ctx:performance
by Shakes-tzd
Analyze and optimize parallel workflow performance. Use when users report slow parallel execution, want to improve speed, or need performance analysis. Activate for questions about bottlenecks, time savings, optimization opportunities, or benchmarking parallel workflows.
cruise-control
by jschulte
Automatic mode - shift through all 6 gears sequentially without stopping. Like cruise control or automatic transmission, this runs the entire StackShift workflow from analysis to implementation in one go. Perfect for unattended execution or when you want to let StackShift handle everything automatically.
gboy-character-selector
by austinatneuko
Select characters from the G*BOY universe for your OpenCLAW agent personality.
tool-design
by eyadsibai
Use when designing agent tools, creating tool descriptions, implementing MCP tools, or asking about "tool design", "agent tools", "tool descriptions", "MCP", "function calling", "tool consolidation"
skill-factory
by basher83
Research-backed skill creation workflow with automated firecrawl research gathering, multi-tier validation, and comprehensive auditing. Use when "create skills with research automation", "build research-backed skills", "validate skills end-to-end", "automate skill research and creation", needs 8-phase workflow from research through final audit, wants firecrawl-powered research combined with validation, or requires quality-assured skill creation following Anthropic specifications for Claude Code.
find-skills
by iannuttall
Find and install agent skills with npx playbooks find skill and npx playbooks add skill. Use whenever a skill needs to be discovered or installed.
ctx:architect
by Shakes-tzd
Systematic architecture analysis following Understand → Research → Specify → Decompose → Plan workflow. Use for system design, solution evaluation, build vs buy decisions, and task decomposition. Activate when users say "design", "architect", "break down", "best approach", or "should I build".
cursor-best-practices
by HKTITAN
"Best practices for using Cursor—rules, commands, skills, subagents, ignore files, Agent security, workflows, and community resources. Use when setting up Cursor, initializing or creating the .cursor folder, writing .cursor/rules or AGENTS.md, creating commands or skills, configuring .cursorignore, working with Agent, discovering rules or MCPs (e.g. cursor.directory), making codebases cursor-compatible, or asking about Cursor workflows, TDD, git commands, or large codebases."