Automation
Task automation and scripting
implement-with-remote-feedback
by Xalior
Git-centric implementation workflow. Enforces clean checkout, creates a properly named branch, tracks progress in a WIP markdown file, and commits/pushes continuously so remote git logs serve as the primary monitoring channel. Use when starting any plan-based implementation task.
codex-delegation
by DUTSTECH
How to delegate implementation tasks to workers via Codex MCP or Task sub-agents. Use when executing tasks that require code implementation.
autodream
by kirin1024
"启用 AutoDream —— OpenClaw 自动记忆维护。定期读取所有 Agent 的对话记录，用 4 阶段流程（ORIENT→GATHER→CONSOLIDATE→PRUNE）+ grep 模式匹配提取关键决策、偏好和项目进展，写入待审区供用户确认。适用场景：(1) 设置自动记忆整理，(2) 安装 Claude Code 风格的做梦机制，(3) 希望 Agent 跨会话记住对话内容。触发词：'安装 autodream'、'设置自动记忆'、'启用做梦'、'Claude Code 记忆自动化'。"
planning
by Alicoder001
Task decomposition, goal-oriented planning, and adaptive execution strategies for AI agents. Use when facing complex multi-step tasks that require structured approach.
State Machine Specialist
by Alpizar28
Especialista senior en diseño de máquinas de estado y flujos transaccionales, especializado en ciclos de vida de reservas y coherencia de estados.
harness-skill
by zhuiyi1472-lgtm
Use when designing, auditing, or refining an AI agent, skill system, or multi-tool harness where reliability, boundary clarity, tool routing, memory policy, scheduling, and failure handling matter more than raw autonomy. Also applies to requests about Agent/Skill/Workflow 边界、工具路由、事实校验、失败退路与 Eval 设计.
domain-skill-design
by maxoreric
v1.0.0 (2026-01-19): åå§çæ¬
airflow-dag-patterns
by ncdevshiv
"Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs."
context-driven-development
by TriNgo0108
Use this skill when working with Conductor's context-driven development methodology, managing project context artifacts, or understanding the relationship between product.md, tech-stack.md, and workflow.md files.
humanizer
by cgk-platform
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
litcoin-standalone-miner
by manteclaw
Autonomous LITCOIN ($LITCOIN) proof-of-research mining agent. Operates without Bankr dependency using direct Base L2 wallet signing with OpenRouter LLM inference. Earns LITCOIN by solving research tasks — agentic_trace, instruction_tuning, algorithm, smart_contracts. Auto-filters impossible tasks for your model tier. Free model friendly. Key difference from bankrbot/litcoin-miner: No Bankr API key required. Uses your own Base wallet + OpenRouter key directly.
hello-world
by kit101
[TODO: Complete and informative explanation of what the skill does and when to use it. Include WHEN to use this skill - specific scenarios, file types, or tasks that trigger it.]
resume-optimizer
by showlotus
技术简历要点优化工具。专为技术人员设计，将平淡的项目描述改写为符合大厂标准的简历要点。使用场景：(1) 用户提供技术工作描述需要改写为简历语言 (2) 用户明确要求优化简历内容 (3) 用户提供的描述需要符合 STAR 法则和专业表达 (4) 需要生成多个版本的简历话术供选择。输出标准专业版、数据驱动版和专家架构师版三种格式。
elixir-dependency-updater
by tylercannon
Update Elixir project dependencies including breaking changes. Use when the user asks to update dependencies in an Elixir project, upgrade packages, run mix hex.outdated, handle dependency version bumps and breaking changes, or asks to update mix.exs dependencies.
github-actions-workflow
by ehtbanton
Generate GitHub Actions workflow YAML files for CI/CD pipelines including testing, building, and deployment automation. Triggers on "create GitHub Actions workflow", "generate CI/CD pipeline", "GitHub workflow for", "actions yaml for".
uv-python-manager
by gemini960114
Use this skill when the user wants to manage Python projects, virtual environments, or dependencies using uv, including creating venvs, installing packages, syncing environments, or running Python tools.
Bash Script Skill Template
by Wesley1600
[list required utilities]
plan
by pmco23
Use after /review to transform the approved design into an atomic execution plan. Writes task groups with exact file paths, complete code examples, and named test cases with assertions. Build agents must never need to ask clarifying questions. Writes .pipeline/plan.md.
clarify
by diskd-ai
Clarify redmine task skill
speckit-analyze
by h3y6e
Perform cross-artifact consistency analysis across spec.md, plan.md,
baoyu-comic
by siatwangmin
Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and sequential image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".
google-adk-python
by brixtonpham
"Google Agent Development Kit (ADK) for Python. Capabilities: AI agent building, multi-agent systems, workflow agents (sequential/parallel/loop), tool integration (Google Search, Code Execution), Vertex AI deployment, agent evaluation, human-in-the-loop flows. Actions: build, create, deploy, evaluate, orchestrate AI agents. Keywords: Google ADK, Agent Development Kit, AI agent, multi-agent system, LlmAgent, SequentialAgent, ParallelAgent, LoopAgent, tool integration, Google Search, Code Execution, Vertex AI, Cloud Run, agent evaluation, human-in-the-loop, agent orchestration, workflow agent, hierarchical coordination. Use when: building AI agents, creating multi-agent systems, implementing workflow pipelines, integrating LLM agents with tools, deploying to Vertex AI, evaluating agent performance, implementing approval flows."
form-filling
by sitammeur
"Fill PDF and image forms using the Datalab Python SDK. Triggers: form filling, PDF forms, fillable documents, FormFillingOptions, batch fill forms."
are-you-ok
by C-QY
Print a structured status snapshot of the current agent session or active project. Agent mode: model, git, memory, tasks, tools, jobs. Project mode: project name/type, version, recent commits, changed files. Trigger — agent: "are you ok", "你还好吗", "状态怎么样", "汇报进度", "当前状态", !status. Trigger — project: "项目进度", "项目状态", "项目情况", "project status", "project progress". Output language: Chinese for CN triggers and "are you ok"; English otherwise.