Automation
Task automation and scripting
w05-task-closure
by qiao-925
任务收尾规范，包含日志生成和优化分析。适用于主要交付完成后的收尾阶段。
spark
by memcoai
Use when the user encounters bugs, errors, or unexpected behavior. Also use when the user mentions "why isn't this working," "getting an error," "this should work but doesn't," debugging issues, library conflicts, version problems, API issues, or configuration problems. Queries collective knowledge from other AI agents who have solved similar problems.
Script.Powershell.7 Skill Entry
by PadtGit
Use AGENTS.md for the repo-local maintenance flow, PLANS.md for the standing ExecPlan rules, and plan.md as the current worked example when you need a living plan. Use docs/sysadmin-main-multi-agent-sop.md for extended notes. Use docs/windows-sandbox-validation.md for both the disposable manual Sandbox shell and the automated -WhatIf capture wrapper. Keep the repo-local entrypoints and .github/workflows/powershell-validation.yml aligned when the validation flow changes.
browser-use
by Jackiexiao
自动进行浏览器交互，以进行Web测试、表单填充、屏幕截图和数据提取。当用户需要浏览网站、与网页交互、填写表单、截屏或从网页中提取信息时使用。
webapp-testing
by zhongjis
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
agentic-actions-auditor
by aleister1102
"Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. Use when reviewing workflow files that invoke AI coding agents, auditing CI/CD pipeline security for prompt injection risks, or evaluating agentic action configurations."
Cariboo Signals — Technical Reference
by zirnhelt
RSS reader: Inoreader free edition
dataforseo-merchant-api
by leonardo-picciani
Collect marketplace and product intelligence with DataForSEO Merchant for "price monitoring", "product research", and "seller analysis".
moses-user-testing
by christopheraaronhogg
Enables Masterbuilder to conduct UX testing using artisans as user personas. After implementation, artisans embody different user types to verify the work from real-world perspectives.
index-skill
by relunctance
会话上下文快照 — 每次新会话开始时输出当前目标/任务/进度索引，让 AI 快速恢复上下文
proxmox-ops
by eddygk
Ops-focused Proxmox VE management via REST API — monitor, control, provision, and troubleshoot VMs and LXC containers with battle-tested operational patterns. Use when asked to: - List, start, stop, restart VMs or LXC containers - Check node status, cluster health, or resource usage - Create, clone, or delete VMs and containers - Manage snapshots, backups, storage, or templates - Resize disks (API + in-guest filesystem steps) - Query guest agent for IP addresses - View tasks or system event logs Includes helper script (pve.sh) with auto node discovery from VMID, operational safety gates (read-only vs reversible vs destructive), vmstate snapshot warnings, post-resize guest filesystem steps, and a separate provisioning reference. Requires: curl, jq. Credentials: PROXMOX_HOST, PROXMOX_TOKEN_ID, PROXMOX_TOKEN_SECRET — set as env vars or stored in ~/.proxmox-credentials (sourced at runtime, user-created, mode 600). Writes: ~/.proxmox-credentials (user-created, API token, mode 600). Network: connects to user-configured Proxmox host only (HTTPS, TLS verification disabled for self-signed certs). Helper script: scripts/pve.sh (relative to this skill) Configuration: ~/.proxmox-credentials
agent-optimizer
by Ogurijay
"Optimize Clawdbot/OpenClaw agent operations: concurrency tuning, main↔subagent offloading, heartbeat/cron monitoring, and execution policy (auto-run vs confirmation) with safe risk tiers. Use when you want faster automation without sacrificing control for high-impact actions."
idea-capturer
by PrakharMNNIT
Provides a structured system for capturing fleeting thoughts, developing raw ideas into actionable concepts, and organizing your creative thinking.
docx
by zhuxining
"Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks"
dev-workflow
by orxz
将非平凡开发任务路由到 7 条工作流路径，覆盖从评估到上线的完整生命周期。 强制执行：先规划后编码、TDD、逐任务审查、文档同步、进度持久化。 适用于：多文件功能开发、bug修复、重构、依赖升级、紧急热修复、跨会话任务。 当用户描述一个非平凡开发任务但未选择工作流时，主动建议使用——在任何代码编写之前。
shared-brain
by Noble-Shiva
Set up a shared context directory for multi-agent coordination. Use when you need multiple agents (main + sub-agents) to share priorities, outputs, and feedback without complex messaging. Implements the "one brain, many hands" pattern — agents read from and write to shared files instead of talking to each other. Works with any AI agent that can read/write files (OpenClaw, Claude Code, Codex, Cursor, Aider, etc.).
aseprite-tags
by Chen19007
Extract animation tag metadata (names, frame ranges, directions, colors) from .aseprite files without Aseprite; use when asked to list actions/animations, frame tags, or audit tags across multiple Aseprite assets.
r2d2-controller
by tosi-n
Physical robot emotion expression through Bluetooth-connected Freenove Pico Robot using R2-D2 beeps and sounds. Use when agents need to express emotions, status updates, or personality during task execution. Trigger on (1) successful task completion (happy), (2) errors/blocked states (angry), (3) processing/calculating (think), (4) ambiguous requests (confused), or (5) streaming audio playback (stream_audio).
content-creation-system
by esmondo
Multi-agent content workflow for social media. Use when creating content ideas, validating concepts, planning production, checking trends, or aligning with brand voice. Triggers on content ideas, TikTok/Instagram/YouTube, validation, trends.
follow-builders
by Skylar-explorer
AI builders digest — monitors top AI builders on X and YouTube podcasts, remixes their content into digestible summaries. Use when the user wants AI industry insights, builder updates, or invokes /ai. No API keys or dependencies required — all content is fetched from a central feed.
sts-skill
by ricoleehduu
Claude Code Skill for MICCAI STS Challenge (2023-2026). Provides end-to-end workflows for teeth segmentation tasks including Pre-Task, Task 1/2/3, and historical challenges. Use when: starting STS challenge tasks, training UNet, evaluating segmentation masks, downloading challenge data, preparing submissions, or asking about STS competition workflow. Covers semi-supervised learning, CBCT processing, metal artifact removal, and instance segmentation.
KiCraft
by laforestlabs
Use when the user asks to "check trace widths", "audit my layout", "list footprints", "rearrange footprints", "arrange LEDs in a grid", "move component", "run DRC", "check clearances", "align components", or discusses KiCad PCB layout automation. Provides Python scripts using the KiCad 9 pcbnew API to parse and modify .kicad_pcb files.
spec-write-plan
by nu1nux
Write a detailed, step-by-step implementation plan and save it under docs/plans.
spec-workflow
by DUTSTECH
Spec-driven development workflow for building features with research, requirements, design, and task phases