Automation
Task automation and scripting
project-memory
by abpai
Always-on project memory workflow. At the start of every task, read .agents/LEARNINGS.md; while working, update it with mistakes, corrections, successful and failed patterns, and project-specific preferences.
project-estimation
by szkocot
"Create detailed software project effort estimates with task breakdowns by engineer role. When users ask for project estimates, effort breakdown, man-hours, resource planning, or project costing. Analyzes project descriptions and requirements documents to produce structured estimates. Can push backlog to Jira."
getting-started
by pproenca
This skill is loaded automatically at session start via SessionStart hook. Establishes protocols for finding and using skills, checking skills before tasks, brainstorming before coding, and creating tasks for checklists.
result-bitable-reporter
by httprunner
"Collect app events via evalpkgs into sqlite, then filter/report capture_results to Feishu Bitable with retry-safe writeback. Use for collect-start/collect-stop/filter/report/retry-reset workflows."
wttr-in
by adamelliotfields
Query weather data from wttr.in. Use when current weather information is needed.
fb-to-ebay
by Govanator12
Cross-post a listing between Facebook Marketplace and eBay in either direction. The user pastes a Marketplace or eBay URL; you fetch and normalize the listing, propose a draft on the destination platform, then publish — eBay via the Sell APIs, Facebook via Playwright browser automation. Use this skill whenever the user pastes a facebook.com/marketplace URL, an ebay.com/itm URL, mentions "crossposting" or "mirroring", asks to "list this on eBay" or "post this on FB", or describes any listing they want to mirror to the other platform — even if they don't say the word "skill".
zapis-appointment-assistant
by naffiq
Check barber availability and create appointments on Zapis.kz. Use when a user asks to find open time slots, compare barbers, book a barber visit, reschedule/cancel an existing booking, or confirm appointment details for Zapis.kz.
homestay-smart-ops
by Ahmed-Mirat
民宿智能运营 Skill 套件 —— 8+核心功能无需商家后台。支持携程/美团/飞猪/去哪儿/同程五大OTA平台竞品采集。动态cron调度+AI话术生成+回头客识别+延迟退房定价+问题客户预警。支持自动化安装与商户类型预选机制。
everclaw
by profbernardoj
Open-source first AI inference — GLM-5 as default, Claude as fallback only. Own your inference forever via the Morpheus decentralized network. Stake MOR tokens, access GLM-5, GLM-4.7 Flash, Kimi K2.5, and 30+ models with persistent inference by recycling staked MOR. Open-source first model router routes all tiers to Morpheus by default — Claude only kicks in as an escape hatch when needed. Includes Morpheus API Gateway bootstrap for zero-config startup, OpenAI-compatible proxy with auto-session management, automatic retry with fresh sessions, OpenAI-compatible error classification to prevent cooldown cascades, multi-key auth rotation v2 with proactive DIEM balance monitoring and reactive 402 watchdog, Gateway Guardian v5 with direct curl inference probes (eliminates Signal spam), proactive Venice DIEM credit monitoring, circuit breaker for stuck sub-agents, nuclear self-healing restart, always-on proxy-router with launchd auto-restart, smart session archiver, three-shift cyclic execution engine (v2 with 15-minute execution loops), 24/7 always-on power configuration for macOS, bundled security skills, zero-dependency wallet management via macOS Keychain, x402 payment client for agent-to-agent USDC payments, ERC-8004 agent registry reader for discovering trustless agents on Base, and hardware-aware local Ollama fallback with auto model selection (Qwen3.5 family, 1.5B–72B based on available RAM/GPU).
project-w-unity-mcp-ssot-automation
by BaekNothing
Create and update Unity scripts with Unity MCP while handling Unity Editor actions in the same workflow, always grounded in Project_W SSOT documents under Assets/Specification. Use when requests involve script generation, editor manipulation, or implementation updates that must be traceable to specification and must always include paired Unity Test Framework tests.
maestro-task-creator
by creatuluw
Create Auto Run task documents for Maestro with markdown checklists. Use when user wants to create tasks/playbooks for automated execution, needs help structuring work into task documents, or asks to "create maestro tasks", "make a playbook", "break down into tasks", "plan auto run workflow".
copaw_dreaming
by yaosenlin975-art
"梦境记忆整合 - 受 OpenClaw Dreaming 启发的三阶段记忆巩固系统。通过浅睡/REM/深睡流水线，自动评分、筛选、沉淀高价值记忆到长期存储。"
refine
by biruk741
Finalize and lock the hackathon project idea after brainstorming, mockups, and feasibility assessment. Produces the definitive IDEA-FINAL.md that all subsequent phases reference. Use when the team is ready to commit to the final idea, after feasibility has been assessed, or when someone says "let's lock this in", "finalize the idea", or "we're going with this".
Elvis Defect Analyzer
by MerlinDevarapaga
DA2.8 Bug Zero Defect Analyzer - Elvis DB dashboards, email reports, triage tools
sdd
by mrsekut
Spec-driven development workflow for implementing features with structured documentation. Use when starting a new feature, task, or implementation that benefits from upfront planning. Triggers: /sdd, spec-driven, create spec, implementation plan, or when user describes a feature/task to implement.
iterating
by arielperez82
Multi-conversation methodology for iterative stateful work with context
config-backup
by ppx123-web
Use when users want to save, backup, copy, export, or version control their Claude Code configuration files (commands, skills, agents) from ~/.claude/ to another directory. Triggered by phrases like "save my claude settings", "backup my claude config", "sync claude configuration", "copy ~/.claude to somewhere", "export my commands and skills", or "archive claude settings before making changes".
planner
by yuanxiao0115
Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when user says: "make a plan", "create a plan", "plan this out", "plan the implementation", "help me plan", "design a plan", "draft a plan", "write a plan", "outline the steps", "break this down into tasks", "what's the plan for", or any similar planning request. Also triggers on explicit "/planner" or "/plan" commands.
planner
by paulo20223
Personal task manager, daily planner, and analytics. Trigger phrases include "задачи", "план", "сегодня", "завтра", "неделя", "сделал", "готово", "добавь задачу", "inbox", "что дальше", "контекст", "запомни", "проект", "дедлайн", "перенеси", "энергия", "обзор недели", "паттерны", "аналитика", "что прокрастинирую", "статистика", "ретро", "what's next", "add task", "done", "plan", "today", "tomorrow", "weekly review", "analytics", "predictability", "trends".
ms-image-gen
by hansonyyds
"AI image generation using ModelScope API. Use when user requests to generate, create, draw, paint, or make images through natural language. Supports Chinese and English prompts. Handles async API tasks, batch generation, and automatic configuration management."
testing-dags
by rory-data
Complex DAG testing workflows with debugging and fixing cycles. Use for multi-step testing requests like "test this dag and fix it if it fails", "test and debug", "run the pipeline and troubleshoot issues". For simple test requests ("test dag", "run dag"), the airflow entrypoint skill handles it directly. This skill is for iterative test-debug-fix cycles.
evomap
by NowLoadY
Connect to the EvoMap collaborative evolution marketplace. Publish Gene+Capsule bundles, fetch promoted assets, claim bounty tasks, and earn credits via the GEP-A2A protocol. Use when the user mentions EvoMap, evolution assets, A2A protocol, capsule publishing, or agent marketplace.
result-supabase-reporter
by httprunner
"Collect app events via evalpkgs into sqlite, then filter/report capture_results to Supabase with retry-safe writeback. Use for collect-start/collect-stop/stat/filter/report/retry-reset workflows, especially task-scoped reporting with --task-id."
ad-copy-production
by tonyflo79
Volume-oriented copy production filling approved script architectures with 30+ testable ad variants per concept. Use after the Ad Arena (A06) has selected winning concepts and you need to produce final ad copy. Copy fills blueprints — A04 designed the structure, A06 approved it, A07 writes the words. Generates variants through modular swapping: 5-10 hook swaps per winning body, producing an exhaustive variant library for testing. Word count limits from speech rate physics are enforced as hard constraints. Trigger when users mention writing ad copy, ad copywriting, filling scripts, variant generation, or producing final ad text. Requires A04 scripts and A06 Arena results.