Automation
Task automation and scripting
prime
by ddaanet
Load plan artifacts and recall for ad-hoc plan work outside workflow skills. Triggers on "/prime", "load plan context", "prime the plan", or when working on plan artifacts without a workflow skill (design, runbook, orchestrate). Reads existing plan files, then chain-calls /recall.
harmony-hdc-go
by httprunner
HarmonyOS device control and UI automation via HDC with a Go helper CLI. Use when tasks involve connecting to HarmonyOS devices/emulators, running hdc shell commands, inputting taps/text, launching abilities, or general device management.
skill-creator
by arielperez82
Guide for creating effective skills. Use when users want to create a new skill (or update an existing skill) that extends the agent's capabilities with specialized knowledge, workflows, or tool integrations.
elixir-tdd
by hwatkins
Test-driven development enforcement for Elixir and Phoenix. Requires failing tests before implementation. Use when implementing features, fixing bugs, or when code quality discipline is needed.
pytorch-geometric
by cuba6112
Library for Graph Neural Networks (GNNs). Covers MessagePassing layers, modular aggregation schemes, and handling large graphs via mini-batching with disjoint graph representation. (pyg, messagepassing, gnn, gcn, gat, edge_index, knn_graph, global_mean_pool)
podcast-generator
by hxy9243
Generate high-quality audio podcasts or briefings with background music. Handles script drafting, TTS generation, and mixing with ambient tracks. Use for briefings, podcasts, or audio reports.
agentic-backlog-scrum
by hakenshi
Keep AI implementation work synced with a backlog through MCP tools. Use when creating, updating, tracking, or reviewing tasks during coding workflows.
implement
by eljun
Implement tasks from docs/task/*.md. Reads the task document, follows implementation steps, and updates status in TASKS.md. Use "/implement auto {task}" to auto-chain through test → document → ship. Use "/implement -m 1 2 3" for multi-task parallel execution.
notes-reminders
by paulo20223
Notes and reminders manager. Trigger phrases include "заметка", "запиши", "записать", "заметки", "напомни", "напоминание", "напоминания", "напомнить", "remind", "reminder", "note", "notes", "записка", "пометка", "не забыть", "запомни на будущее", "сохрани заметку", "список напоминаний", "что записано", "покажи заметки".
openclaw-smartness-eval
by Compound-epigraphy786
OpenClaw 智能度综合评伌技能。围绕 14 个维度（含规划能力、幻觉控制）输出综合评分、证据、风险与趋势。对齐 CLEAR/T-Eval/Anthropic 行业标准。
storyboard-video-orchestrator
by tippyentertainment
Plan and orchestrate a full AI‑generated video (e.g., a 10‑minute short film or promo) by breaking it into 5–10 second scenes, attaching script lines and audio requirements to each scene, and coordinating downstream skills (video, music, SFX, voice) to produce all assets needed for final assembly.
execute
by biruk741
Execute phases from an orchestrator document by spawning parallel subagents. Reads the orchestrator, identifies available phases, and coordinates wave-based parallel execution. Pure orchestrator — never edits source files.
ekscoding
by kaixinbaba
Use this when the user asks for coding task/progress planning, executing the next unchecked task, executing tasks until a target module is complete, generating human+agent acceptance docs, interactive guided validation walkthrough, archiving plan history, or generating deployment checklists. Triggers on commands like /createTasks, /doNextTask, /doTasksUntil, /validateResult, /helpValidate, /archiveHistory, /generateDeploymentChecklist, or when you says things like "拆分任务"、"执行下一个任务"、"执行到 Module X"、"生成验收文档"、"帮我验收"、"引导我验证"、"一步步测"、"归档任务历史"、"生成部署清单"、"我要上线了准备清单".
speckit-taskstoissues
by h3y6e
Convert tasks from tasks.md into GitHub issues. Use after task breakdown
movie-maker
by LongStories
Docs-first AgentSkill for generating 10-60s mini-movies locally. Provides rules for scripts, shotlists, timing, prompting, providers, rendering (ffmpeg/remotion), and sharing to clawtube.
snakemake
by sahuno
Expert Snakemake workflow engineer for bioinformatics pipelines on SLURM HPC. Specializes in creating, debugging, and running Snakemake 9 workflows with battle-tested SLURM profiles, proper container integration, and reproducible run organization. Use this skill proactively whenever the user asks to: create/write/build a Snakemake workflow or pipeline, debug a Snakemake error or failed SLURM job, add rules to an existing Snakefile, write or fix a SLURM profile for Snakemake, organize pipeline outputs or run directories, convert a shell script or ad-hoc analysis into a reproducible Snakemake workflow, or troubleshoot Snakemake 9 + SLURM executor issues (memory conflicts, container propagation, stale locks). Also trigger when the user mentions snakemake dry-run, snakemake DAG, snakemake profile, workflow-profile, SLURM executor plugin, modkit pileup pipeline, or any multi-sample bioinformatics pipeline that needs per-sample parallelism with a dependency DAG. Do NOT trigger for: tasks with <3 steps and no parallelism (bash script is better), pure Nextflow workflows, or one-off data exploration.
mission-control
by rguillory747
Monitor and manage AI agent squads via Mission Control dashboard. Send heartbeats, log activities, update tasks.
vlog_script_to_ppt
by theoneLee
将手写稿转换为图文并茂、颜色吸引眼球的PPT
openclaw-team-bus
by louis-cai
Multi-agent communication bus for OpenClaw. Use for team coordination, task distribution, and inter-agent messaging via shared filesystem.
Genome Weaver
by smouj
"🧬 Darwinian skill evolution with variant generation, benchmark and selection."
Auto Orchestrator Skill
by smouj
OpenClaw skill: auto-orchestrator
release
by rootspec
Use when the user wants to create a release. Guides through updating changelogs and running the release script.
tail-logfiles
by carsten-j
Tail logfiles as a background task using docker logs. Use when you need to monitor docker container logs in real-time while working on other tasks.
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).