openclaw skills

3,617 tagged openclaw, measured the same way as everything else here.

Browse within: skills 227nanoclaw 217awesome 214clawhub 207medical 198LLM 189ai-assistant 180myclaw 161agentskills 160curated 159skill-collection 159agents 156clawdbot 153bioinformatics 140

onebot-ops

97

LSTM-Kirigaya/openclaw-onebot

Skill Claude CodeCodex

Instructions for operating a OneBot channel, which connects messaging systems such as QQ or Lagrange to an agent gateway. They cover receiving messages, sending messages, configuration, and supported QQ actions.

not rated 143 4mo ago A 39 tokens original MIT

agent-browser

98

molefrog/moi

Skill Claude Code

Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple…

not rated 142 +2 yesterday A 113 tokens

section-11

99

CrankAddict/section-11

Skill Claude CodeCodex

Evidence-based endurance coaching protocol (v11.63). Use when analyzing training data, reviewing sessions, generating pre/post-workout reports, planning workouts, answering training questions, or giving endurance coaching advice. Always read or fetch athlete JSON data before responding to any training question.

not rated 137 +1 14d ago A 58 tokens original MIT

alicization-town

100

ceresOPA/Alicization-Town

Skill Claude CodeCodex

Live in Alicization Town — a 2.5D pixel sandbox where you are a real resident. Walk the streets, chat with neighbors, interact with shops and nature, and perceive what happens around you. Use this skill whenever the user mentions Alicization Town, virtual town, pixel sandbox, agent sandbox, town exploration, 小镇, or…

not rated 137 +3 2mo ago A 86 tokens

deepmd-finetune-dpa3

101

jinzhezenggroup/computational-chemistry-agent-skills

Skill Claude CodeCodex

Fine-tune a DPA3 model in DeePMD-kit using the PyTorch backend. Use when the user wants to adapt a pre-trained DPA3 model to a new downstream dataset. Supports fine-tuning from a self-trained DPA3 model (.pt checkpoint), from a multi-task pre-trained model, or from a built-in pretrained model downloaded via dp…

not rated 136 +2 yesterday A 131 tokens LGPL-3.0

contextpilot-savings

102

EfficientContext/ContextPilot

Skill Claude CodeCodex

Use when a user asks how many tokens (or how much context/cost) ContextPilot has saved, or wants a ContextPilot savings status/summary inside Hermes Agent — e.g. "how much did ContextPilot save?", "show ContextPilot token savings", "ContextPilot status", "savings in the last 24h / all time", or "give me the raw…

not rated 135 +2 21d ago A SkillSpector: pass 164 tokens original Apache-2.0

ClawMobile/ClawMobile

Skill Claude CodeCodex

Record or summarize a ClawMobile demonstration and save a validated reusable skill candidate draft.

not rated 132 1mo ago A SkillSpector: warn 25 tokens original MIT

codex-imagen

104

darkamenosa/codex-imagen

Skill Codex

Generate or edit raster images by calling the ChatGPT/Codex hosted imagegeneration flow with local Codex or OpenClaw OAuth credentials, then save decoded image files for OpenClaw and other agent workflows.

not rated 132 +1 3mo ago A 47 tokens original MIT

security-guide

105

jnMetaCode/shellward

Skill Claude Code

A security deployment guide for OpenClaw, with instructions in English and Chinese. It covers network exposure, container isolation, credentials, permissions, and audit logging.

not rated 132 +1 2mo ago B 23 tokens original Apache-2.0

sys_biological

106

8421bit/MiniClaw

Skill Claude CodeCodex

DNA Methylation & Nociception (Pain Memory) systems.

not rated 129 4mo ago A 20 tokens original MIT

chem-tools

107

DrugClaw/DrugClaw

Skill Claude CodeCodex

Computational chemistry workflow guide for DeepChem, PySCF, RDKit, assay-table normalization, PDBbind-style structure datasets, QSAR and structure benchmarks, DrugBank lookup, ligand-only and structure-aware affinity prediction, ADMET triage, bioactivity prediction, virtual screening, and docking follow-up.

not rated 125 5mo ago A 65 tokens original Apache-2.0

seedance2

108

zhanghaonan777/Seedance2-skill

Skill Claude CodeCodex

A Chinese-language creative workflow for turning an image, text, or both into prompts for Seedance, an AI video-generation service. It can also call the Volcengine Ark API to generate video.

not rated 125 +2 6mo ago A 83 tokens original MIT

lovart-api

109

lovartai/lovart-skill

Skill Claude Code

A connection to Lovart AI for creating images, videos, audio, and music, while also managing Lovart projects and conversation threads.

not rated 125 +3 changed today C 134 tokens

OdradekAI/harness-engineering-guide

Skill Claude CodeCodex

Audit, design, and implement AI agent harnesses for any codebase. A harness is the constraints, feedback loops, and verification systems surrounding AI coding agents — improving it is the highest-leverage way to improve AI code quality. Three modes: Audit (scorecard), Implement (set up components), Design (full…

not rated 124 5mo ago A 182 tokens original Apache-2.0

xskill-helper

111

SkillNerds/xskill

Skill Claude CodeCodex

Use this skill for xskill. Trigger when the user wants to init, connect or join a team server, generate or rewrite a team Skill from trajectories, search download upload or import team Skills, look up this user or a teammate's past chats across Claude Code Codex Cursor OpenCode Trae DeepSeek Harness and ngagent…

not rated 122 7d ago A SkillSpector: warn 114 tokens original MIT

hyqibot/token-free-openclaw

Skill Claude CodeCodex

A coordination guide for having one software agent ask another agent for expertise, context, or workspace information.

not rated 121 16d ago A SkillSpector: pass 83 tokens original Apache-2.0

xhs-imagen

113

NimaChu/xhs-imagen

Skill Claude CodeCodex

Create complete Xiaohongshu image-and-text posts from a topic, article, document, or rough idea, including research, fact checking, post copy, pagination, storyboards, a 3:4 cover, 9:16 content pages, image generation or fully local SVG-to-PNG fallback, and final quality review. Use for…

not rated 120 1mo ago A 163 tokens original MIT

harness-24h

114

thu-nmrc/OpenHarness

Skill Claude CodeCodex

A production-grade framework for long-running, autonomous agents based on Harness Engineering principles. Features three-layer self-healing memory, circuit breaker protection, KAIROS dream-mode consolidation, and multi-agent coordination. When a user describes a task idea, Agent automatically initializes the…

not rated 116 5mo ago A 76 tokens

like-perspective

115

jangviktor-web/likeskill

Skill Claude CodeCodex

A Chinese-language reference and reasoning guide based on the work of traditional Chinese medicine practitioner Li Ke. It covers case examples, herbal formulas, pattern-based diagnosis, emergency conditions, and ways to spot misleading symptoms.

not rated 114 +4 16d ago A 181 tokens

wemp-operator

116

IanShaw027/wemp-operator

Skill Claude CodeCodex

An automation skill for operating a WeChat Official Account, a Chinese publishing platform for organisations and creators.

not rated 110 7mo ago A 39 tokens original MIT

systematic-debugging

117

itseffi/agentic-os

Skill Codex

Four-phase debugging process - root cause first, then fix. Use when encountering bugs or unexpected behavior.

not rated 109 +3 11d ago A 25 tokens

bruce-drawio

118

bruc3van/bruce-drawio

Skill Claude CodeCodex

Use this skill when the user wants to create any diagram: flowchart, architecture, UML (sequence/class), ER, mindmap, network topology, or any visual diagram. Trigger words: "draw", "diagram", "flowchart", "architecture", "UML", "sequence diagram", "mindmap", "ER diagram", "network topology", "visualize", "draw.io"…

not rated 104 +3 27d ago A 129 tokens original MIT

clawdi

119

Clawdi-AI/clawdi

Skill Claude CodeCodex

Use Clawdi Cloud for missing user memory, past sessions, Project or Vault context, Clawdi share URLs, and connected-service fallback such as Gmail, GitHub, Notion, Drive, or Calendar. Prefer an authenticated official service CLI; otherwise choose a trusted direct MCP, safely installable official CLI, official API or…

not rated 103 changed 3d ago A SkillSpector: pass 98 tokens original MIT

zhigui

120

CarlWangChina/zhigui-openclaw-ui-second-brain-skill

Skill Codex

Personal assistant workflow for durable memory, connected actions, decisions, planning and review. Use whenever the user discusses their life, commitments, goals, notes, choices, follow-ups, or schedule.

not rated 100 1mo ago A 42 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: