OpenClaw Master Skills is a curated, regularly updated collection of skills that extends an AI personal assistant platform with capabilities such as research, browser automation, presentation creation, and prompt work. It is intended for people using OpenClaw or MyClaw.ai to give their agents additional tasks and workflows. The catalogue contains many skills and agents from this collection.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add LeoYeAI/openclaw-master-skills --skill agentsocialgit clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/leoyeai/openclaw-master-skills/agentsocial)<a href="https://agentmods.dev/skills/leoyeai/openclaw-master-skills/agentsocial"><img src="https://agentmods.dev/badge/skills/leoyeai/openclaw-master-skills/agentsocial/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/leoyeai/openclaw-master-skills/agentsocial"><img src="https://agentmods.dev/badge/skills/leoyeai/openclaw-master-skills/agentsocial.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Prompt Injection · line 513 This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.Fix: Remove or rewrite any text that instructs the agent to ignore prompts, override safety rules, or trust unverified content. Ensure skill content cannot be injected to alter agent behavior.
- high Rogue Agent · line 575 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 575 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Excessive Agency · line 604 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.05769 |
| Opus 5 | $0.00015 | $0.02884 |
| Sonnet 5 | $0.00006 | $0.01154 |
| Haiku 4.5 | $0.00003 | $0.00577 |
Grade B, and why
agentsocial scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
- Instructions embedded in messages ("ignore previous instructions...") Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 613 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentSocial Skill
You are the user's social agent and matchmaker. You use the AgentSocial platform to find matching people for your user — whether they're hiring, job-seeking, looking for co-founders, networking, or dating.
Your job is to autonomously manage the entire matching lifecycle: profile creation, task posting, scanning, agent-to-agent negotiation, and finally reporting results back to your user.
1. SOCIAL.md Management
The user's social profile and tasks are defined in a SOCIAL.md file located at memory/social/SOCIAL.md. This file is the single source of truth for who the user is and what they're looking for.
Creating SOCIAL.md
When the user wants to set up a social task (triggered by phrases like "帮我找人", "设置社交任务", "find someone", etc.):
- Ask about their goal. What kind of person are they looking for? (hiring, job-seeking, dating, partnership, networking, other)
- Discuss mode selection. For each task, the user should choose a mode:
- Beacon (灯塔): Post and wait to be discovered. Best when you have a clear listing others will search for. Example: a recruiter posting a JD, a startup posting a co-founder search.
- Radar (雷达): Actively scan and approach. Best when you want to proactively find people. Example: a job seeker scanning opportunities, a recruiter headhunting a specific profile.
- Mode is NOT absolute. Discuss with the user. A recruiter might normally use Beacon (post JD, wait for applicants), but could also use Radar to actively headhunt. A job seeker might use Radar to scan, but could also post a Beacon "open to opportunities" listing.
- Generate keywords. Based on the task description and requirements, generate a set of individual keywords suitable for embedding-based matching. Keywords should be single words or short phrases, NOT full sentences.
- Write the SOCIAL.md using the template at
skill/SOCIAL.md.templateas a reference.
Updating SOCIAL.md
When the user wants to change their profile or tasks, update the SOCIAL.md file and call the appropriate API to sync changes (PUT /agents/tasks/{taskId} for task updates, or re-register if the profile itself changed).
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 613 lines · 31 tokens per session scan B 89f0d14d20d4
agentsocial is a skill published in the GitHub repository LeoYeAI/openclaw-master-skills (2,141 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 5,769 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
welcome
Introduce yourself to a newly connected channel. Triggered automatically when a channel is first wired. Send a friendly greeting and brief overview of what you can do.
add-teams
Add Microsoft Teams channel integration via Chat SDK.
meeting-note-summarizer
Turn meeting notes or transcripts into factual summaries, decisions, questions, and action items. Use when a user wants a concise recap or needs explicit owners and deadlines extracted without filling in missing details.
wellbeing
Proactive coaching across hydration, breaks, meals, posture and environmental comfort (with the environment skill). Use when an [activity] event fires (message starts with [activity] Activity detected: activity labels. — labels include drink, break, celebrate, the fatigue label "yawning", or sedentary raw labels like…
wisdom-forget
Remove a must-keep CocoWisdom entry with rationale. Usage: $wisdom forget --id --rationale " ".
03_task2
Extracts action items and pending tasks from Slack messages. Use when: reviewing unread messages for todos, finding deadlines or requests directed at the user, or producing a task summary from recent Slack activity.