Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
mysql
Manage MySQL databases via the mysql CLI.
olasunkanmi-SE/codebuddy 118
-
onebot-ops
OneBot (QQ/Lagrange) 渠道运维与使用规范。消息收发通过 Channel outbound 与 deliver 完成，不依赖 Agent 工具。
LSTM-Kirigaya/openclaw-onebot 116
-
Verification Planner
Forces the generation of test_assertions.json during the implementation plan phase. v7.2.0 enhanced with severity gates, dependencies, timeouts, and Claw-as-Validator support.
dcostenco/prism-mcp 116
-
claw-release
Release automation for Claw skills and website. Guides through version bumping, tagging, and release verification.
prompt-security/clawsec 894
-
clawtributor
Community incident reporting for AI agents. Contribute to collective security by reporting threats.
prompt-security/clawsec 894
-
clawsec-clawhub-checker
ClawHub reputation checker for ClawSec suite. Enhances guarded skill installer with VirusTotal Code Insight reputation scores and additional safety checks.
prompt-security/clawsec 894
-
soul-guardian
Drift detection + baseline integrity guard for agent workspace files with automatic alerting support
prompt-security/clawsec 894
-
clawsec-nanoclaw
Use when checking for security vulnerabilities in NanoClaw skills, before installing new skills, or when asked about security advisories affecting the bot
prompt-security/clawsec 894
-
openclaw-audit-watchdog
Automated daily security audits for OpenClaw agents with email reporting. Runs deep audits and sends formatted reports.
prompt-security/clawsec 894
-
clawsec-scanner
Automated vulnerability scanner for agent platforms. Performs dependency scanning (npm audit, pip-audit), multi-database CVE lookup (OSV, NVD, GitHub Advisory), SAST analysis (Semgrep, Bandit), and agent-specific DAST hook execution testing for OpenClaw hooks.
prompt-security/clawsec 894
-
clawsec-feed
Security advisory feed with automated NVD CVE polling for OpenClaw-related vulnerabilities. Updated daily.
prompt-security/clawsec 894
-
clawsec-suite
ClawSec suite manager with embedded advisory-feed monitoring, cryptographic signature verification, approval-gated malicious-skill response, and guided setup for additional security skills.
prompt-security/clawsec 894
-
recover
Scan agent health and auto-recover stale or dead sessions
iii-hq/agentos 113
-
memory
Persistent agent memory — store, recall, search across sessions
iii-hq/agentos 113
-
swarm
Multi-agent swarm coordination — create swarms, broadcast tasks, reach consensus
iii-hq/agentos 113
-
status
System status and health checks — dashboard stats, agent health, worker status
iii-hq/agentos 113
-
evolve
Create, test, and improve functions at runtime — agents write their own code
iii-hq/agentos 113
-
lifecycle
Session lifecycle management — transitions, state tracking, reactions
iii-hq/agentos 113
-
tasks
Task decomposition — break features into subtasks, assign workers, track progress
iii-hq/agentos 113
-
orchestrate
Plan and execute multi-agent work — decompose features, spawn workers, monitor progress
iii-hq/agentos 113
-
security
Security scanning — injection detection, capability checks, audit trails
iii-hq/agentos 113
-
vault
Secret management — encrypted storage for API keys, tokens, credentials
iii-hq/agentos 113
-
workspace-dispatch
Autonomous multi-agent mission orchestrator. Decomposes a mission into tasks, spawns sub-agents for each step, reviews output against exit criteria, and chains tasks automatically with retry. State persists to disk so missions survive context loss. Triggered by the Conductor UI or by direct user request.
outsourc-e/clawsuite 306
-
workspace-dispatch
Single-agent mission orchestrator. Decomposes a mission into tasks, spawns one worker per task using the default model, verifies exit criteria, and chains tasks with retry. No critic pattern — each worker self-verifies. Simple, fast, works with any model config.
outsourc-e/clawsuite 306