self-improving-agent
Captures and maintains learnings, errors, and corrections. Use when a command fails, the user corrects an assumption, a capability is missing, knowledge is…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-18 00:12
24,059 results
Captures and maintains learnings, errors, and corrections. Use when a command fails, the user corrects an assumption, a capability is missing, knowledge is…
Help users master the transition from manual coding to managing AI-driven development workflows by focusing on high-level direction, parallel tasking, and…
Analyze production Agentforce agent behavior using session traces and Data Cloud, and manage Agent Health Monitoring (AHM) alerts. TRIGGER when: user queries…
Create and manage agentic wallets with Cobo. Use for autonomous onchain operations via the caw CLI: token transfers, contract calls, pact creation and…
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
Create and refine OpenCode agents via guided Q&A. Use proactively for agent creation, performance improvement, or configuration design. Examples: - user:…
Spawn Codex subagents via background shell to offload context-heavy work. Use for: deep research (3+ searches), codebase exploration (8+ files), multi-step…
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running…
Pair a remote AI agent with your browser. (gstack)
Build maps, areas, zones, and large-scale environments in Roblox Studio via MCP. Use when: user asks to create a map, battle arena, lobby, hub, town, village,…
CHAIN multiple existing skills into custom multi-step workflows. Programmable skill combinations with automatic handoffs. Create composite skills from building…
Create, refactor, or debug agent skills and their loading. Use writing-agents-md for AGENTS.md/CLAUDE.md; excludes general docs and READMEs.
Use when a task involves creating or editing a Scenario workflow graph through MCP: building an app from a brief, adding or rewiring nodes (models, prompts,…
A curated collection of 2409+ best OpenClaw skills — AI tools, productivity, marketing, frontend, mobile, backend, DevOps and more. Weekly updated by MyClaw.ai — Powered by MyClaw.ai
Prepares meeting materials by gathering context from Notion, enriching with Claude research, and creating both an internal pre-read and external agenda saved…
This skill should be used when agent work needs file-backed context: durable scratchpads, tool-output offloading, just-in-time discovery, cross-agent handoff…
Implement the Syncfusion Angular AI AssistView component. Use this skill when you need to create conversational AI interfaces, integrate AI services, add…
Find 10x product opportunities and high-leverage improvements. Use when user wants strategic product thinking, mentions '10x', wants to find high-impact…
Edit opencode.json, AGENTS.md, and config files. Use proactively for provider setup, permission changes, model config, formatter rules, or environment…
Choose and combine Eve storage primitives to give agents persistent memory — short-term workspace, medium-term attachments and threads, long-term org docs and…
Ni Haixia (1954-2012), Taiwanese Chinese medicine physician, representative figure of the Classical Formula school, founder of Han Tang Chinese Medicine. Core mental models: six-channel pattern differentiation, yang qi theory, classics above all, classical formulas as the mainstay. Decision heuristics: differentiate the six channels first, then select the formula; when yang qi is insufficient, fortify yang first; the original classical formulas are the most reliable. Trigger words: Ni Haixia, Haixia perspective, Chinese medicine Ni Haixia, classical formula thinking, how would Ni Haixia see it, Master Ni. Knowledge base coverage: Shanghan Lun article completion (Taiyang lower section + Yangming section, modules/13…
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
Execute software engineering plan documents using Eve jobs, dependencies, and review gating.
Use when generating or transforming audio with ElevenLabs models on Scenario via MCP: text-to-speech with inline emotion tags, music from a prompt or sectioned…