Skill Library
Let the agent grow its own toolkit by writing reusable skill modules that subsequent runs can call — compounding capability over time.
Intent & Description
🎯 Intent
Accumulate reusable know-how across runs instead of re-deriving the same solutions from scratch every time.
📋 Context
Your long-running agent handles recurring task shapes — weekly competitor reports, periodic data cleans, repeating onboarding workflows. Every run re-derives the same scrape-clean-summarize pipeline from first principles. The runtime supports loading new code modules without restarting the agent.
💡 Solution
A directory (e.g., skills/*.py or skills/*.md) where the agent can write new modules. A loader (importlib in Python, dynamic import in JS) makes them callable. A critic gates additions to prevent low-quality skills from landing. Old skills are versioned, never silently overwritten.
Real-world Use Case
- Patterns of tool use repeat across runs and re-derivation cost is noticeable.
- The agent can write and version reusable modules safely.
- A critic or reviewer gates additions to the library.
Source
📌 TL;DR
Agent writes skills. Skills accumulate. Future runs get faster. Gate additions with a critic and version everything — skills rot without maintenance.
Advantages
- Compounding capability over time — the agent gets better at recurring tasks automatically.
- Skills are reviewable and removable, unlike fine-tuned weights.
Disadvantages
- Skill-name collisions and silent shadowing can corrupt the library.
- Library quality decays without periodic review and pruning.