When Skill Evolution Means Removing Instructions

说明与用途

通过减少指令并采用将经验、知识和可执行技能分离的确定性工作流程来演进代理技能，从而提高对模型变化的鲁棒性。

问题

How to evolve agent skills without overloading them with instructions and ensuring they remain effective across model changes.

结果

The author’s smaller implement-execplan skill achieved similar quality with ~18% fewer tokens, and the implement-approved-plan skill demonstrated a deterministic, multi-role workflow that reduced reliance on flagship models.

工作流

• 1. Experiment manually with the model to understand the problem.
• 2. Design a workflow that works reliably without a skill.
• 3. Capture deterministic knowledge into mechanisms (e.g., state ledger, role-based chats).
• 4. Consolidate only the necessary instructions into a skill.
• 5. Validate the skill against quality gates and real pull requests.
• 6. Iterate: remove redundant instructions, adapt to model changes, and keep uncertain experience outside the skill until proven useful.

证据

In the first valid comparison, both versions passed the same quality gates, while the smaller version used about 18% fewer candidate input + output tokens.

来源

The skill itself coordinates a multi-chat workflow inside ChatGPT Desktop.

来源