Agent Skills
› NeverSight/learn-skills.dev
› agent-harness-construction
agent-harness-construction
GitHub用于设计和优化AI智能体的动作空间、工具定义及观测格式，涵盖动作设计、粒度规则、错误恢复和上下文预算，旨在提升任务完成率。
Trigger Scenarios
优化智能体规划与工具调用逻辑
设计或重构工具Schema
改进错误恢复机制
调整上下文管理策略
Install
npx skills add NeverSight/learn-skills.dev --skill agent-harness-construction -g -y
SKILL.md
Frontmatter
{
"name": "agent-harness-construction",
"origin": "ECC",
"description": "Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates."
}
Agent Harness Construction
Use this skill when you are improving how an agent plans, calls tools, recovers from errors, and converges on completion.
Core Model
Agent output quality is constrained by:
- Action space quality
- Observation quality
- Recovery quality
- Context budget quality
Action Space Design
- Use stable, explicit tool names.
- Keep inputs schema-first and narrow.
- Return deterministic output shapes.
- Avoid catch-all tools unless isolation is impossible.
Granularity Rules
- Use micro-tools for high-risk operations (deploy, migration, permissions).
- Use medium tools for common edit/read/search loops.
- Use macro-tools only when round-trip overhead is the dominant cost.
Observation Design
Every tool response should include:
status: success|warning|errorsummary: one-line resultnext_actions: actionable follow-upsartifacts: file paths / IDs
Error Recovery Contract
For every error path, include:
- root cause hint
- safe retry instruction
- explicit stop condition
Context Budgeting
- Keep system prompt minimal and invariant.
- Move large guidance into skills loaded on demand.
- Prefer references to files over inlining long documents.
- Compact at phase boundaries, not arbitrary token thresholds.
Architecture Pattern Guidance
- ReAct: best for exploratory tasks with uncertain path.
- Function-calling: best for structured deterministic flows.
- Hybrid (recommended): ReAct planning + typed tool execution.
Benchmarking
Track:
- completion rate
- retries per task
- pass@1 and pass@3
- cost per successful task
Anti-Patterns
- Too many tools with overlapping semantics.
- Opaque tool output with no recovery hints.
- Error-only output without next steps.
- Context overloading with irrelevant references.
Version History
- e0220ca Current 2026-07-05 23:50
