agent-harness-construction
Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
- License 许可
- MIT
- 最近更新
- 2026-11-10
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- agent-harness-construction
- origin
- ECC
- description
- Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
03 SKILL.md 正文
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.
04 同仓库更多 Skills
vercel-sandbox
Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.
slack
Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.
electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.
dogfood
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.