Optimize Agent Prompt

Builds and improves Browserbase Agent API demos through an Autobrowse-style outer loop: run a fixed task, collect Agent messages and session logs, score the result, revise one system-prompt heuristic, and confirm convergence. Use when creating a Browserbase Agents demo or POC, optimizing an Agent system prompt, diagnosing flaky Agent runs, or applying auto-research/autobrowse to the Browserbase Agents API.

3,757 stars 239 forksAI, LLMs & AgentsOfficial Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add browserbase/skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add browserbase/skills --skill optimize-agent-prompt
Manual install
git clone --depth 1 https://github.com/browserbase/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skills/optimize-agent-prompt ~/.claude/skills/optimize-agent-prompt

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Optimize Agent Prompt

Optimize a Browserbase Agent's `systemPrompt` while holding its task, result schema, variables, and evaluation criteria fixed. Treat the outer agent as the teacher and each Browserbase Agent run as an inner-agent rollout.

Use Node.js 18 or later and set `BROWSERBASE_API_KEY`. The harness uses only Node.js built-in modules.

## Set up the experiment

Choose a short experiment name and create an isolated workspace inside the demo or POC repository:

```bash
node <skill-dir>/scripts/optimize_agent_prompt.mjs init \
  --workspace ./agent-prompt-optimization/<experiment-name> \
  --name <experiment-name>
```

Edit the generated files:

- `task.json`: keep `task`, `resultSchema`, variables, browser settings, and evaluation oracle stable across iterations.
- `prompts/iteration-001.md`: write the minimal baseline system prompt. Include irreversible-action guardrails when applicable.

Use concrete success criteria. Prefer a strict JSON Schema with required fields and `null` for unavailable facts. Add known-field regexes and factuality-warning regexes under `evaluation` when a truth oracle exists. Read [references/evaluation.md](references/evaluation.md) when designing the task or score.

## Run the baseline

```bash
node <skill-dir>/scripts/optimize_agent_prompt.mjs run \
  --workspace ./agent-prompt-optimization/<experiment-name> \
  --prompt prompts/iteration-001.md \
  --label iteration-001
```
Read the full skill on GitHub

Details

Skill name
optimize-agent-prompt
Path
skills/optimize-agent-prompt/SKILL.md
Repo updated
17 November 2026

FAQ

What does the Optimize Agent Prompt skill do?

Builds and improves Browserbase Agent API demos through an Autobrowse-style outer loop: run a fixed task, collect Agent messages and session logs, score the result, revise one system-prompt heuristic, and confirm convergence. Use when creating a Browserbase Agents demo or POC, optimizing an Agent system prompt, diagnosing flaky Agent runs, or applying auto-research/autobrowse to the Browserbase Agents API.

How do I install the Optimize Agent Prompt skill?

Claude Code plugin: /plugin marketplace add browserbase/skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Optimize Agent Prompt popular?

It lives in browserbase/skills, which has 3,757 GitHub stars and 239 forks.

Related skills

Autobrowse

3.8k

browserbase/skills

Self-improving browser automation via the auto-research loop. Iteratively runs a browsing task, reads the trace, and improves the navigation skill (strategy.md) until it reliably passes. Supports parallel runs across multiple tasks using sub-agents. Use when you want to build or improve browser automation skills for specific website tasks.

Productivity & Notes239

Browser

3.8k

browserbase/skills

Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications. Supports remote Browserbase sessions with Browserbase Identity, Verified browsers, automatic CAPTCHA solving, and residential proxies — ideal for protected websites and JavaScript-heavy pages.

Software Development239

Browser to API

3.8k

browserbase/skills

Turn a website's observable HTTP traffic into a best-effort OpenAPI 3.1 spec by analyzing a `browser-trace` capture. Use when the user wants to discover/extract API endpoints from a browser session, build an OpenAPI doc from network traffic, or document a third-party site's XHR/fetch surface for client integration.

Software Development239

Verified Eval

3.8k

browserbase/skills

Compare standard and Verified Browserbase sessions on user-selected website flows. Use the user's existing agent flow or a small Stagehand v4 Code Mode agent for task scores. Continue useful tests and save task results, timing, and session evidence. This skill does not compare browser providers.

AI, LLMs & Agents239

Geo Optimizer

4.3k

nowork-studio/notfair-plugin

Audit, improve, and measure visibility in AI search answers from ChatGPT, Claude, Perplexity, Gemini, and Google AI Overviews. Use for GEO, AEO, LLM SEO, AI citation and search crawler audits, AI visibility strategy, buyer-question baselines, brand mentions and fact checks in AI answers, or analysis of supplied Bing AI Performance and Search Console Generative AI reports.

AI, LLMs & AgentsIn 2 lists531

Pinme LLM

3.8k

glitternetwork/pinme

Use this skill when a PinMe project (Worker TypeScript) needs to call OpenRouter-backed LLM APIs, including models, chat/completions, streaming, or OpenRouter web search. Guides AI to generate correct Worker TS code.

AI, LLMs & AgentsIn 1 list276

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.