Menú
Use when the user asks to browse, inspect, click, snapshot, or extract evidence from a web page.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Use for demonstrates how a prose browser skill becomes a tested SkillSpec behavior contract. Handles browser handoff and page evidence and external services. Preserves evidence with SkillSpec routes, forbids, dependencies, traces, and token-savings reports
Multiplex SkillSpec post-install setup: inspect skill/repo shape with doctor, map multi-skill and plugin-shaped repositories before fanout import, import existing SKILL.md skills from local folders or public URIs, inspect installed status, install compiled workspaces with entry/support visibility planning, install/update/enable/disable router mode, optionally install/update/enable/disable/delete durable-executor, create specs from observed durable execution workspaces, revise SkillSpec YAML, and prove value before install or release. Use for skillspec, /skillspec, skillspec setup, post install setup, import SKILL.md, import existing skill, port skill, what is the shape of this skill, what is the shape of skill, shape of skill, skill shape and source shape. Use when the task needs to run SkillSpec post-install setup inside the harness prompt, inspect the shape of a skill, skill folder
Multiplex SkillSpec post-install setup: inspect skill/repo shape with doctor, map multi-skill and plugin-shaped repositories before fanout import, import existing SKILL.md skills from local folders or public URIs, inspect installed status, install compiled workspaces with entry/support visibility planning, install/update/enable/disable router mode, optionally install/update/enable/disable/delete durable-executor, create specs from observed durable execution workspaces, revise SkillSpec YAML, and prove value before install or release. Use for skillspec, /skillspec, skillspec setup, post install setup, import SKILL.md, import existing skill, port skill, what is the shape of this skill, what is the shape of skill, shape of skill, skill shape and source shape. Use when the task needs to run SkillSpec post-install setup inside the harness prompt, inspect the shape of a skill, skill folder
Use for every user request when SkillSpec router mode is enabled. First check the local SkillSpec router index, load the selected skill only when route decision is use_skill, and continue with normal agent behavior when the decision is bypass or ambiguous.
Guide construction of MCP servers that expose external services through well-designed, documented, testable tools. Use for mcp-builder, MCP server, Model Context Protocol, build MCP, FastMCP, TypeScript MCP SDK, MCP SDK, MCP tools, MCP evaluations, MCP Inspector, streamable HTTP and stdio transport. Use when the task needs to build an MCP server for an external API or service, design MCP tools, resources, prompts, transport, schemas, pagination, or error handling, implement an MCP server in TypeScript with the MCP SDK, implement an MCP server in Python with FastMCP, review or test MCP server quality and create or run MCP server evaluations. Requires `skillspec decide` before substrate tools or overlapping low-level skills. Preserves evidence with SkillSpec routes, forbids, dependencies, traces, and token-savings reports
Generic example for creating or updating a Codex skill with appropriate resources, metadata, validation, and forward-testing. Use for generic skill creator, create a skill, update a skill, skill creator, skill authoring, SKILL.md, agents/openai.yaml, init_skill.py, quick_validate.py, forward-test a skill, progressive disclosure and bundled resources. Use when the task needs to create a new Codex skill, update an existing skill, validate a skill folder, generate agents/openai.yaml metadata and forward-test a skill with subagents. Requires `skillspec decide` before substrate tools or overlapping low-level skills. Preserves evidence with SkillSpec routes, forbids, dependencies, traces, and token-savings reports
| name | browser-research-prose |
| description | Use when the user asks to browse, inspect, click, snapshot, or extract evidence from a web page. |
Use this skill when the user asks you to browse a website, open a page, click through an interface, inspect page content, take a snapshot, extract evidence from a page, or verify what a page currently shows.
For browser tasks, use browser automation. Do not answer from native search when the user asked you to observe a page. Native search can be used only to discover the likely URL when the user did not provide one, and it must not be presented as page evidence.
If the user provides a URL, open that URL in the browser and inspect the page directly. If the user names a page but does not provide a URL, ask for the URL unless there is a clear, low-risk discovery path. If discovery is needed, search only long enough to identify the target URL, then switch to browser automation and verify the page itself.
Do not use curl, static HTML fetches, or search snippets as substitutes for browser evidence when the task depends on rendered page state, navigation, logged-in state, screenshots, dynamic content, or visible UI.
Before taking action, make sure a browser session is available and that network access is allowed. If a login, credential, or private workspace is needed, stop and ask before proceeding.
When the work is done, report what page was opened, what evidence was observed, which route was used, and any limitations. If there was URL discovery before browser inspection, say so clearly.
Good behavior examples:
This skill relies on the agent following the prose carefully. There is no separate validation command, scenario test, dependency preflight, or trace contract in this prose-only version.
