skillspec

Use when the user asks to browse, inspect, click, snapshot, or extract evidence from a web page.

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

Use for any task involving PDF files, including reading, extracting text or tables, creating, transforming, filling forms, OCR, image extraction, and security operations. Use for pdf, .pdf, PDF file, extract PDF text, extract PDF tables, merge PDFs, split PDF, rotate PDF, watermark PDF, create PDF, fill PDF form and OCR PDF. Use when the task needs to read or extract content from a PDF, extract tables from a PDF, merge, split, rotate, crop, repair, optimize, watermark, encrypt, or decrypt PDFs, create a new PDF, fill a PDF form, OCR a scanned PDF into searchable text and extract embedded images from a PDF. Requires `skillspec decide` before substrate tools or overlapping low-level skills. Preserves evidence with SkillSpec routes, forbids, dependencies, traces, and token-savings reports

Universal first-hop for any tool-backed request that may execute, inspect, mutate, automate, browse, call, fetch, generate, install, test, run, or create artifacts through CLI, shell, API, adapter, browser, provider, local process, or external tool, with trace, alignment, evidence capture, and future recall. Use for any tool-backed request, any and all tool execution, all tool execution starts here, universal cli api shell browser provider router, universal tool-backed execution router, execute inspect mutate automate browse call fetch generate install test run create artifacts, create an artifact with a tool, generate a file with a tool, create audio, create a voice message, generate audio and text to speech. Use when the task needs to remember this workflow for future recall, preserve evidence with trace and alignment, route durable work through a meta-router

Browser domain skill for durable-executor handoffs and explicit rote-browse browser execution with trace, alignment, and page evidence. Use for browser handoff from durable executor, durable browser handoff, preserve durable handoff packet, return browser evidence to durable executor, explicit rote-browse browser execution, attach existing browser, logged-in web app state, snapshot or slice a page, click or type in a page and recover stale browser refs. Use when the task needs to browser handoff from durable executor, preserve browser evidence in a durable workspace, browse a website with rote, browse Gmail or an email web app with rote, attach to an active browser, inspect logged-in web app state and snapshot or slice a page. Handles browser handoff and page evidence and dependency checks. Requires `skillspec decide` before substrate tools or overlapping low-level skills

Use for demonstrates always-loaded policy, on-demand procedure imports, section narrowing, and nested import requirements. Preserves evidence with SkillSpec routes, forbids, dependencies, traces, and token-savings reports

Use when the task needs to summarize a local CSV, convert a file into a report, create JSON from local data, analyze local exports without uploading them and remember a recurring local reporting task. Preserves evidence with SkillSpec routes, forbids, dependencies, traces, and token-savings reports

Use for structured representation of a multi-file PDF skill with references, code snippets, artifacts, and an ordered form-filling recipe. Preserves evidence with SkillSpec routes, forbids, dependencies, traces, and token-savings reports

Use for check a local repository against remote state, CI, contributors, and public profile context. Handles logs and streams. Preserves evidence with SkillSpec routes, forbids, dependencies, traces, and token-savings reports

Use when the task needs to get work done across tools, recurring task, browser and CLI and service work and remember this workflow. Preserves evidence with SkillSpec routes, forbids, dependencies, traces, and token-savings reports

Use when the task needs to browse a website with rote, browse Gmail or an email web app with rote, attach to an active browser, inspect logged-in web app state, snapshot or slice a page, click or type in a page and recover a stale browser ref or page lease. Handles browser handoff and page evidence and dependency checks. Requires `skillspec decide` before substrate tools or overlapping low-level skills. Preserves evidence with SkillSpec routes, forbids, dependencies, traces, and token-savings reports

Use when the task needs to run a local command and remember the result, inspect CLI output with provenance, follow a log or process stream, start or observe a background job, capture terminal-sensitive output, crystallize shell work into a TypeScript flow and combine local CLI facts with adapters or browser observations. Handles CLI and shell commands, APIs, MCP/rote adapters, and service connectors, browser handoff and page evidence, external services, process capture, logs and streams, PTY and terminal-sensitive prompts and dependency checks. Requires `skillspec decide` before substrate tools or overlapping low-level skills. Preserves evidence with SkillSpec routes, forbids, dependencies, traces, and token-savings reports

Review code changes by collecting the review target, researching context, checking risks, and reporting findings before summary.

Write conventional commit messages and run the repository's pre-push checks before commit, push, or PR title work.

Read a repository, map what exists, and produce neutral architecture documentation without changing code.

Use for CLI and shell work through rote: running local commands with `rote exec`, capturing stdout/stderr/files, following logs and background processes, checking dependency manifests, mixing adapters/browser/process steps, and crystallizing CLI work into TypeScript flows. Prefer rote shell primitives over raw shell when the command result should be remembered, queried, replayed, or shared.

Multi-agent code review with deep analysis. Orchestrates codebase research, optional web research, parallel Rust engineers, codex second opinion, and general-purpose reviewers into a synthesized report. Use when the user asks to review code, review a PR, review changes, audit code quality, or says "review", "/review", "code review", "check my changes", "review this PR", "review diff". Trigger for ANY code review request, even partial — e.g., "look over this", "anything wrong with these changes", "sanity check".

Use when writing commit messages, creating PR titles, pushing commits, or creating PRs — ensures conventional commit format and that formatting/linting pass before any push

Document and explain the codebase as-is using parallel sub-agents. Use when the user asks to research, explore, map, document, or understand the codebase — including questions like 'how does X work', 'where is Y implemented', 'show me the architecture', 'what does this module do', or any request for codebase-level understanding. Also use when the user says /research_codebase. Even if the user's question seems simple, if it requires reading multiple files or understanding cross-component interactions, use this skill.

Use when the user asks to browse a page.