agentrel

approval-gates

Classify every tool an AI agent can call as safe to run automatically or requiring human approval, and find the destructive operations that currently have no gate. Checks whether MCP tool annotations match real behaviour, flags tools whose description understates what they do, and produces a permission policy you can adopt. Works on an MCP server, a tool definition file, an OpenAPI spec, or agent tool-handler source. Use when asked whether an agent surface is safe, to review agent permissions or tool authorization, to add human-in-the-loop boundaries, or before letting an agent act on production systems.

docs-architect

Audit the information architecture of a documentation set against what developers and AI assistants actually need, and report what is missing. Maps existing pages to a reference model, finds gaps and orphans, checks whether code examples run, and evaluates machine readability including llms.txt and clean-markdown access. Optionally drafts the missing quickstart. Works on a docs directory, a documentation site, or a repository README. Use when asked to review or restructure documentation, to find documentation gaps, to make docs AI-readable or agent-readable, or when docs exist but developers still cannot find what they need.

feature-to-assets

Turn one shipped feature into the full set of adoption assets that make it discoverable and usable — reference docs, a how-to guide, a runnable example, a changelog entry, an MCP tool definition, a troubleshooting entry, and the announcement copy. Reads the actual implementation so the output describes what the code does rather than what a ticket claimed. Drafts each asset and reports which ones the feature genuinely needs. Use after shipping a feature, when asked to document or announce a new capability, to produce launch or release content, or when a feature exists in code but nowhere else.

surface-audit

Score whether an API, SDK, or documentation surface can actually be used by developers and AI agents, then rank the gaps by impact. Audits the API contract, documentation, time-to-first-value, SDKs and examples, MCP tooling, auth and permissions, and observability, and writes a report with a remediation sequence. Works on a local repo, an OpenAPI or GraphQL schema, a docs directory, or a public developer site. Use when asked whether a product is agent-ready or developer-ready, to audit or score a developer surface, to find adoption or integration friction, or to review an API before exposing it to AI agents.

ttfv-trace

Measure how long a cold developer needs to get from landing page to a first successful API call, and report exactly where the time goes. Walks the quickstart step by step as a first-time reader would, times each step, records every blocker and undocumented prerequisite, and grades the result against published time-to-first-call benchmarks. Use when asked how long onboarding takes, to measure or improve time to first value or time to first call, to find onboarding and quickstart friction, or to test whether a getting-started guide actually works.

registry-presence

Check where a product is listed across the registries agents and coding tools actually resolve — the official MCP Registry, GitHub's MCP Registry, mcp.so, Smithery, Glama, skills.sh, npm, PyPI — and whether the machine-readable entry points a crawler expects are present: llms.txt, AGENTS.md, a documented MCP endpoint. Reports a presence matrix, the exact submission path for every gap, and never guesses: an unreachable registry is reported unknown, not absent. Use when asked whether a product is discoverable by AI agents or assistants, where to list an MCP server, why agents never recommend a product, or to audit agent-facing distribution before a launch.

skill-forge

Draft a publishable agent skill for your own product — the artifact that teaches Claude Code, Cursor, Copilot, and every other coding agent how to use your API or SDK correctly. Reads the real surface, picks the job the skill should do, and writes a SKILL.md with a dispatcher-grade description, references split out for progressive disclosure, install lines for both distribution channels, and a validation checklist. Drafts only, into a staging directory. Use when asked to create or publish a skill for a product, to make a product usable by coding agents, to ship an official integration for Claude Code or Cursor, or when an agent keeps writing wrong code against an API.

snippet-verify

Execute the code in your documentation and report which blocks actually run. Extracts every fenced snippet from a docs directory, README, MDX tree, or public docs URL, classifies each as runnable, credential-blocked, or illustrative, runs the runnable ones in a throwaway workspace against the versions you actually publish, and reports a pass rate with the real error for every failure. Use when asked whether the documentation still works, to verify code samples or quickstart steps, to check examples against a new release, before a launch, or when developers report that the docs do not run.