Skip to content
TrustedSkillsbeta
Back to all skills

Intent Review

Checked
arcblock·vlatest·other·MIT

Analyzes user requests to identify underlying goals and potential misunderstandings for improved task completion.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add arcblock/idd --skill intent-review -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

arcblock

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned arcblock/idd at d46fc54044.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
d46fc54044
Manifest
skills/intent-review/SKILL.md
Scanned
1 file, 198 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The Intent Review skill provides an interactive, section-level approval process for Intent files. It helps AI agents manage and track changes to these files by guiding users through a review workflow. The tool identifies sections within a file and prompts the user to approve, lock (requiring explicit human agreement), or skip them, ensuring consistency and controlled modifications. This is particularly useful in development workflows where clear approval processes are needed for specific code sections.

When to use it

  • Reviewing newly created Intent files after generation by tools like intent-interview.
  • Approving changes made to existing Intent files before they are integrated into a larger system.
  • Ensuring that critical sections of an Intent file (e.g., module boundaries, data structures) adhere to defined standards and require explicit approval.
  • Managing development workflows where modifications need to be tracked and approved by specific individuals.
  • Batch reviewing multiple Intent files within a project using the /intent-review --all command.

Key capabilities

  • Section-level approval: Reviews Intent documents at a granular section level.
  • Three states: Manages sections with statuses of LOCKED (requires human confirmation), REVIEWED (allows modification with notification), and DRAFT (free to modify).
  • Interactive review prompts: Uses AskUserQuestion to present each unmarked section for approval, offering options to lock, review, or skip.
  • Automated marking: Automatically adds markers (::: locked, ::: reviewed, ::: draft) to Intent files based on user choices.
  • History tracking: Provides a history of changes and approvals for each section using /intent-review --history.

Example prompts

  • /intent-review src/core/intent/INTENT.md - Reviews a specific Intent file.
  • /intent-review (when in the src/chambers/terminal directory) - Reviews the default Intent file within the current module.
  • /intent-review --all - Reviews all Intent files in the project.

Tips & gotchas

  • The skill prioritizes finding Intent files first by user-specified path, then intent/INTENT.md in the current directory, and finally INTENT.md in the current directory.
  • LOCKED sections require explicit human approval for any modifications. Be mindful of this when making changes.
  • The skill can detect if a LOCKED section has been modified and will prompt for acceptance of those changes before proceeding.