Intended Vs Implemented Claude Skill

Compares a system's intended behavior with its implementation, building an explicit model of expectations to reveal gaps generic scanners may miss.

Published by phurynphuryn/pm-skills/intended-vs-implemented

phuryn

Source assessment

27,155 GitHub stars · Repository push 2026-10-16

Static risk · Low Quality 90/100

Signals describe text in the listed files, not proven runtime behavior. “Not observed” does not mean absent. This is not a security certification.

Shell commands
Not observed
Network references
Not observed
File reading
Not observed
File writing
Not observed
Credential references
Not observed

Scanned files: 1 · Unscanned companion scripts: 0

Inspect scan evidence

    pm-ai-shipping/skills/intended-vs-implemented/SKILL.md

    How the score is calculated

    Documentation 30/40 + Maintenance 25/25 + Stars 20/20 + License 15/15 = 90/100.

    Read the complete formula, filters and limitations

    License scope: repository metadata; check nested source terms. README

    Snapshot: 2026-10-18T08:26:08 UTC · asd-static-v1

    What you are opening

    A public SKILL.md with instructions for an agent. Open the pinned source to inspect its complete scope, dependencies and permissions.

    How to set it up

    1. Open the pinned SKILL.md and read its instructions and any bundled scripts.
    2. Copy the skill folder into your client’s skills directory with the snippet in the install card.
    3. Start a new session and ask for the task the skill describes.

    Before you add it

    • Read the instructions and review any scripts before running them.
    • Check tool access, required credentials and third-party network requests.
    • The source license and any resource-specific terms take precedence.