NestJS Skills: Feature Audit

    1

    Compare a NestJS feature with its roadmap on a specific Git branch and report evidence-backed gaps.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    About this skill

    A free, MIT-licensed agent skill for auditing one NestJS feature against its documented roadmap at an identified Git revision. It traces requirements to source, tests, configuration, and other available evidence, then reports implementation status, gaps, legacy behavior, defects, and blockers.

    The workflow requires a clear feature scope and roadmap in the repository docs or supplied by the user. If the roadmap is missing or unclear, it stops and asks for it rather than inventing requirements. Findings stay tied to one audited branch and revision, with verified facts separated from unverified claims.

    This skill reports findings and does not implement fixes. It includes safe branch-preparation rules: preserve user changes, stop on unsafe Git state, and use normal branch selection and fast-forward updates only when prerequisites are satisfied. Updating from a remote requires network access.

    Requires Git, a NestJS repository, a clear feature roadmap, and a SKILL.md-compatible agent. The package includes the skill, agent metadata, evaluation scenarios, and references for roadmap discovery, evidence classification, and reporting.

    Individual skill version: 1.0.2, from the NestJS Skills v2.2.0 collection by amirtaherkhani. This listing contains Feature Audit only. The original MIT LICENSE is included unchanged. Source and documentation: https://github.com/amirtaherkhani/nestjs-skills

    Requires a clear feature roadmap and a NestJS Git repository. Stops before branch changes on dirty or otherwise unsafe Git state; a user-approved local snapshot can be audited with the limitation recorded. Does not implement fixes. Remote updates require network access.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    Inspects the authorized target repository and roadmap. Terminal/Git may select the target branch and perform a safe fast-forward update, which changes the checkout but does not implement fixes. Remote updates require network access under the host permissions; if unavailable, the workflow reports that freshness is unverified and asks before using a local snapshot.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill automates the comparison between a NestJS feature's code and its documented roadmap, identifying gaps, implementation status, and legacy behaviors by tracing source code and tests back to requirements.

    The skill requires a local NestJS repository, Git, and a SKILL.md-compatible AI agent, along with a clear feature roadmap provided either in the repository documentation or directly by the user.

    To ensure data integrity, the skill separates verified facts from unverified claims and will stop immediately if it encounters an unsafe Git state or if the feature roadmap is missing, rather than hallucinating requirements.

    This package includes version 1.0.2 of the Feature Audit skill, agent metadata, evaluation scenarios, and comprehensive references for evidence classification and reporting.

    The skill uses safe branch-preparation rules, meaning it will only perform fast-forward updates and preserve user changes, but it does require network access if you need it to pull the latest updates from a remote repository.

    No, this skill is strictly for diagnostic purposes; it reports implementation gaps and blockers with evidence-backed findings but does not attempt to write code or implement fixes.

    New in Agents & Orchestration

    Free