Skip to content
TrustedSkillsbeta
Back to all skills

Factory Review

Checked
jwilger·vlatest·other·CC0-1.0

Analyzes factory layouts, processes, and data to identify inefficiencies and suggest optimization improvements.

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 jwilger/agent-skills --skill factory-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

jwilger

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 jwilger/agent-skills at e2f5e19add.

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

Commit
e2f5e19add
Manifest
skills/factory-review/SKILL.md
Scanned
1 file, 177 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 Factory Review skill streamlines and focuses human review during factory-mode builds by providing concise summaries of build data. It structures the review experience using audit trail summaries, PR digests, retrospective syntheses, quality trend reports, and an autonomy tuning interface. The goal is to provide high-signal information quickly, enabling efficient oversight without requiring exhaustive examination of every detail.

When to use it

  • During Phase 3 of factory-mode builds for focused human review.
  • To quickly understand the outcome of a build session based on audit trail data.
  • When needing a summary of changes introduced by merged pull requests (PRs).
  • For identifying recurring issues and areas for improvement from team retrospectives.
  • To adjust configuration settings (.factory/config.yaml) during review, with validation and explanation of implications.

Key capabilities

  • Audit Trail Summary: Provides a dashboard-style summary including slice completion counts, rework rates, gate failure distribution, and pending escalations.
  • PR Digest: Generates one-paragraph summaries for each merged PR detailing changes, the associated vertical slice, engineer pair, gate results, and rework count.
  • Retrospective Synthesis: Aggregates findings from team retrospectives to identify recurring issues, pairing effectiveness, domain hotspots, and process friction.
  • Quality Trend Tracking: Presents trends in key metrics like mutation score, rework rate, cycle time per slice, and gate failure rates compared to the previous build session.
  • Autonomy Tuning Interface: Allows adjustments to .factory/config.yaml with validation and explanation of potential behavioral changes.

Example prompts

  • "Show me the audit trail summary for the last build."
  • "Give me a digest of all merged pull requests in the current build."
  • "What are the recurring causes of rework from recent retrospectives?"
  • "Display quality trend tracking metrics."
  • "I want to increase the autonomy level; what will that change?"

Tips & gotchas

  • The skill relies on data stored within .factory/audit-trail/ and .factory/config.yaml. Ensure these files are populated with relevant information for accurate results.
  • PR digests are designed for quick scanning, aiming to be completed in under a minute per build session.