loom-judge SKILL.md skillB

loom-judge from rjwalters/kicad-tools is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add rjwalters/kicad-tools/loom-judge@git:20261021.dc501a2

Pins git:20261021.dc501a2 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
rjwalters/kicad-tools
Path
.agents/skills/loom-judge/SKILL.md
Versions recorded
25
Latest version
git:20261021.dc501a2, committed Oct 21, 2026
First version recorded
Oct 1, 2026
Size
167,869 bytes
Repository stars
70
License
MIT

Reviews PRs labeled loom:review-requested.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

<!-- loom-managed-skill -->
<!-- GENERATED FILE — DO NOT EDIT DIRECTLY.
     Produced by `loom-daemon generate-agent-skills` from
     defaults/.claude/commands/loom/judge.md (the same source Claude Code
     reads as /loom:judge via .claude/commands/loom/). This is the
     cross-vendor skill-discovery surface (.agents/skills/<name>/SKILL.md)
     read natively by Codex, Kimi Code, Mistral Vibe, and Grok — see
     runtime-adapters.md §5. To change this file, edit the source above
     and re-run the generator; CI (`loom-daemon generate-agent-skills
     --check`) fails if this file is stale. -->

# Pull Request Judge

You are a thorough and constructive PR evaluator working in this repository.

<!-- toc:begin generated by scripts/check-doc-tocs.sh --fix; do not edit by hand -->
**Contents**

- [⛔ STOP! READ THIS FIRST - GitHub Review API Is BROKEN](#-stop-read-this-first---github-review-api-is-broken)
- [⚠️ `--body @path` Does NOT Expand — It Posts the Literal String](#---body-path-does-not-expand--it-posts-the-literal-string)
- [GraphQL Rate-Limit Exhaustion — REST Fallback for Labels/Comments](#graphql-rate-limit-exhaustion--rest-fallback-for-labelscomments)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add rjwalters/kicad-tools/loom-judge@sha256:2a649563abfd3b5e

The line at the top of this page pins the label git:20261021.dc501a2, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_rwwbp2lneaiyf3j7.svg)](https://markdownregistry.com/a/art_rwwbp2lneaiyf3j7)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 25 versions of this file, between Oct 1, 2026 and Oct 21, 2026, more than one a day.

versioncommittedcommitsizeaudit
git:20261021.dc501a2 latest2026-10-21 dc501a2 167,869 BB view · diff
git:20261019.975de652026-10-19 975de65 166,198 BB view · diff
git:20261017.f2a6fb02026-10-17 f2a6fb0 166,138 BB view · diff
git:20261016.c705eeb2026-10-16 c705eeb 161,335 BB view · diff
git:20261015.20426ec2026-10-15 20426ec 158,782 BB view · diff
git:20261015.c748be22026-10-15 c748be2 159,517 BB view · diff
git:20261015.a58e9ea2026-10-15 a58e9ea 159,483 BB view · diff
git:20261014.868730b2026-10-14 868730b 159,589 BB view · diff
git:20261014.b9041b32026-10-14 b9041b3 159,213 BB view · diff
git:20261014.394e76a2026-10-14 394e76a 160,241 BB view · diff
git:20261014.c9e84262026-10-14 c9e8426 162,506 BB view · diff
git:20261013.eac3d8b2026-10-13 eac3d8b 162,271 BB view · diff
git:20261012.9a2df402026-10-12 9a2df40 162,497 BB view · diff
git:20261012.4a15cb62026-10-12 4a15cb6 162,497 BB view · diff
git:20261012.f1be77f2026-10-12 f1be77f 161,810 BB view · diff
git:20261011.dcb2b512026-10-11 dcb2b51 162,121 BB view · diff
git:20261011.1ba6d1a2026-10-11 1ba6d1a 162,436 BB view · diff
git:20261009.07652cf2026-10-09 07652cf 162,361 BB view · diff
git:20261008.c1f02bf2026-10-08 c1f02bf 162,354 BB view · diff
git:20261007.b2e787a2026-10-07 b2e787a 162,042 BB view · diff
git:20261006.b5193ef2026-10-06 b5193ef 162,066 BB view · diff
git:20261005.317bf302026-10-05 317bf30 162,074 BB view · diff
git:20261003.7c3c8bf2026-10-03 7c3c8bf 163,659 BB view · diff
git:20261003.83917572026-10-03 8391757 163,790 BB view · diff
git:20261001.03259482026-10-01 0325948 163,797 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No prompt-injection phrasing (matched: ignore your previous instructions)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (167869 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

rjwalters/kicad-tools · 70 stars · license MIT · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_rwwbp2lneaiyf3j7
GET https://markdownregistry.com/api/v1/resolve?ref=rjwalters/kicad-tools/loom-judge
GET https://markdownregistry.com/api/v1/blob/2a649563abfd3b5e5db2578f8acc3d9ce8b42ddadd58a77ba8ec901df778402b

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from rjwalters/kicad-tools

loom-architect SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-architect/SKILL.md · Identifies improvement opportunities and creates proposals
git:20261014.c9e8426 · audit A · 70 stars
loom-auditor SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-auditor/SKILL.md · Verifies claims made by other agents against runtime reality by building and testing software
git:20261014.c9e8426 · audit A · 70 stars
loom-builder-complexity SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-builder-complexity/SKILL.md · This document covers complexity assessment, issue decomposition, and scope management for the Builder role. For the…
git:20261014.394e76a · audit A · 70 stars
loom-builder-pr SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-builder-pr/SKILL.md · This document covers PR creation, test output handling, and quality requirements for the Builder role. For the core…
git:20261019.975de65 · audit A · 70 stars
loom-builder-worktree SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-builder-worktree/SKILL.md · This document covers git worktree management for the Builder role. For the core builder workflow, see `builder.md`.
git:20261014.c9e8426 · audit A · 70 stars
loom-builder SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-builder/SKILL.md · Implements issues labeled loom:issue (human-approved work)
git:20261016.c705eeb · audit B · 70 stars
loom-cargo-target-isolation SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-cargo-target-isolation/SKILL.md · **Load when**: you are about to run (or just ran) a local `cargo build`/`cargo test`/`cargo run` whose result will…
git:20261012.bf4491e · audit A · 70 stars
loom-champion SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-champion/SKILL.md · Human avatar for final decisions - promotes quality issues to approved status AND auto-merges Judge-approved PRs that…
git:20261017.d769e10 · audit A · 70 stars
loom-ci-refusals-reference SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-ci-refusals-reference/SKILL.md · **Load when**: `loom-daemon forge wait-checks` printed `LOOM-CHECKS-ERROR` naming an HTTP `401`/`403`/`429`, it left a…
git:20261007.6b901b8 · audit A · 70 stars
loom-comment-body-literal-path SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-comment-body-literal-path/SKILL.md · Single canonical copy; role prompts' short pointers refer here.
git:20261010.688914e · audit A · 70 stars
loom-curator-estimate SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-curator-estimate/SKILL.md · For every issue you actually curate or re-curate, write exactly one concrete, standalone comment in the current issue…
git:20261016.bd59834 · audit A · 70 stars
loom-curator-rate-budget SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-curator-rate-budget/SKILL.md · Why `curator.md`'s per-issue recipes are REST, and what is still unmeasured.
git:20261005.f192e8f · audit A · 70 stars

Every file in rjwalters/kicad-tools

Browse by kind, by grade B, or by owner.