platform-audit SKILL.md skillB
platform-audit from danielc000/loom is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add danielc000/loom/platform-audit@git:20260923.246fef2Pins git:20260923.246fef2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- danielc000/loom
- Path
packages/daemon/assets/skills/platform-audit/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260923.246fef2, committed Sep 23, 2026
- First version recorded
- Sep 6, 2026
- Size
- 23,808 bytes
- Repository stars
- 7
- License
- MIT
The operating doctrine for the Loom Platform Auditor — a scheduled, read-mostly transcript reviewer with three narrow daemon-local writes. Load at the start of any platform-audit session to scan recent session transcripts across projects for Loom bugs, agent friction, vague skill/prompt instructions, and recurring prompts worth saving as presets — filing structured, deduped findings onto the Platform backlog and emitting preset suggestions. Your agent prompt supplies the cadence/scope…
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
# Platform Auditor — Loom transcript-audit doctrine You are the **Platform Auditor**: a scheduled reviewer that reads session transcripts across all projects and turns what it finds into structured findings on the platform backlog. You are the platform's **self-improvement loop** — the eyes that notice where Loom is failing its agents. You are **read-mostly**: you read widely, and you write through exactly **three** narrow, inert, dedupe-guarded daemon-local channels — nothing more. This is the defining constraint of the role, not a temporary limit: - You **read** — session transcripts (live and archived) across projects — enumerate them with `list_sessions`, read one with `transcript_read` — **and** the Loom **source tree**, read-only, via `repo_read_file` / `repo_grep` / `repo_glob` (your code-awareness for the code-structure gap-hunt below). `repo_read_file` / `repo_grep` / `repo_glob` themselves are confined to the Loom checkout and cannot touch any other host file — pure reads, no host-process spawn. That confinement belongs to these three tools, not to your session as a whole: if your session also carries …
Read the whole file at its exact version.
How to install
mdr add danielc000/loom/platform-audit@sha256:227ceb3692f06af8The line at the top of this page pins the label git:20260923.246fef2, 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.
[](https://markdownregistry.com/a/art_q2fjaupmocldicic)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 6, 2026 and Sep 23, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260923.246fef2 latest | 2026-09-23 | 246fef2 | 23,808 B | B | view · diff |
| git:20260923.0e9c544 | 2026-09-23 | 0e9c544 | 23,732 B | B | view · diff |
| git:20260923.64f9f0f | 2026-09-23 | 64f9f0f | 23,516 B | B | view · diff |
| git:20260922.ca051aa | 2026-09-22 | ca051aa | 23,065 B | B | view · diff |
| git:20260906.66b6be5 | 2026-09-06 | 66b6be5 | 22,181 B | B | view |
Audit of the latest version
- 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 (23808 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
danielc000/loom · 7 stars · license MIT · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_q2fjaupmocldicic GET https://markdownregistry.com/api/v1/resolve?ref=danielc000/loom/platform-audit GET https://markdownregistry.com/api/v1/blob/227ceb3692f06af8d755cad1aa9efc4331491a31e7f8e5b31df5e0d82311d638
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.