trace-review-app SKILL.md skillA
trace-review-app from calibre-labs/reforge-ai-evals is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add calibre-labs/reforge-ai-evals/trace-review-app@git:20261028.d1290e3Pins git:20261028.d1290e3 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- calibre-labs/reforge-ai-evals
- Path
skills/trace-review-app/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261028.d1290e3, committed Oct 28, 2026
- First version recorded
- Oct 19, 2026
- Size
- 5,915 bytes
- Repository stars
- 94
- License
- MIT
Design and build a custom trace review app for one AI product: a single-page tool where the team reads traces, writes notes, labels pass or fail, tags trace codes and exports the results for other skills. Built around that product's own trace shape, rubric and failure modes, and set up so reviewing becomes a habit (a queue, progress, streaks, quick keys). Use this skill whenever someone asks to "build a trace viewer", "make an annotation tool", "set up a review page for our traces…
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
# Trace review app skill Generic trace tools show every trace the same way and leave the judging to the reader. Teams open them, spend too long learning them, and stop reviewing. A review app built for one product shows what matters for that product first, asks the questions its rubric asks, and makes a review session short enough to do every day. This skill designs that app and builds it as one HTML file that opens from a folder, with no hosting and no account. The person still does the reading and the judging. The app makes that faster and keeps the results in a shape the other skills can use. ## Inputs | Input | Required | Typical form | |---|---|---| | Sample traces | Yes | A folder of trace files (JSON or JSONL), five or more | | What the product does | Yes | The PRD, or a few sentences from the user | | Rubric | Helpful | The eval rubric, so labels can be per rubric line | | Trace codes | Helpful | A trace codes file from `trace-codes`, used as tags | | Who reviews | Helpful | PMs, domain experts, support leads, and how many | Look for these in the working folder before asking. Read at least five traces before designing …
Read the whole file at its exact version.
How to install
mdr add calibre-labs/reforge-ai-evals/trace-review-app@sha256:a2468a24dd3a1ad6The line at the top of this page pins the label git:20261028.d1290e3, 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_cm4hldqotf5fs6zx)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Oct 19, 2026 and Oct 28, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261028.d1290e3 latest | 2026-10-28 | d1290e3 | 5,915 B | A | view · diff |
| git:20261019.b5e5462 | 2026-10-19 | b5e5462 | 5,837 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5915 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 prompt-injection phrasing
- 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
Source
calibre-labs/reforge-ai-evals · 94 stars · license MIT · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_cm4hldqotf5fs6zx GET https://markdownregistry.com/api/v1/resolve?ref=calibre-labs/reforge-ai-evals/trace-review-app GET https://markdownregistry.com/api/v1/blob/a2468a24dd3a1ad64968f9ec21e69c98f76d95bf08a2be7a4be849bf15e14d92
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.