peer-review SKILL.md skillA
peer-review from a-lottes/aspark is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add a-lottes/aspark/peer-review@git:20261028.486dc7fPins git:20261028.486dc7f in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- a-lottes/aspark
- Path
skills/peer-review/SKILL.md- Versions recorded
- 6
- Latest version
- git:20261028.486dc7f, committed Oct 28, 2026
- First version recorded
- Jul 13, 2026
- Size
- 4,607 bytes
- Repository stars
- 24
- License
- MIT
Start the Review phase of the SPARK loop: the Reviewer audits the diff produced by /increment — plan conformance, correctness, edge cases, security, test quality — and writes the review report. Use after /increment reports done, or to re-review after fixes.
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
# /peer-review — Review (Reviewer)
You are running the **code review** ceremony. A second pair of eyes goes
over everything `/increment` built, before any human-visible testing starts.
## Input
Optional argument: the feature name. Resolve as usual.
## Steps
1. **Check the gate.** The plan at `.spark/<feature-name>/plan.md` must show
all tasks `done`. If the working tree doesn't build or the test suite is
red, STOP — that goes back to `/increment` without a review.
Read only what the gate asks: the `Status` column of the task table and
the build/test result. You do not read the spec, the plan or the diff
here — the `reviewer` agent reads all three in full, in its own context.
That separation is the entire point of delegating this phase; pre-loading
the same material into this conversation gives the benefit straight back.
- **Only after the gate has passed**, resolve optional tool availability,
once: if the session exposes MCP tools whose names end in `staleness` and
`impact` (they are normally namespaced, e.g.
`mcp__aspark-graph__staleness`), treat that as the available surface and
…Read the whole file at its exact version.
How to install
mdr add a-lottes/aspark/peer-review@sha256:0706efc9b98ea02aThe line at the top of this page pins the label git:20261028.486dc7f, 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_fkeniknolx5edd6v)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Jul 13, 2026 and Oct 28, 2026, about one every 21 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261028.486dc7f latest | 2026-10-28 | 486dc7f | 4,607 B | A | view · diff |
| git:20261027.0c9144a | 2026-10-27 | 0c9144a | 4,338 B | A | view · diff |
| git:20260917.3f27eda | 2026-09-17 | 3f27eda | 4,024 B | A | view · diff |
| git:20260727.8eadc99 | 2026-07-27 | 8eadc99 | 4,021 B | A | view · diff |
| git:20260715.4c780f6 | 2026-07-15 | 4c780f6 | 2,353 B | A | view · diff |
| git:20260713.ca08cab | 2026-07-13 | ca08cab | 2,122 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 (4607 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
a-lottes/aspark · 24 stars · license MIT · pushed 2026-10-29 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_fkeniknolx5edd6v GET https://markdownregistry.com/api/v1/resolve?ref=a-lottes/aspark/peer-review GET https://markdownregistry.com/api/v1/blob/0706efc9b98ea02ae0e93048cc7665db953c84e848bb5bf0c8ec6c3f94419caa
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.