review-pr is agent-read markdown (skill) from amd-agi/hyperloom: Review a Hyperloom pull request. Invoke with a PR number whenever asked to review, re-review, or sanity-check a PR in this repository. Collects the PR into a scratch directory, selects from rules.md only the rules this diff can trigger, forces a semantic and core-file risk assessment before any finding is written, refutes every finding twice, and publishes an English conclusion to the PR. The output has two parts only: what the PR does, and blocking issues..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Hyperloom PR review
Written for an agent to execute top to bottom. Every step writes an artifact into `$WORK`; a step
that leaves nothing behind is one a review can skip without the skip being visible. `$WORK` defaults
to `/tmp/hl-review-<PR>` and is printed by `fetch.sh`.
## Output contract
The published review has exactly two parts: what the PR does, and blocking issues. Nothing else.
Non-blocking observations are deleted, not softened. Not "note", not "FYI", not "non-blocking
but", not "for reference", not a postscript under the conclusion. If the only way to keep an
observation is to relabel it, it fails the bar and goes.
The bar is one question: **if this is not changed, is the current behaviour wrong?**
Blocking means one of three things, and the repo treats them as equal:
| Kind | What counts |
|---|---|
| Wrong behaviour | correctness, crash, data or precision error, compatibility break, security, performance regression |
| Desync | an operator-observable change the PR description never states; PR title or description does not match the diff at the current head |
…
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
GET https://markdownregistry.com/api/v1/artifacts/art_gohh3ratag4xaqr2
GET https://markdownregistry.com/api/v1/resolve?ref=amd-agi/hyperloom/review-pr
GET https://markdownregistry.com/api/v1/blob/ae69d0dc368ad44c392ebc19c6f2e21c4fab0c1d924335ba77bcb022b609dcde
Your agent 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.
amd-agi/hyperloom · examples/hyperloom-qwen3-14b-fp8-12h-atom/SKILL.md · Run a 12-hour Hyperloom Qwen3-14B-FP8 optimization session on the ATOM serving framework with the per-kernel…
amd-agi/hyperloom · examples/hyperloom-qwen3-14b-fp8-12h-forge/SKILL.md · Run a 12-hour Hyperloom Qwen3-14B-FP8 optimization session with the per-kernel KernelForge backend instead of GEAK. Use…
amd-agi/hyperloom · examples/hyperloom-qwen3-14b-fp8-12h/SKILL.md · Run a 12-hour Hyperloom Qwen3-14B-FP8 optimization session. Use when the user wants a medium-length Hyperloom demo on…
amd-agi/hyperloom · examples/hyperloom-qwen3-8b-3h/SKILL.md · Run a 3-hour Hyperloom Qwen3-8B FRAMEWORK_AGENT (OPTIMIZE) session without the Kernel Agent. Use when the user wants a…
amd-agi/hyperloom · examples/skills/hyperloom-workload-optimizer/SKILL.md · Autonomously optimizes end-to-end LLM inference throughput on AMD Instinct GPUs and reports a validated gain, using the…
amd-agi/hyperloom · src/hyperloom/agents/critic/SKILL.md · Critic layer for the inference optimizer. Use when Conductor asks
for a Critic Review verdict on Orchestration or…
openonion/connectonion · connectonion/useful_skills/review-pr/SKILL.md · Review GitHub pull requests. Use when user says "review PR", "review pull request", or "/review-pr".
fcakyon/claude-codex-settings · plugins/github-dev/skills/review-pr/SKILL.md · This skill should be used when user asks to "review a PR", "review pull request", "review this pr", "code review this…
go-to-k/cdkd · .claude/skills/review-pr/SKILL.md · Recommend the right reviewer set for a PR from what it touches. Outputs a concrete plan (1 reviewer by default, plus…
doodledood/manifest-dev · claude-plugins/manifest-dev-tools/skills/review-pr/SKILL.md · Autonomous PR review that posts high-signal, human-voiced comments under your account. Use when reviewing someone…
stbenjam/skillsaw · tests/fixtures/content/inconsistent-terminology-registers/.claude/skills/review-pr/SKILL.md · Review an open PR before approving it
