MIOpen Deep Review
$SKILL is the directory this skill was loaded from (the directory containing this
SKILL.md). You are the orchestrator: execute RUNBOOK.md. You pin the change, dispatch
scouts, lanes and verifiers, merge their output and write the report; you do not review
code. Your formats are in report.md; RUNBOOK.md Fan out says
what each agent reads, and lanes/ holds the briefs. RUN builds MIOpen standalone from
projects/miopen and runs miopen_gtest (lanes/build-validate.md).
Prerequisites: network access, an authenticated gh with read access, git 2.38 or later (pin.py uses git merge-tree --write-tree), and Python 3 (it runs the scripts under
$SKILL/scripts/); pre-commit and pytest for the lanes that run validators. RUN and verifiers also need
a ROCm install (/opt/rocm or ROCM_PATH) with the MIOpen dependencies rbuild prepare installs (projects/miopen/requirements.txt), CMake, Ninja, dvc for the kernel databases, and about 60 GB free in $SCRATCH; without them defect and
test-gap findings stay UNVERIFIED and the review closes only through human
ACCEPTED-RISK decisions, recorded with ledger.py set (PIN.md records Build host).
Most of miopen_gtest needs a GPU; the CPU_* suites and the configure, ABI and naming checks do not.
Platforms: Linux. MIOpen's Windows build is exercised only through TheRock; the ROCK lane reads it, nothing here builds it.
Entry contract
Ask for what is missing; record it in PIN.md:
| Input |
Notes |
| Target |
PR URL or number, branch:<name>, or <base>..<head>; intent:<file> (what it is for, how tested, Known issues; required without a PR) holds the intent document, whose Known issues section lists open items the author already knows, numbered K1, K2 and so on, and never renumbered; without a PR, M4 and M5 are N/A (no PR) (policy.md M-rules) |
evidence:<dir>, scratch:<dir>, clone:<dir> |
$EVIDENCE outside the product tree; disposable $SCRATCH; optional clone (default $SCRATCH/clone) |
terms:<file>, knowledge:<dir> |
Optional private terms, one fixed string per line, outside the repository; optional $KNOWLEDGE store |
round:<N> |
Default: one more than the highest $EVIDENCE/r<k>/; 1 when none |
prior:<dir> |
Optional published record of earlier rounds that $EVIDENCE lacks (LEDGER.md and r<k>/); RUNBOOK.md Iterate seeds $EVIDENCE from it |
| Agent limits |
Ask the user or the host for Agents: (maximum concurrent agents), Cores: (CPU cores for builds and tests), GPU: (the local gfx architecture, or none) and Mutation: (a host recipe for mutating a built tree, or none); the skill assumes no values. They go into dispatch-context.md (RUNBOOK.md Fan out) |
| Scope notes |
Ask the user for scope notes the change's description does not state, such as areas being deprecated (the rocMLIR solvers), or none. Free text; it goes into dispatch-context.md as Scope: and is informational unless it says "do not file findings in " (lanes/common.md Rules) |
Local builds and host-only tests are allowed. GPU, remote or shared compute, and every write
to GitHub, Jira or a remote branch need the user's approval for that exact action. The
review is advisory: the user posts the draft comments. Write only $EVIDENCE, $KNOWLEDGE
and $SCRATCH, never the product tree.
Completion
A round is complete when its gates hold and REPORT.md and LEDGER.md exist for the head.
The review is closed (Closure: CLOSED) when no BLOCKING or IMPORTANT finding is OPEN
or UNVERIFIED and no STOP or decision is unresolved. Otherwise Closure: OPEN lists what
blocks it and Iterate starts the next round; the user decides when to stop.
1---2name: miopen-deep-review3description: "Multi-agent deep review of a MIOpen PR, branch or commit range. Scouts map each affected area, focused reviewer lanes run in parallel, every finding is verified by source proof, reproduction or mutation, and a ledger carries findings across rounds until no blocking or important one stays open. For a lighter single-pass review, use miopen-review."4argument-hint: "[<PR URL or number> | branch:<name> | <base>..<head>] evidence:<dir> scratch:<dir> [clone:<dir>] [intent:<file>] [terms:<file>] [knowledge:<dir>] [round:<N>] [prior:<dir>]"5allowed-tools: Bash, Read, Write, Edit, Grep, Glob, Task6metadata:7 source: https://skillmd.com/skills/rocm/miopen-deep-review8---910# MIOpen Deep Review1112`$SKILL` is the directory this skill was loaded from (the directory containing this13`SKILL.md`). You are the orchestrator: execute [RUNBOOK.md](RUNBOOK.md). You pin the change, dispatch14scouts, lanes and verifiers, merge their output and write the report; you do not review15code. Your formats are in [report.md](report.md); [RUNBOOK.md](RUNBOOK.md) *Fan out* says16what each agent reads, and `lanes/` holds the briefs. `RUN` builds MIOpen standalone from17`projects/miopen` and runs `miopen_gtest` ([lanes/build-validate.md](lanes/build-validate.md)).1819Prerequisites: network access, an authenticated `gh` with read access, `git` 2.38 or later (`pin.py` uses `git merge-tree --write-tree`), and Python 3 (it runs the scripts under20`$SKILL/scripts/`); `pre-commit` and `pytest` for the lanes that run validators. `RUN` and verifiers also need21a ROCm install (`/opt/rocm` or `ROCM_PATH`) with the MIOpen dependencies `rbuild prepare` installs (`projects/miopen/requirements.txt`), CMake, Ninja, `dvc` for the kernel databases, and about 60 GB free in `$SCRATCH`; without them `defect` and22`test-gap` findings stay `UNVERIFIED` and the review closes only through human23`ACCEPTED-RISK` decisions, recorded with `ledger.py set` (`PIN.md` records `Build host`).24Most of `miopen_gtest` needs a GPU; the `CPU_*` suites and the configure, ABI and naming checks do not.2526Platforms: Linux. MIOpen's Windows build is exercised only through TheRock; the `ROCK` lane reads it, nothing here builds it.2728## Entry contract2930Ask for what is missing; record it in `PIN.md`:3132| Input | Notes |33|---|---|34| Target | PR URL or number, `branch:<name>`, or `<base>..<head>`; `intent:<file>` (what it is for, how tested, `Known issues`; required without a PR) holds the intent document, whose `Known issues` section lists open items the author already knows, numbered `K1`, `K2` and so on, and never renumbered; without a PR, M4 and M5 are `N/A (no PR)` ([policy.md](policy.md) *M-rules*) |35| `evidence:<dir>`, `scratch:<dir>`, `clone:<dir>` | `$EVIDENCE` outside the product tree; disposable `$SCRATCH`; optional clone (default `$SCRATCH/clone`) |36| `terms:<file>`, `knowledge:<dir>` | Optional private terms, one fixed string per line, outside the repository; optional `$KNOWLEDGE` store |37| `round:<N>` | Default: one more than the highest `$EVIDENCE/r<k>/`; 1 when none |38| `prior:<dir>` | Optional published record of earlier rounds that `$EVIDENCE` lacks (`LEDGER.md` and `r<k>/`); [RUNBOOK.md](RUNBOOK.md) *Iterate* seeds `$EVIDENCE` from it |39| Agent limits | Ask the user or the host for `Agents:` (maximum concurrent agents), `Cores:` (CPU cores for builds and tests), `GPU:` (the local `gfx` architecture, or none) and `Mutation:` (a host recipe for mutating a built tree, or none); the skill assumes no values. They go into `dispatch-context.md` ([RUNBOOK.md](RUNBOOK.md) *Fan out*) |40| Scope notes | Ask the user for scope notes the change's description does not state, such as areas being deprecated (the rocMLIR solvers), or `none`. Free text; it goes into `dispatch-context.md` as `Scope:` and is informational unless it says "do not file findings in <area>" ([lanes/common.md](lanes/common.md) *Rules*) |4142Local builds and host-only tests are allowed. GPU, remote or shared compute, and every write43to GitHub, Jira or a remote branch need the user's approval for that exact action. The44review is advisory: the user posts the draft comments. Write only `$EVIDENCE`, `$KNOWLEDGE`45and `$SCRATCH`, never the product tree.4647## Completion4849A round is complete when its gates hold and `REPORT.md` and `LEDGER.md` exist for the head.50The review is closed (`Closure: CLOSED`) when no `BLOCKING` or `IMPORTANT` finding is `OPEN`51or `UNVERIFIED` and no `STOP` or decision is unresolved. Otherwise `Closure: OPEN` lists what52blocks it and *Iterate* starts the next round; the user decides when to stop.