Run an example ($ARGUMENTS) with profiling enabled on hardware and report the swimlane/timing breakdown. Use when the user asks to profile an example on hardware.
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
# Run the example at $ARGUMENTS with profiling enabled on hardware
Detection / isolation procedures referenced below live in
[`../../lib/onboard-detection.md`](../../lib/onboard-detection.md).
1. Locate the test file under `$ARGUMENTS/`: pick the single `test_*.py` that
lives directly in that directory. If none exists, tell the user the
directory is not a scene test and stop.
2. **Precheck + detect platform** (§A) — derive the arch from `$ARGUMENTS`,
gate on real silicon, then read the detected arch into `PLATFORM`.
3. **Select a single idle device** (§C) — or let `task-submit` pick via
`--device auto --device-num 1`.
4. **Run through `task-submit`** (§E, `--device-num 1`):
```bash
python $ARGUMENTS/test_<name>.py -p <platform> -d $TASK_DEVICE --enable-profiling
```
5. If the test passes, report the swimlane output file location in `outputs/`.
6. Summarize the task statistics from the console output (per-function timing
breakdown).
The line at the top of this page pins the label git:20260629.b025b10, 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.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (1180 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
GitHub
hw-native-sys/simpler · 45 stars · license a license file GitHub does not identify · pushed 2026-11-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_uziz5ag6q7rfwx7z
GET https://markdownregistry.com/api/v1/resolve?ref=hw-native-sys/simpler/profile
GET https://markdownregistry.com/api/v1/blob/38c11942387308519c3a3ba158bc3085e0ff8f78bc109c10809dce86b1d456c1
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.
hw-native-sys/simpler · .claude/skills/benchmark/SKILL.md · Benchmark runtime performance on hardware. If the current branch has commits ahead of upstream/main or uncommitted…
hw-native-sys/simpler · .claude/skills/checkout-pr/SKILL.md · Add a remote for a given PR's head repository and checkout a local pr-xxx-work branch. Use when the user wants to work…
hw-native-sys/simpler · .claude/skills/clean-branches/SKILL.md · Remove stale local and remote git branches that have been merged into main. Detects regular merges and squash merges…
hw-native-sys/simpler · .claude/skills/core-swimlane/SKILL.md · Produce a Core swimlane (the L0/intra-core AICore pipeline) for one task — a single kernel or a mix — via the…
hw-native-sys/simpler · .claude/skills/develop-task/SKILL.md · Plan and deliver a complete simpler task with design alignment, an internal dependency graph, parallel agents, reviewed…
hw-native-sys/simpler · .claude/skills/dfx-analyze/SKILL.md · Analyze an onboard run's performance/scheduling/dependency/dump data using simpler's BUILT-IN DFX tools…
hw-native-sys/simpler · .claude/skills/fix-issue/SKILL.md · Implement a GitHub Issue as its assignee or delegated contributor, selecting direct repair or develop-task planning and…
hw-native-sys/simpler · .claude/skills/github-pr/SKILL.md · Create or update a GitHub pull request after committing, rebasing, and pushing changes. Use when the user asks to…
hw-native-sys/simpler · .claude/skills/hbg-bind-phases/SKILL.md · Measure host_build_graph's `bind` phases — the host-side stage between "caller data in place" and "device can start"…
yahyalendani/opus-tuner-claude-skill · skills/profile/SKILL.md · Switch opus-tuner between the dev and creative profiles, or show the active one. Run by the user, never automatically.
qbeka/jev-job-search · .claude/skills/profile/SKILL.md · Check or change the candidate profile, the standing answers, the drafts and the voice guide. Use when the user says…
gufranco/claude-engineering-rules · skills/profile/SKILL.md · Performance profiling and bottleneck identification. Measures database statements and time per request on the running…
