perf-goal-writer SKILL.md skillA
perf-goal-writer from nvidia/srt-slurm is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add nvidia/srt-slurm/perf-goal-writer@git:20261003.7f76be2Pins git:20261003.7f76be2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- nvidia/srt-slurm
- Path
.agents/skills/perf-goal-writer/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261003.7f76be2, committed Oct 3, 2026
- First version recorded
- Sep 29, 2026
- Size
- 9,905 bytes
- Repository stars
- 93
- License
- a license file GitHub does not identify
Write or refine a ready-to-use /goal prompt for a performance benchmark, regression investigation or optimization campaign. Define measurable targets, a matched baseline, change boundaries, diagnostic evidence and completion criteria. Use for drafting the goal, not executing the campaign.
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
# Write a performance benchmark goal Turn the user's performance question into an actionable goal using an **Analyze → Hypothesize → Verify** loop. Drafting alone does not authorize starting a goal, launching jobs, changing code or publishing results. Honor execution already authorized by the user when a request includes both drafting and action. Use [the goal template](assets/goal-template.md) as a starting point. Scale it to the task: a fixed benchmark comparison does not need an optimization campaign, and an observability feature needs evidence-coverage criteria in addition to any performance target. ## Establish the experiment Read the supplied context and baseline artifacts that are already accessible. Separate facts inspected directly from user-supplied values and unresolved inputs. Capture the information that changes the experiment: | Input | What the goal must make explicit | | --- | --- | | Objective | The behavior to improve or comparison to answer, target workload, and reason for the comparison. | …
Read the whole file at its exact version.
How to install
mdr add nvidia/srt-slurm/perf-goal-writer@sha256:f8a692f41763bf70The line at the top of this page pins the label git:20261003.7f76be2, 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_ds2eyef4xf72bbs5)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Sep 29, 2026 and Oct 3, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261003.7f76be2 latest | 2026-10-03 | 7f76be2 | 9,905 B | A | view · diff |
| git:20260929.9f784fc | 2026-09-29 | 9f784fc | 9,908 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 (9905 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
nvidia/srt-slurm · 93 stars · license a license file GitHub does not identify · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ds2eyef4xf72bbs5 GET https://markdownregistry.com/api/v1/resolve?ref=nvidia/srt-slurm/perf-goal-writer GET https://markdownregistry.com/api/v1/blob/f8a692f41763bf70cbd7b571e61b330134863a5f021ca2d59dadce27e58adde6
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.