CtrlK
BlogDocsLog inGet started
Tessl Logo

tao-run-on-brev

Brev managed GPU instances with Docker support. Use when running TAO training, evaluation, or inference on Brev GPU instances, managing Brev deployments, or dispatching TAO jobs through the Brev CLI. Trigger phrases include "run on Brev", "Brev GPU instance", "submit job to Brev", "Brev CLI deployment".

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An actionable, well-sequenced operational guide with strong validation and error-recovery patterns, hindered mainly by repeated auth guidance and a monolithic structure that underuses the bundled reference file.

Suggestions

Consolidate the repeated headless/token-login guidance into one Authentication section and reference it from Preflight and Error Patterns instead of restating it.

Split the Error Patterns and Preflight script into reference files (and link to them) so the SKILL.md body stays a lean overview, or reference the existing references/skill_info.yaml from the body.

Tighten the Preflight bash block by moving explanatory comments into prose so the script reads as executable rather than annotated.

DimensionReasoningScore

Conciseness

Dense with operational gotchas Claude would not know, but headless/token-login guidance is repeated across the Preflight script comments, Authentication, Headless, and Error Patterns sections and could be consolidated.

2 / 3

Actionability

Provides concrete, copy-paste-ready commands — preflight checks, `brev create` with placement IDs, `docker run`, the readiness-wait loop, and `brev delete`.

3 / 3

Workflow Clarity

Clear Preflight → Launch Preflight → Instance Lifecycle → Docker → Cleanup sequence with explicit validation checkpoints (preflight exits, readiness poll) and an Error Patterns section supplying fix→retry feedback loops.

3 / 3

Progressive Disclosure

A single ~240-line monolithic body with no internal file splits; the bundled references/skill_info.yaml is present but never referenced from the body, and the only pointer is to an external skill.

2 / 3

Total

10

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A concise, third-person description that names concrete capabilities and gives explicit natural-language triggers covering both what and when. It is distinctive and unlikely to conflict with other skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'running TAO training, evaluation, or inference', 'managing Brev deployments', 'dispatching TAO jobs through the Brev CLI' — rather than vague language.

3 / 3

Completeness

Clearly answers both 'what' (Brev managed GPU instances with Docker support for TAO workloads) and 'when' via an explicit 'Use when…' clause with triggers.

3 / 3

Trigger Term Quality

Explicit natural trigger phrases ('run on Brev', 'Brev GPU instance', 'submit job to Brev', 'Brev CLI deployment') that users would plausibly say.

3 / 3

Distinctiveness Conflict Risk

Narrow Brev + TAO niche with distinct triggers makes it unlikely to fire for or conflict with unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
NVIDIA/skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.