CtrlK
BlogDocsLog inGet started
Tessl Logo

debug

Run commands inside a remote Docker container via the file-based command relay (tools/debugger). Use when the user says "run in Docker", "run on GPU", "debug remotely", "run test in container", "check nvidia-smi", "run pytest in Docker", or needs to execute any command inside a Docker container that shares the repo filesystem. Requires the user to have started server.sh inside the container first.

76

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%Weight 40%Scale 1-3

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

An efficient, highly actionable skill body that keeps the SKILL.md as an overview with executable examples and defers detail to a clearly signaled one-level reference; no meaningful weaknesses.

DimensionReasoningScore

Conciseness

A lean one-line intro, a single pointer to the full protocol doc, and a compact commented quick-reference block — every token earns its place with no padding or explanation of concepts Claude already knows.

3 / 3

Actionability

Provides concrete, copy-paste-ready bash commands (status, handshake, run, --timeout, cancel, flush) each annotated with its purpose, fully executable rather than pseudocode.

3 / 3

Workflow Clarity

For this simple single-purpose skill the action is unambiguous and sequenced with status/handshake checks before running, satisfying the simple-skill allowance for a top workflow score.

3 / 3

Progressive Disclosure

Well under 50 lines with a clearly signaled one-level reference ("Read tools/debugger/CLAUDE.md for full usage details") and a single organized Quick Reference section, matching the simple-skill allowance.

3 / 3

Total

12

/

12

Passed

Description

90%Weight 40%Scale 1-3

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 strong, specific description with explicit trigger terms and a clear what/when structure; the only soft spot is that it captures essentially one action rather than a range of concrete actions.

Suggestions

Broaden the capability list slightly (e.g., "run, inspect, and cancel commands") to reach the top specificity anchor that rewards multiple concrete actions.

DimensionReasoningScore

Specificity

Names a concrete action and mechanism ("Run commands inside a remote Docker container via the file-based command relay") but lists a single action rather than multiple specific concrete actions, so it falls short of the top anchor.

2 / 3

Completeness

Explicitly answers what it does (run commands in a remote Docker container via file-based relay) and when to use it (a "Use when the user says..." clause with explicit triggers), plus a precondition that the user start server.sh first.

3 / 3

Trigger Term Quality

Includes natural phrases users would actually say — "run in Docker", "run on GPU", "debug remotely", "run test in container", "check nvidia-smi", "run pytest in Docker" — giving strong coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

The narrow niche of remote Docker debugging via a file-based command relay with distinctive triggers makes it unlikely to fire for an unrelated skill.

3 / 3

Total

11

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
NVIDIA/Model-Optimizer
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.