CtrlK
BlogDocsLog inGet started
Tessl Logo

sdf

SDFormat/SDF model and world generation, validation, and simulator handoff. Use for `.sdf` files, SDFormat XML, Python `gen_sdf()` sources, models, worlds, links, joints, poses, frames, inertials, visual/collision geometry, mesh URIs, sensors, lights, physics, plugins, includes, Gazebo, static SDF review, or simulator-specific metadata. Do not use for signed-distance-field geometry.

73

Quality

90%

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

86%Weight 40%Scale 1-5

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

A well-structured, actionable skill body with executable commands, a concrete report shape, and clean progressive disclosure to real reference files. The main gap is an explicit error-recovery feedback loop in the workflow.

Suggestions

Add an explicit validate→fix→re-validate feedback loop to the Workflow (e.g., 'If bundled validation or gz sdf --check reports errors, fix the generator source and regenerate before reporting'), which would lift workflow_clarity to 5 for batch/generation work.

Trim the `python` interpreter-placeholder paragraph and the "Static rendering does not execute SDF plugins" aside into a single concise note, or move them into references/implementation-notes.md, to tighten conciseness.

Consider adding one inline minimal gen_sdf() example or a pointer to references/examples.md inside the Commands section so a first-time user has an immediately runnable reference.

DimensionReasoningScore

Conciseness

Mostly lean and assumes Claude's competence (no explanation of what SDF or Gazebo is), but a few sentences pad slightly — e.g., the `python` interpreter-placeholder note and "Static rendering does not execute SDF plugins" — which could be trimmed without losing clarity.

4 / 5

Actionability

Provides copy-paste-ready commands covering the common cases (`python scripts/sdf path/to/source.py`, `-o`, `SOURCE.py=OUTPUT.sdf` multi-target, `--gz-check auto/required/never`) plus a concrete required-report template with an explicit example.

5 / 5

Workflow Clarity

A clear 9-step sequence with explicit validation checkpoints (bundled validation, gz check, simulator load, joint motion, plugin startup) and a report checklist, but it lacks an explicit validate→fix→re-validate feedback loop, which keeps it just below 5 for batch/generation work.

4 / 5

Progressive Disclosure

SKILL.md is a well-organized overview with a References section pointing to 12 one-level-deep reference files, all of which exist in ./references/, giving clear and easy navigation without nested indirection.

5 / 5

Total

18

/

20

Passed

Description

95%Weight 40%Scale 1-5

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 description that answers both what and when with concrete trigger terms and file extensions, while proactively guarding against the signed-distance-field acronym conflict. Minor room to make the named actions more granular.

DimensionReasoningScore

Specificity

Names the domain ("SDFormat/SDF") and lists several concrete actions — "model and world generation, validation, and simulator handoff" — but the actions are somewhat high-level rather than granular, leaving minor coverage gaps versus a fully comprehensive action list.

4 / 5

Completeness

Clearly answers "what" ("generation, validation, and simulator handoff") and "when" via the explicit "Use for `.sdf` files, SDFormat XML, ..." trigger clause, plus a "Do not use for" boundary clause.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including the file extension (`.sdf`), synonyms ("SDFormat XML", "SDF"), the tool name "Gazebo", and an exhaustive list of SDF elements (links, joints, poses, frames, sensors, plugins) a user would naturally mention.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (SDFormat simulator documents) and the explicit "Do not use for signed-distance-field geometry" clause disambiguates the SDF acronym collision, minimizing conflict risk.

5 / 5

Total

19

/

20

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
JimmyPang02/open-replicator
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.