CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dimensional

Build and operate DimOS apps and blueprints with the dimos CLI and Python API, and inspect real sensor and memory results.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./dimos/agents/harness/skills/dimensional/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

An exceptionally lean, highly executable operational guide with concrete commands, explicit validation guidance (replay-mode validation, try-on-real-data), and well-signaled one-level deferrals to the dimos-runtime skill and checkout docs. The only notable gaps are the absence of a runnable Python example and of section headers to aid navigation of the dense bullet list.

DimensionReasoningScore

Conciseness

The ~25-line body is maximally dense and operational — commands, caveats, and inline JSON schemas with zero padding and no explanation of concepts Claude already knows. Every token earns its place, matching the lean-and-efficient anchor; nothing is trimmable.

5 / 5

Actionability

Gives copy-paste commands ("dimos run BLUEPRINT --daemon", "dimos --replay run unitree-go2 --daemon") and concrete API names ("Dimos.connect()", "app.list_rpcs()", "materialize()", "Space.to_svg()"). Not a 5: the Python side lacks a runnable snippet (deferred to docs/usage/python-api.md) and list_runs()/stop_entry() are named but not demonstrated.

4 / 5

Workflow Clarity

Sequences are present (run --daemon then status/log/stop; connect then list_rpcs/describe; materialize once then derive) with explicit validation checkpoints — "start with the unitree-go2 blueprint in replay mode" and "Try a memory operation on real data before you rely on it" — plus a feedback loop ("check its --help"). Not a 5 because sequences are implicit rather than ordered steps with recovery guidance.

4 / 5

Progressive Disclosure

Deferrals are one level deep and clearly signaled ("read the dimos-runtime skill", "docs/usage/python-api.md in the checkout explains the API") and no bundle files are nested. Not a 5: the body has no section headers — topic bullets only — and the dense file-visibility/frame-index material is inlined without navigational structure.

4 / 5

Total

17

/

20

Passed

Description

66%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 concrete, third-person description that names specific tools and actions within a distinctive niche, but it omits any explicit "when to use" trigger guidance, which both caps completeness and leaves trigger-term coverage short of comprehensive. Adding a Use-when clause referencing natural user phrases (robot runs, sensor data, memory replay, blueprints) would lift the two weakest dimensions.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user mentions DimOS, dimos CLI, robot blueprints, sensor/memory data, or asks to run or inspect a DimOS system."

Broaden natural trigger terms to include user-facing vocabulary like "robot", "run", "hardware", "replay", and "point cloud" that the body covers but the description omits.

Mention the runtime/robot-operation scope distinction (vs. the dimos-runtime skill) so the description signals when this skill vs. the sibling applies.

DimensionReasoningScore

Specificity

Lists several concrete actions — "Build and operate DimOS apps and blueprints", "inspect real sensor and memory results" — and names the interfaces ("the dimos CLI and Python API"), matching the several-specific-actions anchor. It is not a 5 because coverage omits run/status/memory-stream/replay operations, and not a 3 because it goes beyond 1-2 actions with named tools.

4 / 5

Completeness

The "what" is clear (build/operate/inspect with dimos CLI and Python API), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not a 2 because the "what" half is concrete rather than vague.

3 / 5

Trigger Term Quality

Contains good natural domain keywords users would say: "DimOS", "apps", "blueprints", "dimos CLI", "Python API", "sensor", "memory". Not a 5 because common variations such as "robot", "run", "hardware", "replay", or "point cloud" are missing; better than a 3 since coverage of the domain's natural terms is solid.

4 / 5

Distinctiveness Conflict Risk

"DimOS apps and blueprints" carves out a clear niche with distinct triggers, so conflict risk is low. Not a 5 because the sibling dimos-runtime skill covers the same ecosystem with some overlap; clearly more distinct than the score-3 anchor.

4 / 5

Total

15

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

dimensionalOS/dimos

Path

dimos/agents/harness/skills/dimensional/SKILL.md

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.