dimensional-analysis

Automated dimensional analysis — Buckingham Pi theorem, non-dimensionalization, unit validation with pint, and characteristic scale estimation. Use before any physics computation to verify consistency and reduce parameter space.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

65%

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

A code-rich, actionable skill body with five complete executable workflows and useful reference tables, but it is a monolithic print-heavy file that could be tightened and split into reference files. The workflows are clear as standalone recipes but lack a sequenced, checkpointed process.

Suggestions

Tighten conciseness by removing the redundant Overview (it restates the description) and trimming the print-heavy educational output in the examples to only what demonstrates the result.

Split the dimensionless-numbers and fundamental-dimensions reference tables (and optionally the longer worked examples) into a references/ file, keeping SKILL.md as a concise overview — this moves progressive_disclosure toward a well-signaled one-level structure.

Add a short sequenced workflow with validation checkpoints (e.g. define variables → build dimension matrix → verify rank → derive Pi groups → check each is dimensionless) so the techniques read as a guided process rather than five independent recipes.

Dimension	Reasoning	Score
Conciseness	Mostly efficient code-focused content, but the Overview restates the description and the examples are print-heavy with educational commentary (e.g. formatted dimension-matrix prints, "# → [kg·m²/s²] = [J] ✓" result restatements) that could be trimmed.	2 / 3
Actionability	All five workflows are complete, executable Python with imports, function definitions, and runnable examples — copy-paste ready rather than pseudocode.	3 / 3
Workflow Clarity	The five sections are numbered and individually clear, but they are independent recipes with no overarching sequence and no validate→fix→retry checkpoints linking them.	2 / 3
Progressive Disclosure	Sections are well-organized, but the skill is a ~295-line monolithic single file with no external references, and reference material like the dimensionless-numbers table and detailed examples is inline content that could be split out.	2 / 3
	Total	9 / 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 strong, specific description that states concrete capabilities, gives an explicit when-to-use trigger in third person, and occupies a distinctive niche with low conflict risk. It does not over-claim or pad with fluff.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "Buckingham Pi theorem, non-dimensionalization, unit validation with pint, and characteristic scale estimation" — rather than vague domain-only language, matching the anchor that lists several specific concrete actions.	3 / 3
Completeness	Answers both what (the four techniques) and when, with an explicit trigger clause: "Use before any physics computation to verify consistency and reduce parameter space."	3 / 3
Trigger Term Quality	Uses natural practitioner terms a user would actually say — "dimensional analysis", "Buckingham Pi", "non-dimensionalization", "unit validation", "physics computation" — giving good coverage of the natural vocabulary for this niche.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche with distinctive named methods (Buckingham Pi, pint unit validation) and a specific trigger (before physics computation), making it unlikely to fire for the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/physics/dimensional-analysis/SKILL.md
Commit: 52845c3

Reviewed: about 10 hours ago

Table of Contents

Discovery Implementation Validation

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.