uncertainty-and-units

Track physical units and propagate measurement uncertainty in scientific calculations using pint and uncertainties. Use for unit conversion and dimensional checking, GUM uncertainty budgets, Type A and Type B evaluation, coverage factors and expanded uncertainty, Monte Carlo propagation, significant-figure and plus-minus reporting, error propagation through curve fits, CODATA constants, auditing Python code for stripped units or broken uncertainty propagation, and order-of-magnitude plausibility checks using dimensionless groups (Reynolds, Peclet, Damkohler, Knudsen, Biot, Womersley), characteristic scales such as diffusion time or Debye length, and observed magnitude ranges. Trigger on "is this number physically reasonable", "sanity check these units", "what regime is this flow in", or a result that looks off by orders of magnitude.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%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 strong, actionable body with executable commands, an explicit validated workflow, and clean one-level-deep reference structure. The only room for improvement is minor tightening of redundant prose and the tangential citation block.

Suggestions

Trim the one-line prose restatements that immediately follow each failure-mode code block where the code is already self-explanatory.

Consider moving the 'Citing Scientific Agent Skills' section into a reference file so the SKILL.md body stays focused on procedural guidance.

Dimension	Reasoning	Score
Conciseness	Information-dense and largely assumes Claude's competence—every CLI and failure mode is shown with minimal padding—but a few prose lines restate what the adjacent code already shows, and the citation section is tangential to the skill's task.	4 / 5
Actionability	Provides copy-paste-ready, fully-flagged CLI invocations with realistic arguments for all six bundled scripts, plus executable pint/uncertainties snippets and a concrete audit-rules table covering the common cases.	5 / 5
Workflow Clarity	An 11-step non-negotiable checklist is sequenced with an explicit validation checkpoint (JCGM 101 clause 8 comparison) and a feedback loop (report the Monte Carlo result when linearization fails); the auditor and plausibility tools add --fail-on verification for CI use.	5 / 5
Progressive Disclosure	The body is a clear overview that splits deep material into six well-signaled, one-level-deep reference files (each summarized in the Reference files section) and six scripts whose bundle paths were verified to exist on disk.	5 / 5
	Total	19 / 20 Passed

Description

100%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.

An excellent description: concrete, comprehensive, third-person, and explicitly gated with natural trigger phrases for both what and when. It distinguishes itself clearly from neighboring statistical skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions—unit conversion and dimensional checking, GUM uncertainty budgets, Type A and Type B evaluation, Monte Carlo propagation, curve-fit error propagation, CODATA constants, code auditing, and plausibility checks via named dimensionless groups—giving comprehensive coverage rather than vague abstraction.	5 / 5
Completeness	Clearly answers both what the skill does (track units, propagate uncertainty) and when to use it via explicit "Use for" and "Trigger on" clauses with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes explicit natural trigger phrases a user would actually say—"is this number physically reasonable", "sanity check these units", "what regime is this flow in", and "a result that looks off by orders of magnitude"—covering common phrasings and synonyms.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear metrology niche tied to specific libraries (pint, uncertainties) with distinct, domain-specific triggers, minimizing overlap with adjacent statistical or data-analysis skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/uncertainty-and-units/SKILL.md
Commit: 49c6e97

Reviewed: 3 days 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.