sindy-identification

Sparse Identification of Nonlinear Dynamics (SINDy) — discover governing equations from time-series data. Builds sparse dynamical system models dx/dt = f(x) from measurements using PySINDy. Use when you have trajectory data and want to find the underlying ODE.

Quality

88%

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

88%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.

The body is a well-organized, highly executable guide: complete runnable PySINDy workflows, explicit validation-by-simulation, a parameter reference, and a symptom→fix troubleshooting table. Minor gains available from trimming the redundant Overview and moving advanced workflows into reference files.

Suggestions

Drop or shrink the Overview section, which repeats the frontmatter description, and remove self-evident code comments to tighten conciseness.

Split advanced workflows (custom function libraries, coefficient extraction) into a references/ file linked from a short 'Advanced' section, improving progressive disclosure as the skill grows.

Add the trigger synonyms 'system identification' and 'equation discovery' to the description to broaden natural-term coverage.

Dimension	Reasoning	Score
Conciseness	The body is lean and code-dominated with no padding or explanation of concepts Claude already knows, but the Overview section re-states the frontmatter description and a few code comments ('Ground truth', 'sparsity threshold') restate the obvious — minor instances of over-explanation that could be trimmed, matching anchor 4 rather than the every-token-earns-its-place anchor 5.	4 / 5
Actionability	Six complete, copy-paste-ready PySINDy programs cover the common cases (basic fit, threshold sweep, custom libraries, noisy data, simulation validation, coefficient extraction), backed by a key-parameters table — fully executable guidance with concrete examples covering the common cases.	5 / 5
Workflow Clarity	Workflows are numbered in a clear progression from basic fit to validation, with an explicit validation workflow ('Validate: Simulate and Compare' including quantitative RMSE) and a troubleshooting table that serves as error-recovery feedback ('Too many terms discovered → Increase threshold'). The threshold sweep adds a complexity-vs-error feedback loop, matching the top anchor.	5 / 5
Progressive Disclosure	No bundle files exist, and the ~190-line body is well-sectioned with clear headers, so structure is good — but everything lives inline in SKILL.md (well above the 50-line simple-skill case), and advanced material like custom library construction or coefficient extraction could plausibly be split into reference files, matching anchor 4 ('most content is appropriately placed; minor organization gaps') rather than the reference-splitting anchor 5.	4 / 5
	Total	18 / 20 Passed

Description

87%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: it states what the skill does with mathematical precision and gives an explicit, concrete 'Use when' trigger clause. Trigger-term coverage is good but could add common synonyms such as 'system identification' and 'equation discovery'.

Dimension	Reasoning	Score
Specificity	The description names concrete, mathematically specific actions — 'discover governing equations from time-series data' and 'Builds sparse dynamical system models dx/dt = f(x) from measurements using PySINDy' — but covers only the core discovery task rather than the multiple specific actions (threshold tuning, library selection, validation by simulation) of the comprehensive anchor, so it sits between anchors 4 and 5, closer to 4.	4 / 5
Completeness	It explicitly answers both parts: what ('discover governing equations… Builds sparse dynamical system models dx/dt = f(x) from measurements using PySINDy') and when ('Use when you have trajectory data and want to find the underlying ODE'), with concrete trigger phrases matching the top anchor.	5 / 5
Trigger Term Quality	Good natural keywords users would say — 'trajectory data', 'find the underlying ODE', 'governing equations', 'time-series' — but common synonyms like 'system identification' or 'equation discovery' are absent from the description, matching 'good keyword coverage; a few natural terms missing' rather than the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	The SINDy/PySINDy/ODE-discovery framing carves out a clear niche with distinct triggers ('governing equations', 'underlying ODE', 'trajectory data'); no plausible overlap with generic data-analysis or symbolic-regression skill descriptions.	5 / 5
	Total	18 / 20 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/sindy-identification/SKILL.md
Commit: 4082a2e

Reviewed: 1 day 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.