dynamical-systems

Analyze nonlinear dynamical systems — phase portraits, fixed points, stability analysis, bifurcation diagrams, Poincare sections, Lyapunov exponents, and chaos detection. Use for any autonomous or non-autonomous ODE system where qualitative behavior matters.

Quality

85%

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

78%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 highly actionable, well-organized skill body built almost entirely from executable code with useful reference and troubleshooting tables. Its main weakness is bundling: everything lives in SKILL.md with no reference files, and there is minor code duplication across workflows.

Suggestions

Move the full workflow implementations (Lyapunov exponent, Poincare section, continuation) into a references/ file (e.g. references/workflows.md) and keep SKILL.md as an overview with short key snippets, since the inlined ~325 lines weigh on progressive disclosure.

Factor the repeated finite-difference Jacobian construction into one shared helper shown once instead of duplicating it across three workflows.

Add brief validation checkpoints to the analysis workflows (e.g. checking solve_ivp status/success and verifying trajectory lengths before plotting) to complement the fsolve convergence check already present.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely functional code and reference tables with no padding or explanation of known concepts, but the finite-difference Jacobian construction is repeated in three workflows (fixed point analysis, continuation, and Lyapunov), which is a clear trim/refactor opportunity.	4 / 5
Actionability	Five workflows are fully executable copy-paste-ready code with concrete parameters, sample systems, and expected results ('Expected for Lorenz: ~0.91 s⁻¹'), covering the common analysis cases.	5 / 5
Workflow Clarity	Each workflow is a clear, self-contained sequence, fsolve convergence is explicitly checked in the continuation code, and the troubleshooting table provides symptom/cause/fix recovery guidance. It falls short of a 5 because the other workflows lack explicit validate-then-proceed checkpoints.	4 / 5
Progressive Disclosure	No bundle files exist and everything — five full scripts plus two reference tables — is inlined in a single ~325-line SKILL.md. Section organization is good, but content that belongs in reference files (e.g. the Lyapunov/Poincare implementations and the classification tables) is inline, matching the 'some structure, could be better organized' anchor rather than the minimal-structure one below it.	3 / 5
	Total	16 / 20 Passed

Description

92%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: concrete, comprehensive capability list plus an explicit 'Use for...' clause in third person. The only gap is modest synonym coverage of domain trigger phrases.

Dimension	Reasoning	Score
Specificity	The description enumerates seven concrete capabilities ('phase portraits, fixed points, stability analysis, bifurcation diagrams, Poincare sections, Lyapunov exponents, and chaos detection'), giving comprehensive coverage of the domain rather than several actions with gaps.	5 / 5
Completeness	It explicitly answers both questions: 'Analyze nonlinear dynamical systems — ...' states what it does, and 'Use for any autonomous or non-autonomous ODE system where qualitative behavior matters' states when, matching the anchor for explicit what-and-when with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-keyword coverage ('chaos', 'phase portraits', 'bifurcation', 'Lyapunov exponents', 'ODE system'), but a few natural synonyms users might say are missing (e.g. 'limit cycle', 'attractor', 'strange attractor', 'nonlinear oscillator').	4 / 5
Distinctiveness Conflict Risk	It occupies a clear niche (qualitative nonlinear-dynamics analysis) with distinct technical triggers, so it is unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 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/dynamical-systems/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.