conservation-law-discovery

Discover conserved quantities and symmetries from trajectory data. Identifies energy, momentum, angular momentum, and custom invariants using neural networks and symbolic methods. Inspired by Noether's theorem.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/physics/conservation-law-discovery/SKILL.md

Quality

Content

75%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 code-dense, highly actionable skill body with lean prose, executable examples covering generation, discovery, and validation of conserved quantities, and built-in quantitative checks. Remaining gaps are self-containment of code blocks and lack of any progressive offloading of detail into reference files.

Dimension	Reasoning	Score
Conciseness	Prose is lean throughout ('Discover conserved quantities from trajectory data without knowing the governing equations') and never explains concepts Claude already knows. Not 5 because the ~40-line plotting block in workflow 1 (ticklabel_format, grid styling, tight_layout) is bulk that could be trimmed without losing the method.	4 / 5
Actionability	Three complete, executable Python workflows with real numerics (solve_ivp, SVD null space, gradient-based conservation test) — 'mostly executable guidance' with a minor gap: workflows 2 and 3 depend on variables (x, y_pos, vx, vy, sol, trajectory) defined only in workflow 1's output, so blocks are not independently copy-paste ready. Not 3 because nothing is pseudocode and the shared-state dependency is explicitly signposted ('# Example: find conserved quantities in Kepler data').	4 / 5
Workflow Clarity	The three workflows are numbered and logically ordered (generate data → discover invariants → test candidates), and validation is built in: workflow 3 prints 'Conserved: YES/NO' against a quantitative threshold, and tip 5 mandates cross-validation on a separate trajectory segment. Not 5 because there is no explicit feedback loop (what to do when a candidate fails) and the workflows read as parallel recipes rather than one sequenced pipeline with checkpoints.	4 / 5
Progressive Disclosure	The single-file body is well organized with clear sections (Overview, When to Use, three workflows, Method Summary table, Tips) and no nested or buried references. Not 5 because at ~190 lines everything is inline with no offloading of detail (e.g., the method comparison and neural-network/SINDy approaches mentioned only in the table could live in reference files), which a skill of this size could justify.	4 / 5
	Total	16 / 20 Passed

Description

70%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 specific, third-person description of a well-delineated niche with good natural trigger terms, but it never states when to use the skill. Adding an explicit 'Use when...' clause would lift the capped completeness dimension.

Suggestions

Add an explicit trigger clause, e.g. 'Use when analyzing trajectory or simulation data to verify energy/momentum conservation, or to discover hidden constants of motion in dynamical systems.'

Include common synonyms such as 'constants of motion', 'integrals of motion', or 'first integrals' so users phrasing the need differently still match.

Drop or repurpose 'Inspired by Noether's theorem' — it is background flavor rather than a capability, and its tokens would be better spent on 'when to use' guidance.

Dimension	Reasoning	Score
Specificity	The description lists several concrete third-person actions ('Discover conserved quantities and symmetries from trajectory data. Identifies energy, momentum, angular momentum, and custom invariants using neural networks and symbolic methods'), matching the 'several specific actions; minor gaps' anchor. It falls short of 5 because 'custom invariants' is unspecific and 'Inspired by Noether's theorem' conveys no capability.	4 / 5
Completeness	The 'what' is clear and concrete (discover conserved quantities, identify specific invariants), but there is no 'Use when...' clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the judging guidelines. It is above 2 because the 'what' half is fully explicit.	3 / 5
Trigger Term Quality	Natural physics terms are present ('conserved quantities', 'symmetries', 'trajectory data', 'energy, momentum, angular momentum', 'invariants', "Noether's theorem"), giving good keyword coverage. Not 5 because common synonyms users would say — 'constants of motion', 'integrals of motion', 'Hamiltonian' — are absent.	4 / 5
Distinctiveness Conflict Risk	The description occupies a clear niche — Noether-inspired invariant discovery from trajectory data — with distinct trigger vocabulary that virtually no other skill would claim, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.	5 / 5
	Total	16 / 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/conservation-law-discovery/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.