CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

statistical-mechanics

Monte Carlo simulation for statistical mechanics — Ising model, Metropolis-Hastings, Wolff cluster algorithm, observables (magnetization, susceptibility, specific heat), finite-size scaling, and critical phenomena analysis.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 dense, highly actionable skill body: executable code for every core workflow, an exact-exponents reference table, and a symptom/fix troubleshooting table, all with no padding or basic-concept explanation. The structural weakness is that everything lives inline in SKILL.md — no one-level-deep reference files — and validation checkpoints in the workflows are implicit rather than explicit.

DimensionReasoningScore

Conciseness

The body is lean code with essentially zero concept explanation — it never explains what the Ising model is, what Monte Carlo does, or how numpy works; comments like 'Sum of nearest neighbors' and '# specific heat' carry information, not padding. Every section (simulation, sweep, scaling, error estimation) earns its tokens; this matches the 'lean and efficient, every token earns its place' anchor.

5 / 5

Actionability

Fully executable, copy-paste-ready code throughout: a complete IsingModel class, a temperature-sweep driver with plotting, finite_size_scaling(), and autocorrelation_time(), all with concrete parameters and output files. The snippets cover the common cases (2D Ising, T_c extraction, exponent estimation, error bars), matching the top anchor.

5 / 5

Workflow Clarity

Workflows are clearly numbered and sequenced (1. base simulation → 2. temperature sweep → 3. finite-size scaling → 4. error estimation), with progress checkpoints via per-T and per-L print statements and a troubleshooting table for error recovery. Not 5 because validation is implicit rather than explicit — e.g., no step verifies equilibration before measuring, and no step checks that the measured T_c approaches the Onsager value 2.269 that the skill itself prints.

4 / 5

Progressive Disclosure

The single file has good section structure (Overview, When to Use, numbered workflows, tables), but it is a ~245-line monolith with a ~100-line class implementation inlined and no references/, scripts/, or assets/ files at all. Content like the full Ising class, the finite-size-scaling driver, and the autocorrelation utility arguably belongs in separate reference files; this matches 'some structure but content that should be separate is inline'.

3 / 5

Total

17

/

20

Passed

Description

75%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 dense, specific, jargon-appropriate description that comprehensively states what the skill does with excellent natural trigger terms for the domain. Its only real deficiency is the absence of any explicit 'Use when...' trigger clause, which caps completeness at 3 and leaves the 'when to use' question implied rather than answered.

Suggestions

Append an explicit trigger clause, e.g. 'Use when simulating spin systems, locating phase transitions or critical temperatures, or performing finite-size scaling analysis.'

Add the natural synonyms users say that are currently missing, such as 'phase transition', 'critical temperature', and 'spin models' (the body covers Potts/XY/Heisenberg but the description never mentions them).

DimensionReasoningScore

Specificity

The description enumerates concrete capabilities: 'Monte Carlo simulation for statistical mechanics', 'Ising model', 'Metropolis-Hastings', 'Wolff cluster algorithm', 'observables (magnetization, susceptibility, specific heat)', 'finite-size scaling, and critical phenomena analysis' — comprehensive coverage of the skill's actions with no vague filler. Not 4 because coverage of the domain (algorithms, observables, analysis methods) is complete rather than having minor gaps.

5 / 5

Completeness

The 'what' is clearly and comprehensively stated, but there is no 'Use when...' clause or equivalent explicit trigger guidance — when to use the skill is only weakly implied by the domain terms. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3; it is not 4 because the 'when' is entirely absent rather than present-but-imprecise.

3 / 5

Trigger Term Quality

Strong natural keywords a user would actually say — 'Monte Carlo', 'Ising model', 'Metropolis-Hastings', 'Wolff cluster', 'susceptibility', 'specific heat', 'finite-size scaling', 'critical phenomena'. Not 5 because common variations like 'phase transition', 'critical temperature', 'spin model/simulation', or 'Potts' are absent (the body supports these but the description does not mention them).

4 / 5

Distinctiveness Conflict Risk

It carves out a clear niche — equilibrium statistical mechanics Monte Carlo simulation — with distinct technical triggers (Ising, Wolff, finite-size scaling) that are unlikely to collide with other skills. Not 4 because the specialized physics vocabulary leaves essentially no overlap with adjacent skills.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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/statistical-mechanics/SKILL.md

Reviewed

Table of Contents

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.