spectral-analysis

Frequency-domain analysis — FFT, power spectral density (Welch/periodogram), spectrograms, wavelet transforms, and coherence. Use for any signal with periodic, quasi-periodic, or transient frequency content in physics data.

Quality

90%

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.

A dense, highly actionable catalog of executable spectral-analysis workflows with essentially no filler and a genuinely useful pitfalls/trade-off reference layer. The two areas to tighten are the repeated plot-formatting boilerplate in the code examples and the absence of any progressive-disclosure split — the wavelet and coherence sections could move to reference files to shrink the always-loaded surface.

Suggestions

Trim the repeated matplotlib styling lines (set_xlabel/set_ylabel/set_title/grid/tight_layout) to a single illustrative pattern or a note, cutting a large fraction of the token budget without losing actionability.

Move the advanced workflows (CWT wavelets, cross-spectral/coherence) into a references/ file with one-line pointers from SKILL.md so the core file stays lean and disclosure is progressive.

Add a short 'sanity-check your result' note (e.g. verify peaks at known driving frequencies, confirm Nyquist coverage) to convert the pitfalls table into an in-workflow verification step.

Dimension	Reasoning	Score
Conciseness	Mostly lean: code dominates, comments are brief and load-bearing ('# Welch PSD (better noise averaging than raw FFT)'), and no space is spent explaining concepts Claude already knows. Slightly below anchor 5 because the repeated matplotlib formatting boilerplate (set_xlabel/set_title/grid/tight_layout blocks in every example) could be trimmed. Clearly above anchor 3 — there is no padded explanatory prose at all.	4 / 5
Actionability	Six fully executable, copy-paste-ready scipy/numpy workflows covering the common cases, plus concrete parameter guidance ('frequency resolution = fs/nperseg') and a pitfalls table with specific fixes ('Nyquist: fs ≥ 2 × f_max'). Matches the anchor-5 profile exactly.	5 / 5
Workflow Clarity	Each technique is a single unambiguous recipe; operations are read-only analysis and plot output, so the destructive/batch validation cap does not apply, and the 'Common Pitfalls' table functions as an explicit error checklist with fixes (aliasing, leakage, DC dominance, non-uniform sampling). Not anchor 4 because the pitfall/fix structure supplies the checkpoint-and-recovery guidance the 4-level example lacks.	5 / 5
Progressive Disclosure	Well-organized sections (When to Use, per-technique workflows, trade-off table, pitfalls) with all content inline and no bundle files present. Structure is good, but at ~200 lines the advanced workflows (wavelet transform, coherence) are candidates for split-out reference files — between the anchor-3 'content that should be separate is inline' and anchor-4 'most content appropriately placed'.	4 / 5
	Total	18 / 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 that names concrete capabilities and gives an explicit, specific 'Use for...' trigger clause. The only weakness is trigger-term coverage: it relies on technical vocabulary and omits everyday synonyms users might naturally say. Third-person voice is used correctly and there is no fluff.

Suggestions

Add natural synonyms to the trigger clause, e.g. 'Use for Fourier transform / power spectrum / frequency analysis of signals' so users who say those phrases still match.

Consider mentioning cross-spectral or filtering use cases in the description if those are common entry points, since the body covers them but the description does not.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete capabilities with method-level detail — 'FFT, power spectral density (Welch/periodogram), spectrograms, wavelet transforms, and coherence' — giving comprehensive coverage of the spectral-analysis domain rather than the minor-gaps profile of a 4.	5 / 5
Completeness	Explicitly answers both what ('Frequency-domain analysis — FFT, power spectral density...') and when ('Use for any signal with periodic, quasi-periodic, or transient frequency content in physics data') with concrete trigger phrases, matching the anchor-5 example structure.	5 / 5
Trigger Term Quality	Good keyword coverage including natural terms users would say ('FFT', 'spectrograms', 'periodic', 'signal', 'frequency content'), but misses common synonyms such as 'Fourier transform', 'power spectrum', or 'frequency analysis'. Falls between anchor 4 (good coverage, a few natural terms missing) and anchor 5 (comprehensive with synonyms).	4 / 5
Distinctiveness Conflict Risk	Clear niche — frequency-domain techniques scoped to physics signals — with distinct, specific triggers; minimal conflict risk with adjacent skills since the named methods (Welch, wavelets, coherence) are unambiguous.	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/spectral-analysis/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.