Tessl • The package manager for agent skills

SkillPublic

nmr-compound-inference

Analyze 1D 1H or 13C NMR data with nmrglue, generate spectrum plots and peak tables, compare against standard NMR libraries such as BMRB, HMDB, SDBS, and nmrshiftdb2, then produce a ranked candidate-compound report with evidence, caveats, and direct links.

Quality

81%

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

82%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-structured, actionable overview: executable commands that match the bundled script, a clearly sequenced workflow with guardrails, and well-signaled one-level-deep references that actually exist. Remaining polish is minor — deduplicate the comparison rules/library URLs between the body and the reference file, merge the near-identical command examples, and add an explicit output-validation checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and free of concept explanations Claude already knows, but there is minor duplication: the two bash blocks differ only by optional flags and could be one block, and the 'Comparison rules' section plus the four library URLs repeat content that also lives in references/standard-libraries.md.	4 / 5
Actionability	Fully executable guidance: copy-paste bash invocations of scripts/nmr_candidate_report.py whose flags (--input, --output-dir, --nucleus, --solvent, --field-mhz) match the actual script's argparse, an enumerated list of generated outputs, concrete library search URLs, and a specific checklist for the final report.	5 / 5
Workflow Clarity	A clear 4-step sequence (run script → review outputs → read reference and search libraries → return report) with a soft checkpoint ('Review the generated outputs') and quality gates in 'Guardrails'. Not 5 because there is no explicit validation of the script's outputs (e.g. confirm peak_table.csv is non-empty or handle script failure), though the read-only, non-destructive nature softens that gap.	4 / 5
Progressive Disclosure	Good structure: the body is an overview, code lives in scripts/nmr_candidate_report.py and library details in references/standard-libraries.md — both real files, one level deep, clearly signaled ('Read references/standard-libraries.md'). Not 5 because the comparison rules and library URLs are inlined in the body despite being duplicated in the reference file, a minor organization gap.	4 / 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 strong, specific, third-person description that comprehensively states what the skill does with concrete actions and named libraries. Its one structural weakness is the absence of any 'Use when…' trigger guidance, which caps completeness at 3, and it lacks a few natural synonyms users might say.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user provides a 1D NMR spectrum (1H or 13C) or asks to identify a compound from NMR peaks, chemical shifts, or a spectrum plot.'

Add natural synonyms users would say, such as 'proton NMR', 'carbon NMR', 'spectra', 'chemical shifts', and 'compound identification', to improve trigger matching.

Optionally mention supported input formats in the description (Bruker fid/pdata, NMRPipe, ppm/intensity text) so format-based triggers also match.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'Analyze 1D 1H or 13C NMR data with nmrglue', 'generate spectrum plots and peak tables', 'compare against standard NMR libraries such as BMRB, HMDB, SDBS, and nmrshiftdb2', 'produce a ranked candidate-compound report with evidence, caveats, and direct links' — in third-person voice, covering the full capability range from input to deliverable.	5 / 5
Completeness	The 'what' is clearly and concretely answered, but there is no 'Use when…' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 3 even though the capability list is strong.	3 / 5
Trigger Term Quality	Good natural keywords are present ('NMR', '1H', '13C', 'spectrum', 'peak tables', 'compound', named libraries), but common variations users would say are missing — e.g. 'proton NMR', 'carbon NMR', 'identify a compound', 'chemical shifts', 'spectra'. Not generic, but not comprehensive synonym coverage either.	4 / 5
Distinctiveness Conflict Risk	A clear niche (1D NMR compound identification via nmrglue with specific named reference libraries) with distinct technical triggers; virtually no overlap risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/chemistry/nmr-compound-inference/SKILL.md
Revision: 6a85742

Reviewed: 4 days ago

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.

nmr-compound-inference

Table of Contents

Is this your skill?