biopython-advanced

Advanced Biopython modules for motifs, population genetics, sequence utilities, restriction analysis, clustering, and GenomeDiagram visualization; use when you need extended bioinformatics analysis beyond basic sequence I/O and alignment.

Quality

68%

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 ./scientific-skills/Data Analysis/biopython-advanced/SKILL.md

Quality

Content

61%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 highly actionable, with three complete runnable examples following consistent config-first conventions, and it appropriately offloads detail to references/advanced.md. Weaknesses are redundancy in the Implementation Details section and a missing validation/verification step in the batch workflow, plus a small outputs/ directory assumption that breaks first-run execution.

Suggestions

Add an explicit validation/verification checkpoint to the workflow (e.g., a step that confirms outputs/*.json is valid JSON and that codon/CDS inputs are in-frame) so the batch workflow scores above the validation cap.

Trim redundant re-explanation in Implementation Details and consolidate the repeated UTF-8/ensure_ascii guidance into a single statement to tighten token use.

Either create outputs/ in the scripts (os.makedirs('outputs', exist_ok=True)) or note the prerequisite, so the examples run cleanly on first execution.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but padded: the Implementation Details section re-explains motif/restriction/codon behavior already shown in the code, and the UTF-8/ensure_ascii I/O conventions are stated three times (Key Features, example headers, Implementation Details). Not lower because it never over-explains concepts Claude already knows.	3 / 5
Actionability	Three complete, copy-paste-ready scripts with matching config JSON and run commands covering the common cases, but a minor execution gap: scripts write to outputs/ without creating it, so they fail unless the directory already exists.	4 / 5
Workflow Clarity	The config-first workflow (write config/task_config.json -> run python scripts/<task>.py -> write outputs/*.json) is clearly sequenced, but for a batch/analysis skill there are no validation or verification checkpoints, and the codon example relegates CDS-frame validation to a caveat rather than a step; the rubric caps batch skills without validation at 3.	3 / 5
Progressive Disclosure	Good sectioned overview (When to Use, Key Features, Dependencies, Example Usage, Implementation Details) with a clearly signaled, one-level-deep pointer to the verified references/advanced.md file. Stays below 5 because the body is still fairly heavy (three full inline scripts) with only a single reference file.	4 / 5
	Total	14 / 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.

The description is strong: it names a comprehensive set of concrete Biopython capability areas, includes an explicit 'Use when...' trigger, and clearly distinguishes itself from basic sequence I/O skills. Its main limitation is that the trigger clause is broad ('extended bioinformatics analysis beyond...') rather than rich with concrete, user-natural trigger phrases and synonyms.

Suggestions

Lead with verb-led concrete actions (e.g., 'Discover motifs, find restriction enzyme cut sites, compute codon usage') so capabilities read as actions rather than a module list.

Sharpen the 'when' clause with concrete, user-natural trigger phrases (e.g., 'use when the user asks for motif PWMs, restriction maps, codon frequency tables, or GenomeDiagram plots').

Add common synonyms/variants (e.g., 'PWM/consensus', 'restriction digest', 'GC content') to broaden natural-term coverage.

Dimension	Reasoning	Score
Specificity	Lists several specific capability areas ('motifs, population genetics, sequence utilities, restriction analysis, clustering, and GenomeDiagram visualization') with comprehensive domain coverage, though framed as module/domain enumeration rather than verb-led actions, so it stops short of the 5 anchor.	4 / 5
Completeness	Explicitly answers both 'what' (advanced Biopython modules for the listed analyses) and 'when' ('use when you need extended bioinformatics analysis beyond basic sequence I/O and alignment'), but the 'when' trigger is somewhat broad rather than enumerating concrete trigger phrases like the 5 anchor.	4 / 5
Trigger Term Quality	Contains natural domain terms a user would say ('motif discovery', 'restriction analysis', 'codon usage', 'population genetics', 'GenomeDiagram', 'bioinformatics analysis'), giving good keyword coverage, but lacks synonyms and file-extension variants that would reach the 5 anchor.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche ('advanced Biopython ... beyond basic sequence I/O and alignment') that carves it apart from general-purpose skills with minimal conflict risk, though the trigger surface remains domain-broad enough to stay just below the 5 anchor.	4 / 5
	Total	16 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 6 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/biopython-advanced/SKILL.md
Commit: f5ef65b

Reviewed: ~23 hours 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.