CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

biopython-sequence-io

Use Biopython to read/write/convert biological sequence files (FASTA/GenBank/FASTQ, etc.) and perform basic sequence operations; use when you need reliable sequence I/O, lightweight sequence manipulation, or scalable processing of large sequence datasets.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/biopython-sequence-io/SKILL.md
SKILL.md
Quality
Evals
Security

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 technical core is excellent — a complete runnable script, concrete config conventions, and specific SeqIO guidance make the skill immediately actionable, with a clean one-level reference file. However, roughly a third of the body is generic template boilerplate (input validation, output contracts, failure handling) that wastes context and adds no Biopython-specific value, and the batch-processing workflow ships without any concrete validation checkpoint or feedback loop.

Suggestions

Remove or collapse the generic boilerplate sections ('When Not to Use', 'Required Inputs', 'Recommended Workflow', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling', 'Quick Validation') — they restate safety/validation rules Claude already follows and are not specific to Biopython sequence I/O; keeping only the technical sections would fix the conciseness gap.

Add a concrete validation checkpoint to the workflow, e.g., after conversion verify output record count matches the 'kept_records' summary and spot-check that GenBank output retained annotations — this also resolves the batch-operation cap on workflow_clarity.

Reconcile the script placement: either ship the example script as an actual 'scripts/sequence_io.py' bundle file (matching the documented 'python scripts/<task_name>.py' convention) or drop the scripts/ path references and present the inline script as the sole artifact, so the documented layout matches the bundle.

DimensionReasoningScore

Conciseness

Noticeably verbose due to several padded boilerplate sections that teach Claude nothing Biopython-specific: 'When Not to Use', 'Required Inputs', 'Recommended Workflow', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling' are generic template text ('Do not fabricate measurements...', 'Validate required inputs before execution'), and 'Quick Validation' explicitly says 'No local script validation step is required for this skill' while still spending lines on an expected-output format. This matches anchor 2 ('several unnecessary explanations or padded sections') rather than anchor 3, where only isolated tightening would be needed.

2 / 5

Actionability

Fully executable guidance: a complete config JSON, the exact command ('python scripts/sequence_io.py'), a copy-paste-ready ~70-line runnable script covering the common convert-and-filter case, and concrete API direction ('SeqIO.index(input_path, format)' for random access). Score 5 per anchor: specific examples cover the common cases.

5 / 5

Workflow Clarity

The example usage gives an unambiguous execution path, but the batch-processing workflow (streaming many records, writing converted output) lacks concrete validation checkpoints: 'Run a final validation pass for completeness, consistency, and safety' is generic template text with no actual check, no feedback loop (validate output → fix → retry), and 'Quick Validation' confirms no verification step exists. Per the rubric's cap guidance for batch operations without validation, workflow clarity cannot exceed 3.

3 / 5

Progressive Disclosure

Good structure with a clearly signaled, real one-level-deep reference ('See references/sequence_io.md for additional notes' — the file exists in the bundle) and well-organized sections. Minor gaps keep it below anchor 5: ~70 lines of the full script are inlined in SKILL.md while the body also references a 'scripts/sequence_io.py' path that does not exist as a bundle file, and the generic boilerplate sections belong nowhere in the bundle.

4 / 5

Total

14

/

20

Passed

Description

73%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 solid description that explicitly covers what the skill does and when to use it, with distinct format-level triggers. Its main weaknesses are the second-person trigger phrasing (which violates the third-person voice rule and costs specificity) and trigger terms phrased as internal capabilities rather than natural user-mentionable situations.

DimensionReasoningScore

Specificity

Base level 4: the description lists several concrete actions ('read/write/convert biological sequence files (FASTA/GenBank/FASTQ, etc.)') with only minor gaps ('perform basic sequence operations' is vague). Reduced by 1 per the rubric guideline because the trigger clause uses second-person voice ('use when you need reliable sequence I/O') instead of third person.

3 / 5

Completeness

Both 'what' ('read/write/convert biological sequence files... and perform basic sequence operations') and 'when' ('use when you need reliable sequence I/O, lightweight sequence manipulation, or scalable processing') are explicitly present, matching anchor 4. Not anchor 5 because the 'when' clause is phrased from the agent's perspective with mild buzz ('reliable') rather than concrete user-mentionable trigger situations like 'when the user mentions FASTA files'.

4 / 5

Trigger Term Quality

Good keyword coverage with natural terms users would say: 'Biopython', 'FASTA/GenBank/FASTQ', 'sequence I/O', 'sequence manipulation', 'large sequence datasets'. A few natural terms are missing (e.g., 'reverse complement', 'translate', '.fasta' extensions), which keeps it below the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

Clear niche with distinct triggers: naming Biopython plus specific formats (FASTA/GenBank/FASTQ) makes conflict with other skills minimal — any request matching this description unambiguously belongs to sequence file handling.

5 / 5

Total

16

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

14

/

16

Passed

Repository

aipoch/medical-research-skills

Path

scientific-skills/Data Analysis/biopython-sequence-io/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.