CtrlK
BlogDocsLog inGet started
Tessl Logo

biopython-entrez

Use Bio.Entrez to access NCBI databases (e.g., PubMed/GenBank) for searching, fetching summaries, and downloading records when your workflow needs to call the NCBI E-utilities API over the network.

59

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Evidence Insight/biopython-entrez/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.

A well-structured, largely executable skill body with a runnable example and sensible operational guidance. Its main weaknesses are repeated configuration conventions, missing validation/retry checkpoints for a batch network operation, and prose-only coverage of EFetch/ELink.

Suggestions

Add an explicit validation/retry checkpoint to the workflow (e.g., retry on HTTP 429/5xx with backoff, and verify the output JSON has the expected record count before finishing) so the batch operation can score above 3 on workflow clarity.

De-duplicate the configuration and encoding conventions between 'Key Features' and 'Implementation Details' to reduce padding and tighten conciseness.

Add a short executable EFetch snippet (or move the EFetch/ELink detail into references/databases.md) so actionability covers all four advertised E-utilities rather than only esearch/esummary.

DimensionReasoningScore

Conciseness

Mostly efficient operational guidance (rate limits, batching, usehistory) that Claude may not fully know, but configuration/encoding conventions are repeated in both 'Key Features' and 'Implementation Details', and the full example script is long enough that it could be tightened.

3 / 5

Actionability

Provides a complete, copy-paste-ready config + Python script + run command covering the common esearch→esummary case, but EFetch and ELink are only described in prose without executable examples.

4 / 5

Workflow Clarity

The example sequence (esearch, sleep, esummary, write JSON) is clear, but this batch operation has no validation/verification checkpoint; retry/backoff is mentioned in prose yet not implemented in the script, so the batch-without-validation cap at 3 applies.

3 / 5

Progressive Disclosure

Well-organized sections with a clearly signaled one-level-deep reference to references/databases.md (a real file), though some implementation detail remains inline and only one reference file is provided.

4 / 5

Total

14

/

20

Passed

Description

78%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 clear, specific description that names concrete actions and an explicit when clause within a well-defined niche. It stops short of comprehensive trigger-term coverage and frames the 'when' as a technical condition rather than user-facing trigger phrases.

DimensionReasoningScore

Specificity

Names the domain (Bio.Entrez, NCBI databases) and three concrete actions ('searching, fetching summaries, and downloading records'), but omits cross-linking/identifier conversion that the body covers, leaving minor gaps.

4 / 5

Completeness

Explicitly answers both what (access NCBI databases for searching/fetching/downloading) and when ('when your workflow needs to call the NCBI E-utilities API over the network'), but the when clause is a technical condition rather than a concrete user-need trigger phrase.

4 / 5

Trigger Term Quality

Includes natural terms users would say ('PubMed', 'GenBank', 'NCBI databases'), but lacks synonyms and file-format extensions (e.g., FASTA, .gb) that would round out coverage.

4 / 5

Distinctiveness Conflict Risk

The Bio.Entrez + NCBI (PubMed/GenBank) niche is highly specific with distinct triggers and minimal overlap risk against other skills.

5 / 5

Total

17

/

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.

Validation14 / 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
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.