CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

geo-search-api

Search for gene expression DataSets and Profiles in the NCBI GEO database. Use this skill when the user wants to find microarray, RNA-seq, or other genomic data by keywords, organism, author, or specific fields.

Quality

72%

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/geo-search-api/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 core Usage section is genuinely executable and the bundle structure (script plus one clearly linked reference) is sound, but the body is padded with generic template sections that add no GEO-specific value and contains a broken internal cross-reference and a fabricated expected-output block. Trimming the boilerplate and fixing the validation example would substantially improve it.

Suggestions

Cut the generic template sections ("Key Features", "Output Contract", "Validation and Safety Rules", "Failure Handling", "Required Inputs") or rewrite each to contain GEO-specific guidance; the current text is boilerplate that restates the description and adds no actionable detail.

Fix the "Example Usage" section: replace "See `## Usage` above" with a correct forward reference (Usage appears below), remove the hardcoded "20260316/scientific-skills/..." cd path, and replace the fabricated "Expected output format" under Quick Validation with the actual output of "python scripts/search_geo.py --help".

Consolidate the overlapping workflow guidance ("Example Usage" run plan, "Recommended Workflow", "Quick Validation") into one concrete sequence: build the query from references/query_fields.json, run the script, and inspect the actual JSON/markdown output it produces.

DimensionReasoningScore

Conciseness

Roughly half the body is generic template boilerplate — "Use this skill when the request matches its documented task boundary", "Prefer this skill for repeatable, checklist-driven execution rather than open-ended brainstorming", "Output Contract", "Validation and Safety Rules", "Failure Handling" — none of it GEO-specific, and the frontmatter description is restated verbatim inside "Key Features". This is noticeably verbose with several padded sections (anchor 2), not merely trimmable at the margins (anchor 4).

2 / 5

Actionability

The Usage section provides concrete, copy-paste-ready guidance: a full argument list, an executable example ("python scripts/search_geo.py \"diabetes\" --filters '{\"Organism\": \"Mus musculus\"...}' --limit 5"), and a compile/help check. It falls short of anchor 5 because the "Expected output format" block describes a result-file summary that "--help" would not actually produce, and no real sample search output is shown.

4 / 5

Workflow Clarity

A sequence exists (validate inputs, run script, review output) and a "Quick Validation" step is included, but the checkpoints are generic template text rather than skill-specific ones, and the stated expected validation output does not match what the check command produces. This matches anchor 3 (steps present, checkpoints missing or implicit) rather than anchor 4's concrete validated sequence.

3 / 5

Progressive Disclosure

The bundle split is appropriate and the single reference is well signaled ([query_fields.json](references/query_fields.json), one level deep), but the body inlines substantial boilerplate that belongs in no file at all, duplicates content (description repeated in "Key Features"), and contains a broken cross-reference ("See `## Usage` above" when the Usage section appears below "Example Usage"). Organization gaps are more than minor, so anchor 3 fits better than anchor 4.

3 / 5

Total

12

/

20

Passed

Description

82%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 clearly and explicitly states what the skill does and when to use it, with natural trigger terms and a distinct niche. The only minor gap is that it describes a single search action rather than a broader set of capabilities.

DimensionReasoningScore

Specificity

The description names the domain ("NCBI GEO database") and one concrete action ("Search for gene expression DataSets and Profiles") with two record types, which matches the anchor for naming domain and 1-2 concrete actions without comprehensive coverage. It does not reach anchor 4 because it lists only a single action (searching) rather than several distinct specific actions.

3 / 5

Completeness

It explicitly answers both questions: the what is "Search for gene expression DataSets and Profiles in the NCBI GEO database" and the when is "Use this skill when the user wants to find microarray, RNA-seq, or other genomic data by keywords, organism, author, or specific fields" — concrete trigger phrases matching the anchor-5 example. Not below 5 since neither half is vague or implicit.

5 / 5

Trigger Term Quality

Strong natural terms users would say: "microarray", "RNA-seq", "genomic data", "gene expression", "by keywords, organism, author". It falls short of anchor 5 because common variations like "transcriptomic", "GSE" accession numbers, or "high-throughput sequencing" are missing.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (NCBI GEO gene expression database searches) with distinct triggers (microarray, RNA-seq, organism/author field search) and minimal overlap with adjacent bioinformatics skills. It is far more specific than the anchor-4 example, which still carries cross-format overlap risk.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

aipoch/medical-research-skills

Path

scientific-skills/Evidence Insight/geo-search-api/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.