CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

tooluniverse-data-integration-analysis

Integrate computed statistical results (DEGs, GWAS hits, associations) with biological context from ToolUniverse databases (UniProt, GO, Reactome, ClinVar, OpenTargets). Use for adding gene function/pathway/disease annotations to a result list, building biological narrative around statistical findings, and going beyond p-values to mechanism.

Quality

78%

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 ./plugins/tooluniverse/skills/tooluniverse-data-integration-analysis/SKILL.md

The canonical home for this skill is tooluniverse-data-integration-analysis in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

66%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 well-structured with a genuinely rigorous five-step methodology and strong built-in validation via the cross-validation step. It is dragged down by textbook re-explanations of epidemiological concepts Claude already knows and by the absence of any executable code example despite the skill's own 'compute, don't describe' mandate.

Suggestions

Trim Step 3's background explanations of Mendelian randomization, DAG confounder/mediator/collider definitions, and 'association is not causation' down to only the applied decision rules (instrument strength F>10, pleiotropy checks, what to adjust for).

Add one worked, copy-paste-ready example of the full pipeline the skill mandates — e.g., a find_tools() query, retrieving UniProt/Reactome annotations for a short gene list, and the pandas merge that produces the evidence summary table.

Move the evidence-grading table and the causal-reasoning frameworks (DAG, triangulation, MR, mediation) into a reference file linked from SKILL.md so the main file stays a lean overview.

DimensionReasoningScore

Conciseness

Mostly efficient — tables are dense and every section carries decision rules — but Step 3 re-explains concepts Claude already knows ("genetic variants (instruments) are assigned at conception, so they are not confounded", definitions of confounders/mediators/colliders, "Statistical association is not causation") that could be tightened to just the applied heuristics. This fits 'mostly efficient but includes some unnecessary explanation or could be tightened'; it is well above the padded verbosity of the 2 anchor.

3 / 5

Actionability

Concrete elements exist — exact `find_tools("...")` query strings, a 4-tier evidence grading table, and a filled-in report template — but no executable code despite the body mandating "write and run Python code via Bash... Don't describe what you would do -- execute it". The tool-discovery snippets are effectively pseudocode hints with no worked example of a query→pandas→report pipeline, matching 'some concrete guidance but incomplete; pseudocode instead of executable code'.

3 / 5

Workflow Clarity

A clear five-step sequence (map findings to questions → multi-database evidence → causal reasoning → cross-validation → structured reporting) with an explicit validation checkpoint: "Before reporting a finding as robust, attempt to falsify it" plus five falsification checks. Feedback loops for error recovery are present ("If MR contradicts observational data, suspect confounding"; "there is a contradiction to resolve"), matching the top anchor. Not below 5 because nothing here is a destructive/batch operation requiring additional checkpoints.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), and the ~125-line body is well-sectioned with clear headers, tables, and no buried or nested references. This fits 'good structure; most content appropriately placed; minor organization gaps' (4) rather than 5, since the evidence-grading tables and causal-reasoning frameworks are reference-grade material that could be split out to keep SKILL.md a leaner overview.

4 / 5

Total

15

/

20

Passed

Description

80%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: concrete, third-person, names specific databases and result types, and includes an explicit 'Use for' clause. Its only weaknesses are a few missing natural trigger synonyms and mild overlap in phrasing with sibling tooluniverse interpretation skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "Integrate computed statistical results (DEGs, GWAS hits, associations) with biological context", "adding gene function/pathway/disease annotations to a result list", "building biological narrative around statistical findings" — and names the specific databases (UniProt, GO, Reactome, ClinVar, OpenTargets) and input types. Coverage is comprehensive with no vague filler, matching the top anchor; it clearly exceeds the 'several specific actions with minor gaps' (4) anchor.

5 / 5

Completeness

Both parts are present: a clear 'what' (integrate statistical results with biological context from named ToolUniverse databases) and an explicit 'Use for...' clause naming three concrete use cases. It stops short of the 5 anchor because the 'when' is phrased as use cases rather than concrete user trigger moments (e.g., "Use when the user asks what their significant genes mean"), so it could be slightly more explicit.

4 / 5

Trigger Term Quality

Good natural-term coverage: "DEGs", "GWAS hits", "associations", "gene function", "pathway", "disease annotations", "p-values", "mechanism" — phrases users analyzing omics results would plausibly say. A few common synonyms are missing (e.g., "enrichment", "interpret results", "biological interpretation"), so it fits the 'good coverage, a few natural terms missing' anchor rather than the comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (post-analysis biological interpretation of existing statistical results, anchored to specific ToolUniverse databases), but the skill family includes closely related siblings (gene-enrichment, variant-interpretation, literature-deep-research per the body) whose territory partially overlaps "adding gene function/pathway annotations". This is minor overlap risk with closely related skills — the 4 anchor — not the minimal-conflict 5.

4 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

mims-harvard/ToolUniverse

Path

plugins/tooluniverse/skills/tooluniverse-data-integration-analysis/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.