DE

devtu-optimize-skills

This skill improves output quality by applying verification, data layering, and evidence grading patterns with a focus on completeness.

Install

mkdir -p .claude/skills/devtu-optimize-skills && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/6931" && unzip -o skill.zip -d .claude/skills/devtu-optimize-skills && rm skill.zip

Installs to .claude/skills/devtu-optimize-skills

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Optimize ToolUniverse skills for better report quality, evidence handling, and user experience. Apply patterns like tool verification, foundation data layers, disambiguation-first, evidence grading, quantified completeness, and report-only output. Use when reviewing skills, improving existing skills, or creating new ToolUniverse research skills.
347 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Advanced

Key capabilities

  • →Implement evidence grading tiers from T1 to T4
  • →Standardize tool output using interpretation tables
  • →Embed Python computational procedures for statistical analysis
  • →Apply disambiguation-first workflows to resolve identifiers
  • →Structure reports with mandatory completeness checklists

How it works

The framework applies a multi-phase workflow starting with tool parameter verification, followed by foundation data aggregation, disambiguation, and evidence-graded synthesis. It replaces simple tool catalogs with reasoning frameworks that map raw API data to biological or clinical meaning.

Inputs & outputs

You give it
Unoptimized research skill documentation or workflow
You get back
Optimized skill documentation with verification, synthesis, and evidence grading

When to use devtu-optimize-skills

  • →Refining agent report quality
  • →Implementing verification steps in skills
  • →Improving evidence handling accuracy
  • →Standardizing data output formats

About devtu-optimize-skills

It applies specific patterns for tool verification, foundation data layering, and evidence grading. It ensures consistent output quality through disambiguation-first approaches and quantified completeness.

Optimize ToolUniverse skills for better report quality, evidence handling, and user experience. Apply patterns like tool verification, foundation data layers, disambiguation-first, evidence grading, quantified completeness, and report-only output. Use when reviewing skills, improving existing skills, or creating new ToolUniverse research skills.

When not to use it

  • →When creating aspirational capabilities not supported by APIs
  • →When writing skill documentation without testing tool calls first

Prerequisites

ToolUniverse environmentPython packages: pandas, scipy, numpy, networkx, requests, biopython

Limitations

  • →Computational procedures are restricted to packages available in ToolUniverse dependencies
  • →API-based tools may require fallback chains when primary data sources are unavailable

How it compares

Unlike generic skill development, this approach mandates test-driven tool verification and explicit interpretation tables to transform raw data into actionable scientific insights.

Compared to similar skills

devtu-optimize-skills side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
devtu-optimize-skills (this skill)15moNo flagsAdvanced
markitdown1775moReviewIntermediate
whisper1110moReviewBeginner
yams15moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

More by mims-harvard

View all by mims-harvard →

tooluniverse-drug-research

mims-harvard

Generates comprehensive drug research reports with compound disambiguation, evidence grading, and mandatory completeness sections. Covers identity, chemistry, pharmacology, targets, clinical trials, safety, pharmacogenomics, and ADMET properties. Use when users ask about drugs, medications, therapeutics, or need drug profiling, safety assessment, or clinical development research.

323

tooluniverse-pharmacovigilance

mims-harvard

Analyze drug safety signals from FDA adverse event reports, label warnings, and pharmacogenomic data. Calculates disproportionality measures (PRR, ROR), identifies serious adverse events, assesses pharmacogenomic risk variants. Use when asked about drug safety, adverse events, post-market surveillance, or risk-benefit assessment.

323

tooluniverse-precision-oncology

mims-harvard

Provide actionable treatment recommendations for cancer patients based on molecular profile. Interprets tumor mutations, identifies FDA-approved therapies, finds resistance mechanisms, matches clinical trials. Use when oncologist asks about treatment options for specific mutations (EGFR, KRAS, BRAF, etc.), therapy resistance, or clinical trial eligibility.

321

tooluniverse-expression-data-retrieval

mims-harvard

Retrieves gene expression and omics datasets from ArrayExpress and BioStudies with gene disambiguation, experiment quality assessment, and structured reports. Creates comprehensive dataset profiles with metadata, sample information, and download links. Use when users need expression data, omics datasets, or mention ArrayExpress (E-MTAB, E-GEOD) or BioStudies (S-BSST) accessions.

217

tooluniverse-literature-deep-research

mims-harvard

Conduct comprehensive literature research with target disambiguation, evidence grading, and structured theme extraction. Creates a detailed report with mandatory completeness checklist, biological model synthesis, and testable hypotheses. For biological targets, resolves official IDs (Ensembl/UniProt), synonyms, naming collisions, and gathers expression/pathway context before literature search. Default deliverable is a report file; for single factoid questions, uses a fast verification mode and may include an inline answer. Use when users need thorough literature reviews, target profiles, or to verify specific claims from the literature.

213

tooluniverse-target-research

mims-harvard

Gather comprehensive biological target intelligence from 9 parallel research paths covering protein info, structure, interactions, pathways, expression, variants, drug interactions, and literature. Features collision-aware searches, evidence grading (T1-T4), explicit Open Targets coverage, and mandatory completeness auditing. Use when users ask about drug targets, proteins, genes, or need target validation, druggability assessment, or comprehensive target profiling.

25

Search skills

Search the agent skills registry