Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Optimizing ToolUniverse Skills · mims-harvard | DecimalAI

agent toolingby mims-harvard

Optimizing ToolUniverse Skills

devtu-optimize-skills

Source mims-harvard/ToolUniverse ↗License Apache-2.0

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.

SkillScore65Maintained

Automatic

AI Engineer pack

Last verified 7/27/2026

What it changes

Passed 14 of 22 test cases with the skill, and 4 of 22 without it.

Without skill17%

With skill65%

11 fixed4 passed either way8 still failing0 broke

Pass-rate lift: +48 pp
Tokens: +72%
Agent turns: 0%
Response time: -24%

Model gemini-3.6-flashMeasured 7/27/2026v115 of 23 cases passed with skill · 22 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/devtu-optimize-skills/SKILL.md https://app.decimal.ai/s/devtu-optimize-skills/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add devtu-optimize-skills, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/devtu-optimize-skills/ and pins it in .decimal/skills.lock

decimalai skills add devtu-optimize-skills

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/devtu-optimize-skills/SKILL.md https://app.decimal.ai/s/devtu-optimize-skills/SKILL.md

Raw file: /s/devtu-optimize-skills/SKILL.md ↗ · machine-readable summary at /s/devtu-optimize-skills.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

What's inside

The instructions your model reads when the skill loads.

SKILL.md227 lines5 files

Optimizing ToolUniverse Skills

Best practices for high-quality research skills with evidence grading and source attribution.

Tool Quality Standards

Error messages must be actionable — tell the user what went wrong AND what to do
Schema must match API reality — run python3 -m tooluniverse.cli run <Tool> '<json>' to verify
Coverage transparency — state what data is NOT included
Input validation before API calls — don't silently send invalid values
Cross-tool routing — name the correct tool when query is out-of-scope
No silent parameter dropping — if a parameter is ignored, say so

Core Principles (13 Patterns)

Full details: references/optimization-patterns.md

#	Pattern	Key Idea
1	Tool Interface Verification	`get_tool_info()` before first call; maintain corrections table
2	Foundation Data Layer	Query aggregator (Open Targets, PubChem) FIRST
3	Versioned Identifiers	Capture both `ENSG00000123456` and `.12` version
4	Disambiguation First	Resolve IDs, detect collisions, build negative filters
5	Report-Only Output	Narrative in report; methodology in appendix only if asked
6	Evidence Grading	T1 (mechanistic) → T2 (functional) → T3 (association) → T4 (mention)
7	Quantified Completeness	Numeric minimums per section (>=20 PPIs, top 10 tissues)
8	Mandatory Checklist	All sections exist, even if "Limited evidence"
9	Aggregated Data Gaps	Single section consolidating all missing data
10	Query Strategy	High-precision seeds → citation expansion → collision-filtered broad
11	Tool Failure Handling	Primary → Fallback 1 → Fallback 2 → document unavailable
12	Scalable Output	Narrative report + JSON/CSV bibliography
13	Synthesis Sections	Biological model + testable hypotheses, not just paper lists

Optimized Skill Workflow

Phase -1: Tool Verification (check params)
Phase  0: Foundation Data (aggregator query)
Phase  1: Disambiguation (IDs, collisions, baseline)
Phase  2: Specialized Queries (fill gaps)

Track record

Benchmark

14 / 22

test cases passed, vs 4 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/30/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

mims-harvard / ToolUniverse

skills/devtu-optimize-skills/SKILL.md

View on GitHub ↗

License Apache License 2.0Imported 8/2/2026Version v1Bundled 4 files

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

What's inside

Optimizing ToolUniverse Skills

Tool Quality Standards

Core Principles (13 Patterns)

Optimized Skill Workflow

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills