Registry skillby microsoft

Unit Converter

microsoft/unit-converter

Source microsoft/agent-framework ↗License MIT

Convert between common units using a multiplication factor.

NewMaintained

Automatic

Personal Assistant pack

Last verified 8/30/2026

What it changes

3 of 23 test cases passed with the skill.

Pass-rate lift: —
Tokens: +108%
Agent turns: 0%
Response time: +108%

Model gemini-3.6-flashMeasured 8/30/2026v33 of 23 cases passed with skill · 5 comparable

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

Lift withheld: 5 comparable cases; this report requires 8.

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/microsoft-unit-converter/SKILL.md https://app.decimal.ai/s/microsoft-unit-converter/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add microsoft-unit-converter, 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/microsoft-unit-converter/ and pins it in .decimal/skills.lock

decimalai skills add microsoft-unit-converter

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

curl -fsSL --create-dirs -o .claude/skills/microsoft-unit-converter/SKILL.md https://app.decimal.ai/s/microsoft-unit-converter/SKILL.md

Raw file: /s/microsoft-unit-converter/SKILL.md ↗ · machine-readable summary at /s/microsoft-unit-converter.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.md6 lines3 filesincludes scripts

Usage

When the user requests a unit conversion:

First, review references/CONVERSION_TABLES.md to find the correct factor
Run the scripts/convert.py script with --value <number> --factor <factor> (e.g. --value 26.2 --factor 1.60934)
Present the converted value clearly with both units

Track record

Benchmark

3 / 23

test cases passed with the skill

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 — 8/10/2026

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

microsoft / agent-framework

dotnet/samples/02-agents/AgentSkills/Agent_Step01_FileBasedSkills/skills/unit-converter/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v3Bundled 2 files · scripts

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

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

+43 pp pass-rate lift

apm-strategy[APM CEO persona](../../../.apm/agents/apm-ceo.agent.md)+41 pp pass-rate lift

apm-triage-panelThe panel is fixed at **3 mandatory specialist lenses + up to 3+77 pp pass-rate lift

batch-bug-shepherdThis skill is an A10 ORCHESTRATOR-SAGA over fan-out waves (triage,+55 pp pass-rate lift