Ready to supercharge your AI agents?

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

Get Started Free →

Common Failure Modes: AVOID · microsoft | DecimalAI

agent toolingby microsoft

Common Failure Modes: AVOID

microsoft/using-skills

Source microsoft/FluidFramework ↗License MIT

Describes how to use abilities. Read before any conversation.

NewMaintained

Automatic

AI Engineer pack

Last verified 8/2/2026

What it changes

Passed 3 of 10 test cases with the skill, and 3 of 10 without it.

Without skill27%

With skill27%

Checks it passed that the model alone missed

The response confirms verification results before marking the TodoWrite item complete.
The response issues multiple TodoWrite tool calls splitting each step into its own item.

2 fixed4 passed either way14 still failing2 broke

Pass-rate lift: 0 pp
Tokens: +137%
Agent turns: 0%
Response time: +71%

Model gemini-3.6-flashMeasured 8/2/2026v16 of 22 cases passed with skill · 10 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/microsoft-using-skills/SKILL.md https://app.decimal.ai/s/microsoft-using-skills/SKILL.md

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

decimalai skills add microsoft-using-skills

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 2

Prompt

You are completing the final step of our deployment checklist. Update the task status.

What was checked, without and with the skill
Checked	Without skill	With skill
The response confirms verification results before marking the TodoWrite item complete.	Missed	Passed

case-10 · gemini-3.6-flash · 8/2/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md90 linessingle file

Use Read tool to read the skill.
If the skill is relevant, announce you are using the skill.
Create TodoWrite todos for checklists.

Common Failure Modes: AVOID

Don't rationalize. Always read the current skill.

Do not skip using TodoWrite. Always create TodoWrite todos for checklists.

Track record

Benchmark

3 / 10

test cases passed, vs 3 / 10 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 — 8/1/2026

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 / FluidFramework

.agency/plugins/nori/skills/using-skills/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

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

Ready to supercharge your AI agents?

See it in action

What's inside

Common Failure Modes: AVOID

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills