Ready to supercharge your AI agents?

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

Sensei · microsoft | DecimalAI

agent toolingby microsoft

Sensei

sensei

Source microsoft/github-copilot-for-azure ↗License NOASSERTION

**WORKFLOW SKILL** — Iteratively improve skill frontmatter compliance using the Ralph loop pattern. WHEN: \"run sensei\", \"sensei help\", \"improve skill\", \"fix frontmatter\", \"skill compliance\", \"frontmatter audit\", \"score skill\", \"check skill tokens\". INVOKES: token counting tools, test runners, git commands. FOR SINGLE OPERATIONS: use token CLI directly for counts/checks.

SkillScore73Maintained

Automatic

AI Engineer pack

Last verified 8/9/2026

What it changes

Passed 15 of 20 test cases with the skill, and 3 of 20 without it.

Without skill14%

With skill73%

Checks it passed that the model alone missed

The loop returns to step 2.
The reference skill is vally-eval.
The maximum iteration cap per skill is 5.

and 10 more in the full report

13 fixed3 passed either way6 still failing0 broke

Pass-rate lift: +59 pp
Tokens: -8%
Agent turns: 0%
Response time: -62%

Model gemini-3.6-flashMeasured 8/9/2026v316 of 22 cases passed with skill · 20 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/sensei/SKILL.md https://app.decimal.ai/s/sensei/SKILL.md

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

decimalai skills add sensei

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 13

Prompt

In sensei, if frontmatter checks or routing tests keep failing repeatedly for a given skill, what is the maximum number of correction iterations allowed before stopping?

What was checked, without and with the skill
Checked	Without skill	With skill
The maximum iteration cap per skill is 5.	Missed	Passed

case-07 · gemini-3.6-flash · 8/9/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md52 lines6 files

Help

When user says "sensei help" or asks how to use sensei, show this:

╔══════════════════════════════════════════════════════════════════╗
║  SENSEI - Skill Frontmatter Compliance Improver                  ║
╠══════════════════════════════════════════════════════════════════╣
║                                                                  ║
║  USAGE:                                                          ║
║    Run sensei on <skill-name>              # Single skill        ║
║    Run sensei on <skill1>, <skill2>, ...   # Multiple skills     ║
║    Run sensei on all skills                # All skills          ║
║                                                                  ║
║  EXAMPLES:                                                       ║
║    Run sensei on appinsights-instrumentation                     ║
║    Run sensei on azure-ai, azure-compute                         ║
║                                                                  ║
║  WHAT IT DOES:                                                   ║
║    1. READ      - Load skill's SKILL.md and tests                ║
║    2. VERIFY    - Compare skill frontmatter with convention      ║
║    3. SCAFFOLD  - Create tests from frontmatter if missing       ║
║    4. IMPROVE   - Add WHEN: triggers                             ║
║    5. TEST      - Run tests, fix if needed                       ║
║    6. SUMMARY   - Show before/after with suggestions             ║
║    7. PROMPT    - Ask: Commit, Create Issue, or Skip?            ║
║    8. REPEAT    - Until routing tests pass                       ║
╚══════════════════════════════════════════════════════════════════╝

Main Loop

For each skill, execute this loop until the frontmatter aligns with convention, have thorough routing tests AND routing tests pass:

READ - Load plugins/{plugin}/skills/{skill-name}/SKILL.md, and vally eval suites in evals/{skill-name}/*.yaml.
VERIFY - Compare the skill frontmatter with conventions in CONVENTIONS. If the skill's frontmatter violates any written convention, notify the user and propose a fix to align the frontmatter with the convention.
SCAFFOLD - If evals/{skill-name}/ doesn't exist, follow instructions in vally-eval skill to scaffold a set of routing tests. The routing tests test if the skill can be invoked for target user prompts. Generate user prompts that match the target scenario of the skill's description.
IMPROVE - If the skill description doesn't already have WHEN: triggers, add them.
TEST - Follow instructions in vally-eval skill to run the routing tests. If there are failed tests, suggest fixes.
SUMMARY - Display before/after comparison with unimplemented suggestions.

Track record

Benchmark

15 / 20

test cases passed, vs 3 / 20 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 — 8/8/2026

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 / github-copilot-for-azure

.github/skills/sensei/SKILL.md

View on GitHub ↗

License MITImported 8/8/2026Version v3Bundled 5 files

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