Ready to supercharge your AI agents?

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

Get Started Free →

runnable · ai-creed | DecimalAI

Registry skillby ai-creed

runnable

ai-creed/runnable

Source ai-creed/ai-shakespii ↗License MIT

Use when the user asks for a one-word acknowledgement drill — replies with exactly the word the drill names.

NewMaintained

Automatic

QA & Test Engineering pack

Last verified 8/4/2026

What it changes

Passed 0 of 22 test cases with the skill, and 22 of 22 without it.

Without skill100%

With skill0%

0 fixed17 passed either way4 still failing1 broke

Pass-rate lift: -100 pp
Tokens: +4%
Agent turns: 0%
Response time: -28%

Model gemini-3.6-flashMeasured 8/4/2026v117 of 22 cases passed with skill

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/ai-creed-runnable/SKILL.md https://app.decimal.ai/s/ai-creed-runnable/SKILL.md

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

decimalai skills add ai-creed-runnable

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

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

Raw file: /s/ai-creed-runnable/SKILL.md ↗ · machine-readable summary at /s/ai-creed-runnable.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.md33 linessingle file

runnable

Intent

Give the eval-run exercise a minimal, valid target: a skill whose eval suite is deterministic-clean and cheap to execute, with one case that fails its expectation by design so a runner has a real failure to report.

Inputs

A drill prompt naming what to say.

Preconditions

None.

Procedure

Read the drill prompt.
Reply with exactly what it asks for, nothing more.

Output

The requested reply, verbatim.

Examples

Input: Say the word apple. Output: apple

Anti-patterns

Adding commentary around the requested reply.

Track record

Benchmark

0 / 22

test cases passed, vs 22 / 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 — 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

ai-creed / ai-shakespii

skills/using-shakespii/evals/fixtures/runnable/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?

What's inside

runnable

Intent

Inputs

Preconditions

Procedure

Output

Examples

Anti-patterns

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills