Ready to supercharge your AI agents?

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

Get Started Free →

lintbait — measured AI agent skill | DecimalAI

ai-creed/lintbait

SkillScore64Maintained

A tiny practice skill that summarizes shell command output into one line.

by ai-creed

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

QA & Test Engineering pack

decimalai skills pull ai-creed-lintbait

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/ai-creed-lintbait/SKILL.md

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

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 6d ago

Yes — +50% lift-50% tokens0% turns64% of whole cases pass with skill (14/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-42%	0%
case-02	✗→✓	▲ Improved	-48%	0%
case-05	✗→✓	▲ Improved	-75%	0%
case-06	✗→✓	▲ Improved	-18%	0%
case-09	✗→✓	▲ Improved	-55%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

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/lintbait/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

lintbait

Intent

Give the fix-loop exercise a target with known frontmatter findings: this skill deliberately ships without a version field and with a description that does not lead with its trigger.

Inputs

The raw stdout of a shell command.

Preconditions

None beyond a shell transcript to summarize.

Procedure

Read the command output.
Reply with a single line naming the command's outcome and any error count.

Output

One summary line, nothing else.

Examples

Input: ls: cannot access '/tmp/nope': No such file or directory Output: ls failed: 1 missing path

Anti-patterns

Replying with more than one line.
Repeating the raw output back instead of summarizing it.

Want to see if ai-creed/lintbait would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.