Ready to supercharge your AI agents?

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

🧬 Taiwan.md — Sub-agent Batch Audit — measured AI agent skill | DecimalAI

frank890417/twmd-batch-audit

NewSkillScoreMaintained

Audit sub-agent batch for the three default cheating patterns (cross-pollination commits / merged commits / missing落檔) per DNA #42. TRIGGER when: user says "batch audit", "sub-agent 後驗證", "agent 偷吃步檢查", or after running parallel sub-agent batches.

agent-toolingby frank890417

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

Automatic

QA & Test Engineering pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/frank890417-twmd-batch-audit/SKILL.md

decimalai skills pull frank890417-twmd-batch-audit --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/frank890417-twmd-batch-audit/SKILL.md https://app.decimal.ai/s/frank890417-twmd-batch-audit/SKILL.md

Raw file: /s/frank890417-twmd-batch-audit/SKILL.md ↗ · machine-readable summary at /s/frank890417-twmd-batch-audit.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 2h ago

—-16% tokens0% turns36% of whole cases pass with skill (8/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-05	✗→✓	▲ Improved	-33%	0%
case-07	✗→✓	▲ Improved	-36%	0%
case-16	✗→✓	▲ Improved	-23%	0%
case-17	✗→✓	▲ Improved	-28%	0%
case-20	✓→✗	▼ Worse	-72%	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 — 8/3/2026

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

frank890417 / taiwan-md

.claude/skills/twmd-batch-audit/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Skill contents

SKILL.md

🧬 Taiwan.md — Sub-agent Batch Audit

你是 Taiwan.md（簽名 🧬）。

嚴格完整讀取 docs/semiont/DNA.md §四工程衛生 #32 + #42 三偷吃步 pattern。

跑 bash scripts/tools/audit-batch.sh（如未存在 → 先建再做，per §造橋鋪路）。

故意最小化。三類偷吃步偵測 / git log 分析 / reports/research 落檔驗證全部在 DNA + audit-batch.sh canonical。

Want to see if frank890417/twmd-batch-audit 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.

Ready to supercharge your AI agents?

frank890417/twmd-batch-audit

SkillSafety

Source

🧬 Taiwan.md — Sub-agent Batch Audit

Related skills