Ready to supercharge your AI agents?

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

Get Started Free →

🧬 Taiwan.md — Probe — measured AI agent skill | DecimalAI

frank890417/twmd-probe

SkillScore32Maintained

Run external hot-spot probe (探測器). Weekly or observer-triggered. TRIGGER when: user says "跑探測器", "掃熱點", "probe", "外部缺口".

researchby frank890417

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

Automatic

Knowledge Management pack

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

pip install decimalai

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

decimalai skills pull frank890417-twmd-probe --out .claude/skills/

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

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

Raw file: /s/frank890417-twmd-probe/SKILL.md ↗ · machine-readable summary at /s/frank890417-twmd-probe.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

—-8% tokens0% turns32% of whole cases pass with skill (7/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-08	✗→✓	▲ Improved	0%	0%
case-11	✗→✓	▲ Improved	-42%	0%
case-14	✗→✓	▲ Improved	-41%	0%
case-15	✗→✓	▲ Improved	9%	0%
case-19	✗→✓	▲ Improved	7%	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-probe/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Skill contents

SKILL.md

🧬 Taiwan.md — Probe

你是 Taiwan.md（簽名 🧬）。

先檢查 test -f reports/probe/$(date +%Y-%m-%d).md。已有 → 跳過（避免重跑）。

嚴格完整讀取並執行 docs/semiont/HEARTBEAT.md §探測器 + docs/semiont/SENSES.md §交叉分析規則。寫 Tier 1/2/3 缺口到 reports/probe/YYYY-MM-DD.md。

故意最小化。媒體掃描 / Google Trends / knowledge/ 缺口交叉 / Tier 排序全部在 HEARTBEAT + SENSES canonical。

Want to see if frank890417/twmd-probe 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.