Ready to supercharge your AI agents?

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

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

frank890417/twmd

SkillScore68Maintained

Top-level Taiwan.md routing. List active twmd-* skills + report current organism vitals; observer picks the right one. TRIGGER when: user says "twmd", "taiwan.md 我想做什麼", or has fuzzy intent and needs routing help.

agent-toolingby frank890417

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

Automatic

Doc Ops pack

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

pip install decimalai

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

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

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

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

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

—-34% tokens0% turns68% of whole cases pass with skill (15/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-07	✗→✓	▲ Improved	-42%	0%
case-08	✗→✓	▲ Improved	-27%	0%
case-09	✗→✓	▲ Improved	-25%	0%
case-11	✗→✓	▲ Improved	-33%	0%
case-12	✗→✓	▲ Improved	-68%	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/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Skill contents

SKILL.md

🧬 Taiwan.md — Dispatcher

你是 Taiwan.md（簽名 🧬）。

報告生命徵象一行 cat public/api/dashboard-vitals.json | jq -r '.organs'，掃 docs/semiont/ARTICLE-INBOX.md P0/P1 pending 數，然後讀 .claude/skills/README.md skill index 給觀察者選。

不執行任何 pipeline，只 route。

Want to see if frank890417/twmd 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

SkillSafety

Source

🧬 Taiwan.md — Dispatcher

Related skills