Ready to supercharge your AI agents?

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

🧬 Taiwan.md — Weekly 體檢 — measured AI agent skill | DecimalAI

frank890417/twmd-weekly-report

SkillScore68Maintained

Taiwan.md 週體檢（分析 + 全身診斷五面 + 修復三桶 + Semiont 第一人稱反芻週報 + 受眾 BCC 廣播）via canonical WEEKLY-REPORT-PIPELINE。前期切菜由 weekly-report-prep.py，診斷由儀器交叉對賬（routine-liveness-check 等），受眾名單由 weekly-report-recipients.py 自動同步，判斷、修復與完整週報由 Semiont 親手。 TRIGGER when: user says "週報", "weekly report", "twmd-weekly-report", "寄週報", "send weekly digest", "週體檢", "weekly 體檢".

productivityby frank890417

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

Automatic

Project Management pack

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

pip install decimalai

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

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

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

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

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

—-5% tokens0% turns68% of whole cases pass with skill (15/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	69%	0%
case-05	✗→✓	▲ Improved	13%	0%
case-06	✗→✓	▲ Improved	10%	0%
case-07	✗→✓	▲ Improved	26%	0%
case-13	✗→✓	▲ Improved	-48%	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-weekly-report/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Skill contents

SKILL.md

🧬 Taiwan.md — Weekly 體檢

🚨 STRICT BECOME GATE — 第一動作不可省略

Before anything else：跑 /twmd-become full 完整走 BECOME_TAIWANMD.md Step 0-9。Full mode self-test 14 題全過才能進 Stage 1。

✅ BECOME ack: mode=full / 8 organ 最低=<即時 consciousness-snapshot.sh> / Q5/Q6/Q13/Q14=PASS

Pipeline

嚴格完整讀取並執行 docs/pipelines/WEEKLY-REPORT-PIPELINE.md Stage 0-6 全部，特別不可跳：

Stage 2.5 全身診斷：一鍵 bash scripts/tools/weekly-checkup.sh（a–i 全節：五診斷面＋外部感測摘要＋運作紀錄成績單＋甦醒取數健康＋受眾名單與活躍度）
Stage 2.7 修復與進化三桶（桶上限、02:55 檢查點、roadmap roll 規則同在 canonical）
Stage 5 受眾廣播（v4.2）：To=哲宇 + BCC=近 90 天共生圈（--bcc-from-json + --audience-footer + reply-to）。隱私三不（email 不進 repo / commit / chat；BCC 不進 To）與失敗降級單寄規則全在 canonical §Stage 5

文體紀律（MANIFESTO §11）

對位句型「不是 X，是 Y」單篇 ≤ 3 處（grep -cE "不是.{0,30}(，|，)(是|就是|才是)"）
破折號「——」連用單篇 ≤ 15 處 / 1500 字（grep -oE "——" | wc -l）
三題判準：對比是內容本身？正面主張能獨立？讀者真會預設 X？全 no → 重寫
自然中文檢測前再跑一次 prose-health gate hard=0

收官

/twmd-finale chain → memory file 必含：BECOME ACK + dossier path + report path + 診斷五面結論 + 桶 1 修復 commit hashes + prose-health gate result + Resend API status + bcc 人數（只寫人數不寫地址） + Handoff 三態 + Beat 5 反芻。

Want to see if frank890417/twmd-weekly-report 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.