Ready to supercharge your AI agents?

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

🧬 Taiwan.md — Embeddings (fleet bge-m3 semantic index rebuild) · frank890417 | DecimalAI

ai mlby frank890417

🧬 Taiwan.md — Embeddings (fleet bge-m3 semantic index rebuild)

frank890417/twmd-embeddings

Source frank890417/taiwan-md ↗License Not recorded

Rebuild the bge-m3 semantic index via canonical EMBEDDING-PIPELINE — one keystone build feeds reader related-articles (src/data/related) + RAG vectors (public/api/rag). Sovereignty-preserving: embeddings computed in-house (mac-m4max local primary, GPU fleet fallback), never outsourced. TRIGGER when: user says "重建語意索引", "跑 embeddings", "rebuild embeddings", "embedding routine", or routine `twmd-embeddings-nightly` fires.

SkillScore82Maintained

Automatic

AI Engineer pack

Last verified 8/15/2026

What it changes

Passed 17 of 21 test cases with the skill, and 7 of 21 without it.

Without skill32%

With skill82%

Checks it passed that the model alone missed

Escalates to LESSONS-INBOX
Specifies running /twmd-become micro
Escalates the failure to LESSONS-INBOX

and 11 more in the full report

12 fixed6 passed either way3 still failing1 broke

Pass-rate lift: +50 pp
Tokens: -20%
Agent turns: 0%
Response time: -44%

Model gemini-3.6-flashMeasured 8/15/2026v118 of 22 cases passed with skill · 21 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

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

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add frank890417-twmd-embeddings, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

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

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/frank890417-twmd-embeddings/ and pins it in .decimal/skills.lock

decimalai skills add frank890417-twmd-embeddings

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

The vector build step generated files under public/api/rag/ as well as src/data/related/. We want to run git add on all generated files. Which directory path should be committed?

What was checked, without and with the skill
Checked	Without skill	With skill
Restricts git commit exclusively to src/data/related/	Missed	Passed

case-09 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md19 linessingle file

🧬 Taiwan.md — Embeddings (fleet bge-m3 semantic index rebuild)

你是 Taiwan.md（簽名 🧬）。如未甦醒先跑 /twmd-become micro。
嚴格完整讀取並執行 docs/pipelines/EMBEDDING-PIPELINE.md： Stage 0 fleet preflight（不可達 → graceful skip，非 error）→ Stage 1 rebuild （scripts/core/build-embeddings.mjs，~13 min）→ Stage 2 儀器化 verify → Stage 3 commit src/data/related/（--no-verify + git ls-files 驗證）→ Stage 4 /twmd-finale 收官。
鐵律：
- endpoint 解析走 pipeline §前置（本機優先 + fleet registry 備援，v1.1 2026-07-05），不 hardcode IP。
- 只 commit src/data/related/（public/api/rag + related 是 gitignored fleet 產出）。
- 內容無 diff → skip commit，不留空 commit。
- verify FAIL / fail rate >5% / fleet 連 3 天 skip → escalate LESSONS-INBOX 帶證據。

故意最小化。前置 endpoint 解析、Stage 0-4 細節、verify threshold、排程全部在 pipeline canonical。

Track record

Benchmark

17 / 21

test cases passed, vs 7 / 21 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

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-embeddings/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

🧬 Taiwan.md — Embeddings (fleet bge-m3 semantic index rebuild)

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills