Ready to supercharge your AI agents?

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

🧬 Taiwan.md — Factcheck · frank890417 | DecimalAI

researchby frank890417

🧬 Taiwan.md — Factcheck

frank890417/twmd-factcheck

Source frank890417/taiwan-md ↗License Not recorded

Hallucination audit via canonical FACTCHECK-PIPELINE. TRIGGER when: user says "事實查核", "hallucination audit", "幻覺檢查", "factcheck".

SkillScore91Maintained

Automatic

Doc Ops pack

Last verified 8/15/2026

What it changes

Passed 19 of 21 test cases with the skill, and 3 of 21 without it.

Without skill14%

With skill91%

Checks it passed that the model alone missed

Executes in Quick Mode
Signs the response with 🧬
Uses the 🧬 emoji signature

and 30 more in the full report

18 fixed2 passed either way1 still failing1 broke

Pass-rate lift: +77 pp
Tokens: -13%
Agent turns: 0%
Response time: -27%

Model gemini-3.6-flashMeasured 8/15/2026v120 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-factcheck/SKILL.md https://app.decimal.ai/s/frank890417-twmd-factcheck/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add frank890417-twmd-factcheck, 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-factcheck/ and pins it in .decimal/skills.lock

decimalai skills add frank890417-twmd-factcheck

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 17 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 17

Prompt

Please state your operating identity and mandatory signature token when executing factual verification tasks on Taiwanese history docs.

What was checked, without and with the skill
Checked	Without skill	With skill
Identifies identity as Taiwan.md	Missed	Passed
Uses the 🧬 emoji signature	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.md11 linessingle file

🧬 Taiwan.md — Factcheck

你是 Taiwan.md（簽名 🧬）。
嚴格完整讀取並執行 docs/pipelines/FACTCHECK-PIPELINE.md。
觸發判斷：REWRITE Stage 3.5 → Quick Mode；A 級 ship 後 / 月度巡邏 / PR 接收 → Full Mode。

故意最小化。Phase 1-6 / 8 atom 類 / 11 hallucination pattern / 6 drift modes 全部在 pipeline canonical。

Track record

Benchmark

19 / 21

test cases passed, vs 3 / 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-factcheck/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 — Factcheck

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills