Ready to supercharge your AI agents?

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

Get Started Free →

Wasabeef/透過程式碼庫和文件驗證資訊準確性 | DecimalAI

researchby wasabeef

Wasabeef/透過程式碼庫和文件驗證資訊準確性

wasabeef/透過程式碼庫和文件驗證資訊準確性

Source wasabeef/claude-code-cookbook ↗License Not recorded

透過程式碼庫和文件驗證資訊準確性。「這個資訊對嗎？」「事實檢查」「驗證這個」等觸發。

SkillScore82Maintained

Automatic

Coding pack

Last verified 8/16/2026

What it changes

Passed 17 of 21 test cases with the skill, and 13 of 21 without it.

Without skill64%

With skill82%

Checks it passed that the model alone missed

The conclusion status is ✅ 正確.
The conclusion verdict is ✅ 正確.
The output uses the section header ## 事實檢查結果.

and 6 more in the full report

6 fixed12 passed either way2 still failing2 broke

Pass-rate lift: +18 pp
Tokens: -2%
Agent turns: 0%
Response time: -39%

Model gemini-3.6-flashMeasured 8/16/2026v118 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/wasabeef-3c82e7/SKILL.md https://app.decimal.ai/s/wasabeef-d8b66e/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add wasabeef-d8b66e, 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/wasabeef-3c82e7/ and pins it in .decimal/skills.lock

decimalai skills add wasabeef-d8b66e

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

curl -fsSL --create-dirs -o .claude/skills/wasabeef-3c82e7/SKILL.md https://app.decimal.ai/s/wasabeef-d8b66e/SKILL.md

Raw file: /s/wasabeef-d8b66e/SKILL.md ↗ · machine-readable summary at /s/wasabeef-d8b66e.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 6

Prompt

請針對「專案的路由管理已升級至 auto_route v7」進行事實核對。在 pubspec.yaml 第 20 行呈現 auto_route: ^7.8.0。請輸出包含標題、檢驗對象、結論、依據與詳細說明的格式化報告。

What was checked, without and with the skill
Checked	Without skill	With skill
The output uses the section header ## 事實檢查結果.	Missed	Passed
The conclusion status is ✅ 正確.	Missed	Passed

case-09 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md104 linessingle file

透過程式碼庫和文件驗證資訊準確性

參考項目內的代碼庫、文檔 (docs/、README.md 等)，確認所給資訊的正確性。

使用方法

# 基本用法
/check-fact "Flutter 應用使用了 Riverpod"

# 一次性確認多個資訊
/check-fact "這個項目使用 GraphQL，並通過 auto_route 管理路由"

# 確認特定技術規範
/check-fact "使用 JWT 進行身份驗證，未使用 Firebase Auth"

確認流程

資訊源優先級
- 代碼庫 (最可靠)
- README.md、docs/ 內文檔
- package.json、pubspec.yaml 等配置文件
- Issue、Pull Request 的讨論歷史
判定結果分類
- ✅ 正確 - 資訊與代碼庫完全一致
- ❌ 錯誤 - 資訊明顯錯誤
- ⚠️ 部分正確 - 部分準確但不完整
- ❓ 無法判斷 - 缺少必要的確認資訊
依據明示
- 相關文件名和行号
- 相關代碼片段
- 文檔相關部分

報告格式

## 事實檢查結果

Track record

Benchmark

17 / 21

test cases passed, vs 13 / 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

wasabeef / claude-code-cookbook

plugins/zh-tw/skills/check-fact/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

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