Ready to supercharge your AI agents?

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

xunzhi-business-dictionary — measured AI agent skill | DecimalAI

lishuangqiang/xunzhi-business-dictionary

NewSkillScoreMaintained

AI-Meeting 业务对象词典 Skill。用于统一跨域名词、真相源、对象层级、生命周期和不变量；当需求涉及 `sessionId`、`requestId`、`questionNumber`、`agentName`、`loadMode`、`confidence` 等高频名词，或者在改接口、配置、工作流、快照、归档前需要先搞清对象真实语义时使用。

Documentationby lishuangqiang

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

Automatic

Knowledge Management pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/lishuangqiang-xunzhi-business-dictionary/SKILL.md

decimalai skills pull lishuangqiang-xunzhi-business-dictionary --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/lishuangqiang-xunzhi-business-dictionary/SKILL.md https://app.decimal.ai/s/lishuangqiang-xunzhi-business-dictionary/SKILL.md

Raw file: /s/lishuangqiang-xunzhi-business-dictionary/SKILL.md ↗ · machine-readable summary at /s/lishuangqiang-xunzhi-business-dictionary.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 3h ago

Yes — +27% lift-11% tokens0% turns95% of whole cases pass with skill (21/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-38%	0%
case-02	✗→✓	▲ Improved	-29%	0%
case-03	✗→✓	▲ Improved	-8%	0%
case-12	✗→✓	▲ Improved	7%	0%
case-13	✗→✓	▲ Improved	-3%	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

lishuangqiang / ai-meeting

skills/xunzhi-business-dictionary/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 1 file

Skill contents

references/

SKILL.md

xunzhi-business-dictionary

这个 Skill 不负责直接改某个具体业务域，它负责先把“你到底在改什么对象”说清楚。

使用顺序

先看 references/object-dictionary.md，统一对象层级和真相源。
再判断当前对象属于面试域、Agent 域、媒体域、鉴权域还是运行时域。
如果对象语义已经清楚，再切到对应领域 Skill 做具体修改。

这层主要解决什么

sessionId 在不同域里是不是同一个东西。
requestId 是业务主键，还是幂等边界。
questionNumber 是数据库主键，还是业务题号。
loadMode、confidence 是展示字段，还是运行时写入能力的正式语义。
某个对象到底是主记录、运行态、快照、归档，还是接口契约。

必守约束

先判定真相源，再改实现。
不要把运行态缓存当成最终业务事实。
不要把 DTO、工作流字段或视图对象误当成主记录。
不要让同一个名词在不同域里被默认当成同一个对象。

不要用我做什么

不要用我直接改面试状态机；那属于 xunzhi-interview-domain。
不要用我直接改通用 Agent 聊天；那属于 xunzhi-agent-domain。
不要用我直接改媒体协议；那属于 xunzhi-media-domain。
不要用我直接调 Guard、限流或线程池；那属于 xunzhi-ai-runtime。

参考资料

references/object-dictionary.md

Want to see if lishuangqiang/xunzhi-business-dictionary 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.