Ready to supercharge your AI agents?

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

xunzhi-agent-domain — measured AI agent skill | DecimalAI

lishuangqiang/xunzhi-agent-domain

NewSkillScoreMaintained

AI-Meeting 通用 Agent 业务知识 Skill。用于处理通用 Agent 会话创建、SSE 聊天、历史消息、会话归属、Agent 属性管理、文件上传与业务场景绑定；当需求命中 `/api/xunzhi/v1/agents/**`、`/api/xunzhi/v1/agent-properties/**` 或通用 Agent 会话行为时使用。

agent-toolingby lishuangqiang

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

Automatic

Coding pack

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

pip install decimalai

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

decimalai skills pull lishuangqiang-xunzhi-agent-domain --out .claude/skills/

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

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

Raw file: /s/lishuangqiang-xunzhi-agent-domain/SKILL.md ↗ · machine-readable summary at /s/lishuangqiang-xunzhi-agent-domain.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 — +73% lift-23% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-12	✗→✓	▲ Improved	-56%	0%
case-01	✗→✓	▲ Improved	-3%	0%
case-02	✗→✓	▲ Improved	-3%	0%
case-18	✗→✓	▲ Improved	-21%	0%
case-04	✗→✓	▲ Improved	-23%	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-agent-domain/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 7 files · scripts

Skill contents

scripts/

references/

SKILL.md

xunzhi-agent-domain

当需求属于“通用 Agent 会话层”，而不是面试专属链路时，使用这个 Skill。

使用顺序

再看 references/object-dictionary.md，确认会话、消息、配置、归属对象的真相源。
先看 references/module-map.md，分清通用 Agent 和面试 Agent 的边界。
再看 references/session-flow.md，确认建会话、聊天、分页、结束的调用链。
涉及场景名与 Agent 名称绑定时看 references/agent-binding.md 和 references/generated-agent-scene-map.md。
涉及易错边界时看 references/gotchas.md。

关键入口

admin/src/main/java/com/hewei/hzyjy/xunzhi/agent/api/AgentController.java
admin/src/main/java/com/hewei/hzyjy/xunzhi/agent/api/AgentFileController.java
admin/src/main/java/com/hewei/hzyjy/xunzhi/agent/api/AgentPropertiesController.java
admin/src/main/java/com/hewei/hzyjy/xunzhi/agent/service/impl/AgentMessageServiceImpl.java
admin/src/main/java/com/hewei/hzyjy/xunzhi/agent/application/BusinessAgentScene.java
admin/src/main/java/com/hewei/hzyjy/xunzhi/agent/application/BusinessAgentResolver.java

必守约束

sessionId 不是展示字段，它是会话主键语义；历史查询必须做归属校验。
通用 Agent 会话和面试主链路要保持边界清晰。
所有带用户上下文的会话查询都必须保留归属校验。
SSE 聊天必须有有效 sessionId，不能跳过会话存在性和归属校验。
场景绑定名不是展示文案，而是实际运行时选择哪个 Agent 的入口。

参考资料

references/object-dictionary.md
references/module-map.md
references/session-flow.md
references/agent-binding.md
references/generated-agent-scene-map.md
references/gotchas.md
scripts/extract_agent_scene_map.py

Want to see if lishuangqiang/xunzhi-agent-domain 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.