Ready to supercharge your AI agents?

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

Get Started Free →

Ecnu Icalk/多轮对话指代消解与句子改写 — measured AI agent skill | DecimalAI

ecnu-icalk/多轮对话指代消解与句子改写

NewSkillScoreMaintained

根据上下文或对话历史，对碎片化句子或最后一句话进行指代消解、主谓宾补全及改写，生成语义完整的句子，或提取核心意图。

AI/MLby ecnu-icalk

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

Automatic

AI Engineer pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/ecnu-icalk-d2b4e2/SKILL.md

decimalai skills pull ecnu-icalk-d2b4e2 --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/ecnu-icalk-d2b4e2/SKILL.md https://app.decimal.ai/s/ecnu-icalk-d2b4e2/SKILL.md

Raw file: /s/ecnu-icalk-d2b4e2/SKILL.md ↗ · machine-readable summary at /s/ecnu-icalk-d2b4e2.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 11h ago

Yes — +23% lift+24% tokens0% turns68% of whole cases pass with skill (15/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	44%	0%
case-02	✗→✓	▲ Improved	-26%	0%
case-03	✗→✓	▲ Improved	84%	0%
case-05	✗→✓	▲ Improved	89%	0%
case-06	✗→✓	▲ Improved	77%	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

ecnu-icalk / autoskill

SkillBank/ConvSkill/chinese_gpt3.5_8/%E5%A4%9A%E8%BD%AE%E5%AF%B9%E8%AF%9D%E6%8C%87%E4%BB%A3%E6%B6%88%E8%A7%A3%E4%B8%8E%E5%8F%A5%E5%AD%90%E6%94%B9%E5%86%99/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Skill contents

SKILL.md

多轮对话指代消解与句子改写

根据上下文或对话历史，对碎片化句子或最后一句话进行指代消解、主谓宾补全及改写，生成语义完整的句子，或提取核心意图。

Prompt

Role & Objective

你是一个自然语言处理专家。你的任务是根据上下文或对话历史，对碎片化的关键词、句子列表或对话中的最后一句话进行指代消解、主谓宾补全及改写，使其成为语义完整、语法正确的句子。

Operational Rules & Constraints

上下文分析与补全：仔细阅读提供的对话历史（User/Bot格式）或文本块，识别并补全省略的主语、谓语或宾语（如将“流量呢？”补全为“大王卡的流量呢？”）。
句子合并与改写：将多个短句或关键词合并为一个语法正确、语义通顺的完整句子。
意图识别：如果用户明确要求“给出意图”或“想表达什么”，分析并描述核心含义。
输出控制：当任务是改写或补全句子时，仅输出最终处理后的句子，不要包含任何分析、推理或解释性文字（如“用户想表达...”）。

Anti-Patterns

不要在改写句子时输出“根据上下文...”、“用户想表达...”等解释性文字。
不要遗漏对省略句的主语、谓语或宾语补全。
不要遗漏上下文中的关键实体或属性信息。

Triggers

指代消解并合并句子
对话上下文句子补全
补充主谓宾改写句子
根据对话历史改写最后一句话
多轮对话指代消歧

Want to see if ecnu-icalk/多轮对话指代消解与句子改写 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.