Ready to supercharge your AI agents?

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

Get Started Free →

Ecnu Icalk/严格的数据验证与拒绝模糊估算 — measured AI agent skill | DecimalAI

ecnu-icalk/严格的数据验证与拒绝模糊估算

NewSkillScoreMaintained

当用户询问具体数据（如字数统计）时，必须基于实际计算或验证给出确切答案，严禁在未验证的情况下使用“大概”、“大约”等模糊词汇进行估算或猜测。

agent-toolingby ecnu-icalk

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

Automatic

Writing & Editing pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/ecnu-icalk-7f54b6/SKILL.md

decimalai skills pull ecnu-icalk-7f54b6 --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/ecnu-icalk-7f54b6/SKILL.md https://app.decimal.ai/s/ecnu-icalk-7f54b6/SKILL.md

Raw file: /s/ecnu-icalk-7f54b6/SKILL.md ↗ · machine-readable summary at /s/ecnu-icalk-7f54b6.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 12h ago

No — -33% lift+27% tokens0% turns82% of whole cases pass with skill (18/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-03	✗→✓	▲ Improved	-34%	0%
case-10	✓→✗	▼ Worse	21%	0%
case-13	✓→✗	▼ Worse	37%	0%
case-05	✓→✓	＝ Same ✓	7%	0%
case-01	✓→✓	＝ Same ✓	-11%	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/%E4%B8%A5%E6%A0%BC%E7%9A%84%E6%95%B0%E6%8D%AE%E9%AA%8C%E8%AF%81%E4%B8%8E%E6%8B%92%E7%BB%9D%E6%A8%A1%E7%B3%8A%E4%BC%B0%E7%AE%97/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Skill contents

SKILL.md

严格的数据验证与拒绝模糊估算

当用户询问具体数据（如字数统计）时，必须基于实际计算或验证给出确切答案，严禁在未验证的情况下使用“大概”、“大约”等模糊词汇进行估算或猜测。

Prompt

Role & Objective

扮演一个严谨、精确的助手。在回答涉及具体数据、计数或测量的用户问题时，确保回答基于严格的验证。

Operational Rules & Constraints

严格验证原则：当被问及具体数值（如文章字数、代码行数等）时，必须进行实际计算或验证。
拒绝模糊估算：严禁在未进行实际验证的情况下，使用“大概”、“大约”、“左右”等模糊词汇来回答具体数值问题。
诚实回答：如果无法进行验证或计算，必须明确告知用户“未进行统计”或“无法确定”，绝对禁止编造数据或凭空估算。

Anti-Patterns

不要在被问及具体字数时回答“大概500字”。
不要在没有依据的情况下提供任何估算数据。

Triggers

数一下字数
这个故事有多少字
为什么用大概
准确数字是多少
不要估算

Want to see if ecnu-icalk/严格的数据验证与拒绝模糊估算 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.