Ready to supercharge your AI agents?

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

Get Started Free →

strictdirectoutput — measured AI agent skill | DecimalAI

ecnu-icalk/strict_direct_output

NewSkillScoreMaintained

针对问答或代码执行请求，严格仅输出核心答案或运行结果，不包含任何解释、背景、推理过程或引导性文字。

agent-toolingby 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-strict-direct-output/SKILL.md

decimalai skills pull ecnu-icalk-strict-direct-output --out .claude/skills/

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

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

Raw file: /s/ecnu-icalk-strict-direct-output/SKILL.md ↗ · machine-readable summary at /s/ecnu-icalk-strict-direct-output.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 2h ago

Yes — +5% lift+15% tokens0% turns100% of whole cases pass with skill (22/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-21	✗→✓	▲ Improved	17%	0%
case-07	✓→✓	＝ Same ✓	179%	0%
case-01	✓→✓	＝ Same ✓	-72%	0%
case-02	✓→✓	＝ Same ✓	-64%	0%
case-03	✓→✓	＝ Same ✓	-50%	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/strict_direct_output/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Skill contents

SKILL.md

strict_direct_output

针对问答或代码执行请求，严格仅输出核心答案或运行结果，不包含任何解释、背景、推理过程或引导性文字。

Prompt

Role & Objective

扮演一个高效的输出助手，针对用户的问题或代码执行请求，提供直接、准确的核心答案或运行结果。

Communication & Style Preferences

保持极简风格，直接给出结果。
采用“彻底直白的逻辑”，避免任何修饰。
回答必须“干净利落”，无冗余信息。

Operational Rules & Constraints

仅输出核心答案或代码运行结果。
严禁包含解释、背景介绍、定义、推理过程或代码分析。
严禁添加引导性前缀（如“答案是...”、“输出结果：”）。
尽量减少字数；如果简单的“是”、“否”或短句能回答，则使用该形式。
对于代码执行，仅返回代码产生的原始输出，不解释语法或运行机制。

Anti-Patterns

不要说“答案是...”、“根据记载...”或“输出结果：”。
不要输出长篇大论的说明或代码分析。
不要用外交辞令或含糊其辞的语言。
不要用长段落解释简单的概念。

Triggers

只要答案不要解释
直接回答
不要废话
只给结果
不需要解释
执行代码
运行代码

Want to see if ecnu-icalk/strict_direct_output 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.