Ready to supercharge your AI agents?

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

Get Started Free →

Distill Shield · agenmod | DecimalAI

securityby agenmod

Distill Shield

agenmod/distill-shield

Source agenmod/immortal-skill ↗License MIT

Distill Shield：为个人移交资料包生成 Canary 与可选加固策略，提高未授权蒸馏成本；仅适用于有权处置的数据。

SkillScore86Maintained

Automatic

Security & AppSec pack

Last verified 8/14/2026

What it changes

Passed 18 of 21 test cases with the skill, and 10 of 21 without it.

Without skill45%

With skill86%

Checks it passed that the model alone missed

Specifies using the --label parameter.
Notes that contradiction samples may confuse human readers.
States that contradiction samples pollute distillation output consistency.

and 10 more in the full report

9 fixed10 passed either way3 still failing0 broke

Pass-rate lift: +41 pp
Tokens: +3%
Agent turns: 0%
Response time: -31%

Model gemini-3.6-flashMeasured 8/14/2026v119 of 22 cases passed with skill · 21 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/agenmod-distill-shield/SKILL.md https://app.decimal.ai/s/agenmod-distill-shield/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add agenmod-distill-shield, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

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

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/agenmod-distill-shield/ and pins it in .decimal/skills.lock

decimalai skills add agenmod-distill-shield

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

curl -fsSL --create-dirs -o .claude/skills/agenmod-distill-shield/SKILL.md https://app.decimal.ai/s/agenmod-distill-shield/SKILL.md

Raw file: /s/agenmod-distill-shield/SKILL.md ↗ · machine-readable summary at /s/agenmod-distill-shield.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

使用 Shield 生成脚本标记自定义业务名称为 '财务审计2024' 时，使用哪个命令行参数？

What was checked, without and with the skill
Checked	Without skill	With skill
Specifies using the --label parameter.	Missed	Passed

case-20 · gemini-3.6-flash · 8/14/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md81 linessingle file

复制给 AI

本 Skill 唯一入口：当前文件 distill-shield-skill/SKILL.md。
仓库根：假定 immortal-skill/（或含本目录与 kit/ 的克隆根）。
从仓库根运行生成脚本（推荐，避免路径歧义）：

python3 distill-shield-skill/kit/shield_gen.py --output ./handover-bundle --label "我的移交包"

聚合入口：FOR_AI.md 第三节。

Distill Shield

语言

根据用户第一条消息的语言，全程使用同一语言。

何时激活

用户要「防蒸馏」「加固资料包」「移交前埋 Canary」。
用户运行 kit/shield_gen.py 后需要根据输出做伦理与可读性检查。

伦理红线

仅对本人或已获授权的数据使用；禁止对他人资料恶意投毒。
不承诺数学上不可攻破；承诺 可检测性、审计成本、部分管线干扰。

路径约定

本 Skill 根目录 {baseDir} = distill-shield-skill/。

操作顺序

Phase 0：威胁模型

蒸馏场景：一次性 LLM 蒸馏 vs 批量训练 vs 仅人类阅读？
接收方：家人 / 律师 / 公司？（决定策略强度）

Phase 1：材料盘点

Track record

Benchmark

18 / 21

test cases passed, vs 10 / 21 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

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

agenmod / immortal-skill

distill-shield-skill/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

复制给 AI

Distill Shield

语言

何时激活

伦理红线

路径约定

操作顺序

Phase 0：威胁模型

Phase 1：材料盘点

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills