Ready to supercharge your AI agents?

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

External System Debugging · doccker | DecimalAI

codingby doccker

External System Debugging

doccker/external-system-debugging

Source doccker/cc-use-exp ↗License NOASSERTION

涉及浏览器、编辑器、CDN/WAF、IM 平台、操作系统剪贴板、第三方 SaaS 等"外部黑盒系统"的代码编写或 bug 调试时触发。强制先抓真实环境数据再推理,避免连续 2 轮"凭代码推理"的修复 no-op。关键词:粘贴/复制异常、跨平台显示不一致、第三方 API 怪结果、CDN/WAF 拦截、本地复现失败、HTML→MD 转换丢属性。

SkillScore82Maintained

Automatic

Coding pack

Last verified 8/13/2026

What it changes

Passed 17 of 21 test cases with the skill, and 10 of 21 without it.

Without skill45%

With skill82%

Checks it passed that the model alone missed

Requires capturing binary payload data using hexdump.
Requires capturing HTML content using outerHTML instead of innerText.
Demands explicitly marking unverified environment versions as unknown.

and 9 more in the full report

8 fixed10 passed either way4 still failing0 broke

Pass-rate lift: +36 pp
Tokens: +48%
Agent turns: 0%
Response time: -20%

Model gemini-3.6-flashMeasured 8/13/2026v318 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/doccker-external-system-debugging/SKILL.md https://app.decimal.ai/s/doccker-external-system-debugging/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add doccker-external-system-debugging, 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/doccker-external-system-debugging/ and pins it in .decimal/skills.lock

decimalai skills add doccker-external-system-debugging

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

curl -fsSL --create-dirs -o .claude/skills/doccker-external-system-debugging/SKILL.md https://app.decimal.ai/s/doccker-external-system-debugging/SKILL.md

Raw file: /s/doccker-external-system-debugging/SKILL.md ↗ · machine-readable summary at /s/doccker-external-system-debugging.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

We want to set up a standardized placeholder framework in our repository to prepare for upcoming third-party browser clipboard formatting bugs before full post-mortems are written. What file naming convention should be used for these placeholder frameworks?

What was checked, without and with the skill
Checked	Without skill	With skill
Directs naming placeholder files using the template-{system}-{symptom}.md convention under references/.	Missed	Passed

case-17 · gemini-3.6-flash · 8/13/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md119 lines4 files

外部黑盒系统调试方法论

"代码没说谎,但黑盒系统的行为不在代码里。"

涉及代码以外的环境(浏览器、编辑器、CDN、IM 平台、第三方 API),编码和调试都必须先抓真实数据,再做推理。

何时触发

写代码场景

输出会被第三方平台消费的内容(HTML 推送到 CSDN/微信/Notion/钉钉/飞书)
集成浏览器/操作系统 API(Clipboard / Drag-Drop / File System)
调用经过 CDN/WAF/反代的第三方 HTTP API
在 IM / 富文本编辑器中渲染内容

调试场景

跨浏览器/跨设备/跨终端表现不一致
粘贴/复制行为异常
第三方 API 返回怪结果(body 空、headers 不全、200 但 error)
本地复现失败但线上有问题
连续 2 轮"凭代码推理"的修复都 no-op(最强信号)

黑盒判定清单

维度	不是黑盒	是黑盒(触发本 skill)
控制权	自己写的代码	第三方/平台/浏览器实现
文档完备性	有完整 API 文档	文档不全或有未文档化行为
可调试性	能加日志、断点	只能从外部观察输入输出
行为可预测	给定输入必然得到给定输出	同一输入在不同环境表现不同

满足任意 2 项 → 走本 skill 方法论。

数据采集模板(核心)

Track record

Benchmark

17 / 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

doccker / cc-use-exp

.antigravity/skills/external-system-debugging/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v3Bundled 3 files

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

doccker/cc-external-system-debugging涉及浏览器、编辑器、CDN/WAF、IM 平台、操作系统剪贴板、第三方 SaaS 等"外部黑盒系统"的代码编写或 bug 调试时触发。强制先抓真实环境数据再推理,避免连续 2 轮"凭代码推理"的修复 no-op。关键词:粘贴/复制异常、跨平台显示不一致、第三方 API 怪结果、CDN/WAF 拦截、本地复现失败、HTML→MD 转换丢属性。Near-identical description+27 pp pass-rate lift

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