Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ayuayue/PiDeck --skill pideck-doctorgit clone --depth 1 https://github.com/ayuayue/PiDeckWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ayuayue/pideck/pideck-doctor)<a href="https://agentmods.dev/skills/ayuayue/pideck/pideck-doctor"><img src="https://agentmods.dev/badge/skills/ayuayue/pideck/pideck-doctor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ayuayue/pideck/pideck-doctor"><img src="https://agentmods.dev/badge/skills/ayuayue/pideck/pideck-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00116 | $0.01349 |
| Opus 5 | $0.00058 | $0.00674 |
| Sonnet 5 | $0.00023 | $0.00270 |
| Haiku 4.5 | $0.00012 | $0.00135 |
Grade A, and why
pideck-doctor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PiDeck 环境诊断(pideck-doctor)
这是什么
用户在 PiDeck 里遇到问题(pi 连不上、会话起不来、卡顿、闪退、模型列表为空等)时, 本技能引导用户走一条标准排障路径,用一份脱敏诊断报告替代反复追问环境细节, 快速定位根因。
第一步:让用户生成诊断报告
请用户打开 PiDeck 的**「问题反馈」入口(侧边栏/帮助菜单 → 意见反馈 → 环境诊断 tab), 点击「生成诊断报告」**,然后:
- 描述问题现象,最好补充复现步骤;
- 在「导出分享」里复制报告(Markdown 或 AI 提示词形态);
- 把报告粘贴给 AI(本会话)。
用户也支持直接导出 zip(含脱敏日志),但尽量先拿 Markdown 报告,zip 仅在报告不足以 定位时再要求(zip 里是逐行脱敏的日志,同样不含原始配置内容)。
报告包含什么
- 环境信息:PiDeck 版本、安装形态(安装版/便携版/开发态)、OS 版本、Electron/Node/Chrome 版本、 locale、时区、WSL/代理等开关状态(只给开关布尔值,不给代理地址);
- 体检项:pi 是否已装且可读版本、pi 配置(models/auth/settings.json)是否可解析、 最近 7 天 error/warn 条数、数据盘剩余空间、主进程常驻内存、代理配置是否自洽、 WSL 兜底是否自洽;
- 最近报错日志:脱敏后的最新 warn/error(时间/级别/作用域/消息)。
所有路径都把 home 目录替换成 ~,token/Key/邮箱/手机号一律替换为 [redacted]。
第二步:对照故障模式库定位
pi 未安装 / 版本读不出来
- 现象:体检项
pi.installed为 error/warn。 - 处置:引导用户检查自定义 pi 路径设置(可能指到了非 pi 程序);安装正式 pi;Windows 上用
WSL 兜底时确认发行版已填。定位到
~/.pi/agent目录存在且 models.json 在。
配置损坏(models/auth/settings 解析失败)
- 现象:体检项
config.parsable为 error,模型列表为空、会话起不来。 - 处置:不要直接改配置原文(可能含 apiKey)。先建议备份对应 json 到别处, 再让用户在「配置管理」界面重新填写/重置。若 JSON 明显缺字段导致解析失败, 可重建最小结构,但保留原有 key 值不动。
报错密度高(logs.errors 异常)
- 现象:
logs.errors为 error/warn,且 recent 里能看到具体错误作用域。 - 处置:读取 recent 报错,按作用域归类(rpc / agent / terminal / git / web 等), 定位具体异常类型。若错误消息里出现路径/Key,已由脱敏替换,需结合上下文推断。
磁盘不足
- 现象:
disk.space为 error(< 512MB)或 warn(< 2GB)。 - 处置:引导清理数据目录(userData)或系统磁盘;会话/日志写不进去是闪退常见根因。
内存过高
- 现象:
memory.rss为 error(≥ 3GB)。 - 处置:多为内存泄漏或超大会话,建议重启应用、关闭大会话后复测。
代理自相矛盾
- 现象:
proxy.consistency为 warn(开了代理却没填地址)。 - 处置:在设置里填代理地址或关闭对应代理开关。
WSL 兜底失效
- 现象:
wsl.config为 warn(开了 WSL 却没填发行版)。 - 处置:在设置里填发行版名,或关闭 WSL 兜底用原生 pi。
第三步:给出修复并复测
- 每给一条修复建议,都让用户重新生成一次诊断报告,对比相关体检项是否从 error/warn 变为 ok——用数据验证修复是否生效,而不是猜。
- 若修复后仍异常,导出 zip 日志包,@群内支持者继续排查。
边界与隐私
- 只读诊断报告,不读原始配置:报告已脱敏,绝不要求用户把 auth.json/models.json 原文贴出来。
- 不代替 pi 做 Agent 行为:本技能只管 PiDeck 应用自身的安装/配置/环境问题,不处理 pi 内部的模型调用/工具逻辑(那些属于 pi 自身的排障)。
- 报告里的路径是
~缩写:需要真实路径定位时,请用户在应用内通过「设置 → 打开数据目录」 查看,而不是要求贴完整路径。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 84 lines · 116 tokens per session scan A 18f79100a9ae
pideck-doctor is a skill published in the GitHub repository ayuayue/PiDeck (783 stars, last pushed today), licensed MIT. It adds 116 tokens to every session and 1,349 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
ha-logs
A read-only troubleshooting skill for querying Hope Agent’s local SQLite databases, which store logs, conversations, and background-job status.
ha-self-diagnosis
Self-understanding and issue reporting for Hope Agent itself. Use when the user asks how Hope Agent works internally, asks about its own source code/docs/runtime behavior, reports a bug/failure/slowness/crash, asks to diagnose logs, or asks to create/submit a GitHub issue for a bug, feature request, or improvement…
ha-debug
Hope-native debugging for code failures, regressions, crashes, flaky behavior, and bad output: reproduce or characterize, rank falsifiable hypotheses, fix the smallest root cause, and prove the failing path.
desktop-inspect
Inspect window UI element tree structure for debugging and understanding interface layout. When you need to debug UI automation issues, understand application structure, or find correct element identifiers.
tlamatini-flw-doctor
Validate a .flw workflow file: check connection topology, terminal agents, Parametrizer single-lane queue, missing connectors, dangling targetagents.
superpowers-systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.