Peter Steinberger

Oracle

AI 智能体v1.0.1
作者:Peter Steinberger更新于 2026-05-18共 2 个版本 · 最新版本发布于 2026-01-05oracle@clawhub_steipete/oracle
工作流编排提示词优化工具调用#Debugging#Browser#Prompt

据 AlphaMoat 统计,截至 2026-10,Oracle 累计下载 23,049 次、获 17 个星标,按累计下载量在本次参与排名的 10,914 个 AI 技能中排名第 1,232 位,在「AI 智能体」分类(1,632 个)中排名第 183 位。

列表默认按累计下载量排序,也可按星标排序;详情页排名按累计下载量计算。

累计下载
2.3万
星标
17
全站下载量排名
#1,232
全站前 12% · 「AI 智能体」前 12%
平台累计下载星标评论
ClawHub ↗2.0万17-
SkillHub ↗2.3万17—

各平台的计数口径不同,统计时间不一致。

这个技能是做什么的

技能用 oracle 命令行把提示词与选定文件合成一次性请求,交给另一套模型在真实仓库上下文里回答,用于调试、重构与设计评审。默认走 --engine browser,输出只作参考,必须回到代码与测试里核对。

资料发布于 2026-10-27

可以用来做什么

  • 让另一个模型复核一次重构方案的风险点
  • 把报错现场与相关文件打包做交叉验证

什么时候用

  • 同一问题想听第二个模型的判断时
  • 跨模型对比结论但不希望上传整个仓库时

示例提示词

以下是根据技能文档生成的示例,不代表实际运行结果。

把这次重构涉及的文件打包,让另一个模型指出可能破坏的调用方
这个线上报错我想交叉验证,先选好相关文件再发起一次复核

月度数据趋势

累计下载2.3万
1.7万2.0万2.3万2026-05 · 累计下载 1.8万2026-06 · 累计下载 1.8万2026-07 · 累计下载 1.9万2026-08 · 累计下载 2.0万2026-09 · 累计下载 2.0万2026-10 · 累计下载 2.3万26-0526-0926-10
星标17
1516172026-05 · 星标 152026-06 · 星标 162026-07 · 星标 172026-08 · 星标 172026-09 · 星标 172026-10 · 星标 1726-0526-0926-10

2026-09 起统计方法调整:同名技能按作者分别统计,并覆盖全部技能。图中虚线为调整前的月份,与之后的数据不直接比较,也不计算跨越调整的增长。 该技能有同名的其他版本,调整前的数据归属当前下载量最大的这一个。

月份累计下载环比星标
2026-102.3万—17
2026-092.0万—17
2026-082.0万+2.8%17
2026-071.9万+5.0%17
2026-061.8万+3.2%16
2026-051.8万—15

SKILL.md 原文

以下是作者发布的原始文件,按纯文本显示,本站未做修改或审核;其中的链接不可点击,命令请核实后再运行。抓取于 2026-10-23。

5.7 KB · ClawHub v1.0.1
---
name: oracle
description: Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.
---

# Oracle (CLI) — best use

Oracle bundles your prompt + selected files into one “one-shot” request so another model can answer with real repo context (API or browser automation). Treat outputs as advisory: verify against the codebase + tests.

## Main use case (browser, GPT‑5.2 Pro)
展开全部(共 112 行)

Default workflow here: `--engine browser` with GPT‑5.2 Pro in ChatGPT. This is the “human in the loop” path: it can take ~10 minutes to ~1 hour; expect a stored session you can reattach to.

Recommended defaults:
- Engine: browser (`--engine browser`)
- Model: GPT‑5.2 Pro (either `--model gpt-5.2-pro` or a ChatGPT picker label like `--model "5.2 Pro"`)
- Attachments: directories/globs + excludes; avoid secrets.

## Golden path (fast + reliable)

1. Pick a tight file set (fewest files that still contain the truth).
2. Preview what you’re about to send (`--dry-run` + `--files-report` when needed).
3. Run in browser mode for the usual GPT‑5.2 Pro ChatGPT workflow; use API only when you explicitly want it.
4. If the run detaches/timeouts: reattach to the stored session (don’t re-run).

## Commands (preferred)

- Show help (once/session):
  - `npx -y @steipete/oracle --help`

- Preview (no tokens):
  - `npx -y @steipete/oracle --dry-run summary -p "<task>" --file "src/**" --file "!**/*.test.*"`
  - `npx -y @steipete/oracle --dry-run full -p "<task>" --file "src/**"`

- Token/cost sanity:
  - `npx -y @steipete/oracle --dry-run summary --files-report -p "<task>" --file "src/**"`

- Browser run (main path; long-running is normal):
  - `npx -y @steipete/oracle --engine browser --model gpt-5.2-pro -p "<task>" --file "src/**"`

- Manual paste fallback (assemble bundle, copy to clipboard):
  - `npx -y @steipete/oracle --render --copy -p "<task>" --file "src/**"`
  - Note: `--copy` is a hidden alias for `--copy-markdown`.

## Attaching files (`--file`)

`--file` accepts files, directories, and globs. You can pass it multiple times; entries can be comma-separated.

- Include:
  - `--file "src/**"` (directory glob)
  - `--file src/index.ts` (literal file)
  - `--file docs --file README.md` (literal directory + file)

- Exclude (prefix with `!`):
  - `--file "src/**" --file "!src/**/*.test.ts" --file "!**/*.snap"`

- Defaults (important behavior from the implementation):
  - Default-ignored dirs: `node_modules`, `dist`, `coverage`, `.git`, `.turbo`, `.next`, `build`, `tmp` (skipped unless you explicitly pass them as literal dirs/files).
  - Honors `.gitignore` when expanding globs.
  - Does not follow symlinks (glob expansion uses `followSymbolicLinks: false`).
  - Dotfiles are filtered unless you explicitly opt in with a pattern that includes a dot-segment (e.g. `--file ".github/**"`).
  - Hard cap: files > 1 MB are rejected (split files or narrow the match).

## Budget + observability

- Target: keep total input under ~196k tokens.
- Use `--files-report` (and/or `--dry-run json`) to spot the token hogs before spending.
- If you need hidden/advanced knobs: `npx -y @steipete/oracle --help --verbose`.

## Engines (API vs browser)

- Auto-pick: uses `api` when `OPENAI_API_KEY` is set, otherwise `browser`.
- Browser engine supports GPT + Gemini only; use `--engine api` for Claude/Grok/Codex or multi-model runs.
- **API runs require explicit user consent** before starting because they incur usage costs.
- Browser attachments:
  - `--browser-attachments auto|never|always` (auto pastes inline up to ~60k chars then uploads).
- Remote browser host (signed-in machine runs automation):
  - Host: `oracle serve --host 0.0.0.0 --port 9473 --token <secret>`
  - Client: `oracle --engine browser --remote-host <host:port> --remote-token <secret> -p "<task>" --file "src/**"`

## Sessions + slugs (don’t lose work)

- Stored under `~/.oracle/sessions` (override with `ORACLE_HOME_DIR`).
- Runs may detach or take a long time (browser + GPT‑5.2 Pro often does). If the CLI times out: don’t re-run; reattach.
  - List: `oracle status --hours 72`
  - Attach: `oracle session <id> --render`
- Use `--slug "<3-5 words>"` to keep session IDs readable.
- Duplicate prompt guard exists; use `--force` only when you truly want a fresh run.

## Prompt template (high signal)

Oracle starts with **zero** project knowledge. Assume the model cannot infer your stack, build tooling, conventions, or “obvious” paths. Include:
- Project briefing (stack + build/test commands + platform constraints).
- “Where things live” (key directories, entrypoints, config files, dependency boundaries).
- Exact question + what you tried + the error text (verbatim).
- Constraints (“don’t change X”, “must keep public API”, “perf budget”, etc).
- Desired output (“return patch plan + tests”, “list risky assumptions”, “give 3 options with tradeoffs”).

### “Exhaustive prompt” pattern (for later restoration)

When you know this will be a long investigation, write a prompt that can stand alone later:
- Top: 6–30 sentence project briefing + current goal.
- Middle: concrete repro steps + exact errors + what you already tried.
- Bottom: attach *all* context files needed so a fresh model can fully understand (entrypoints, configs, key modules, docs).

If you need to reproduce the same context later, re-run with the same prompt + `--file …` set (Oracle runs are one-shot; the model doesn’t remember prior runs).

## Safety

- Don’t attach secrets by default (`.env`, key files, auth tokens). Redact aggressively; share only what’s required.
- Prefer “just enough context”: fewer files + better prompt beats whole-repo dumps.

「AI 智能体」分类下的热门技能

Peter Steinberger 的其他技能

数据月份:2026-10 · 下载/星标数聚合自公开技能注册库(ClawHub、SkillHub),按月更新。口径说明见数据方法。