Peter Steinberger

Oracle

AI 智慧體v1.0.1
作者:Peter Steinberger更新於 2026-05-18共 2 個版本 · 最新版本釋出於 2026-01-05oracle@clawhub_steipete/oracle
工作流編排提示詞最佳化工具呼叫#Debugging#Browser#Prompt

據 AlphaMoat 統計,截至 2026-10,Oracle 累計下載 23,049 次、獲 17 個星標,按累計下載量在本次參與排名的 10,914 個 AI 技能中排名第 1,232 位,在「AI 智慧體」分類(1,632 個)中排名第 183 位。

列表預設按累計下載量排序,也可按星標排序;詳情頁排名按累計下載量計算。

累計下載
2.3萬
星標
17
全站下載量排名
#1,232
全站前 12% · 「AI 智慧體」前 12%
平台累計下載星標評論
ClawHub ↗2萬17-
SkillHub ↗2.3萬17—

各平台的計數口徑不同,統計時間不一致。

這個技能是做什麼的

技能用 oracle 命令列把提示詞與選定檔案合成一次性請求,交給另一套模型在真實倉庫上下文裡回答,用於除錯、重構與設計評審。預設走 --engine browser,輸出只作參考,必須回到程式碼與測試裡核對。

資料釋出於 2026-10-27

可以用來做什麼

  • 讓另一個模型複核一次重構方案的風險點
  • 把報錯現場與相關檔案打包做交叉驗證

什麼時候用

  • 同一問題想聽第二個模型的判斷時
  • 跨模型對比結論但不希望上傳整個倉庫時

示例提示詞

以下是根據技能文件生成的示例,不代表實際執行結果。

把這次重構涉及的檔案打包,讓另一個模型指出可能破壞的呼叫方
這個線上報錯我想交叉驗證,先選好相關檔案再發起一次複核

月度資料趨勢

累計下載2.3萬
1.7萬2萬2.3萬2026-05 · 累計下載 1.8萬2026-06 · 累計下載 1.8萬2026-07 · 累計下載 1.9萬2026-08 · 累計下載 2萬2026-09 · 累計下載 2萬2026-10 · 累計下載 2.3萬26-0526-0926-10
星標17
1516172026-05 · 星標 152026-06 · 星標 162026-07 · 星標 172026-08 · 星標 172026-09 · 星標 172026-10 · 星標 1726-0526-0926-10

2026-09 起統計方法調整:同名技能按作者分別統計,並覆蓋全部技能。圖中虛線為調整前的月份,與之後的資料不直接比較,也不計算跨越調整的增長。 該技能有同名的其他版本,調整前的資料歸屬當前下載量最大的這一個。

月份累計下載環比星標
2026-102.3萬—17
2026-092萬—17
2026-082萬+2.8%17
2026-071.9萬+5.0%17
2026-061.8萬+3.2%16
2026-051.8萬—15

SKILL.md 原文

以下是作者釋出的原始檔案,按純文字顯示,本站未做修改或稽核;其中的連結不可點選,命令請核實後再執行。抓取於 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)
展開全部(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 智慧體」分類下的熱門技能

Peter Steinberger 的其他技能

資料月份:2026-10 · 下載/星標數聚合自公開技能註冊庫(ClawHub、SkillHub),按月更新。口徑說明見資料方法。