Skip to content
cccskills
FreePublished on GitHubEnglish overview

oracle

Bundle a question and selected project files for a second AI model to review code, investigate bugs, or assess design options. Preview the files and token usage before running through an API or browser.

OriginalShow the original description

Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine.

openclaw/openclaw
Works withOpenAI
AI rating90/ 100See how to install

Good for

  • Getting a second AI opinion on code
  • Investigating errors with relevant project files
  • Comparing design and refactoring options
  • Previewing files and token usage before submission

Overview

What it does

Bundle your question and the files it needs, then send them to another AI model for code review, bug investigation, refactoring advice, or design advice. The oracle CLI lets you select files and exclusions and preview the outgoing content and token usage before execution. It supports API and browser execution. If a long run disconnects, you can reconnect to its saved session.

When it helps

Use it when you want another view on an unexplained error or need to compare the advantages and disadvantages of design options. Including relevant code, configuration, and reproduction steps gives the model concrete material to examine.

Example requests

  • “Gather the relevant files and error, then ask another model for the cause and possible fixes.”
  • “Compare these design options. Check the file list and token usage before sending.”

Notes

The oracle CLI is required. API execution uses OPENAI_API_KEY or Azure configuration; browser execution supports GPT and Gemini. Explain the project each time because the model does not remember previous runs. Files larger than 1 MB cannot be attached. Exclude secrets from attachments and treat responses as advice to verify against code and tests.

This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.

Objective evaluation

AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.

Clear instructionsIs it clear when to use it and what it does?
AGoodIt explicitly sends a prompt and selected files to another model for review and debugging.
Concrete stepsAre steps, inputs, outputs, and examples spelled out?
AGoodIt provides file selection, preview, execution, and reconnection steps with CLI command examples.
SafetyAre sending data, deleting files, and running commands disclosed?
AGoodIt instructs users to preview what is sent to another model and exclude secrets from attachments.
Easy setupDoes it need few tools or API keys, and are they documented?
BPartly lackingCLI installation examples are provided, but preparation steps for OPENAI_API_KEY or Azure configuration are absent.

The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 19, 2026. Treat it as a guide and read the original before installing.

Disagree? Request a re-evaluation

Tell us which point is wrong and why. No login needed. We will check it against the SKILL.md, redo the evaluation, and show the result here.

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

Files included (1)

  • SKILL.md4.8 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

oracle

Oracle bundles a prompt + selected files for one second-model pass. Treat output as advisory; verify against code + tests.

Main path

Current CLI default model: gpt-5.5-pro. Browser engine is useful for long ChatGPT Pro runs; API engine is useful when OPENAI_API_KEY or Azure config is ready.

Recommended defaults:

  • Preview first: --dry-run summary --files-report
  • Browser long run: --engine browser --model gpt-5.5-pro
  • API explicit: --engine api --model gpt-5.5

Golden path

  1. Pick a tight file set (fewest files that still contain the truth).
  2. Preview payload + token spend (--dry-run + --files-report).
  3. Use browser mode for long Pro thinking; API mode for explicit API calls.
  4. If the run detaches/timeouts: reattach to the stored session. Do not blindly re-run.

Commands (preferred)

  • Help:

    • oracle --help
    • If the binary isn't installed: npx -y @steipete/oracle --help (avoid pnpx here; sqlite bindings).

  • Preview (no tokens):

    • oracle --dry-run summary -p "<task>" --file "src/**" --file "!**/*.test.*"
    • oracle --dry-run full -p "<task>" --file "src/**"

  • Token sanity:

    • oracle --dry-run summary --files-report -p "<task>" --file "src/**"

  • Browser run (main path; long-running is normal):

    • oracle --engine browser --model gpt-5.5-pro -p "<task>" --file "src/**"

  • Manual paste fallback:

    • 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/**"
    • --file src/index.ts
    • --file docs --file README.md

  • Exclude:

    • --file "src/**" --file "!src/**/*.test.ts" --file "!**/*.snap"

  • Defaults (implementation behavior):

    • Default-ignored dirs: node_modules, dist, coverage, .git, .turbo, .next, build, tmp (skipped unless explicitly passed as literal dirs/files).
    • Honors .gitignore when expanding globs.
    • Does not follow symlinks.
    • Dotfiles filtered unless opted in via pattern (e.g. --file ".github/**").
    • Files > 1 MB rejected.

Engines (API vs browser)

  • Auto-pick: api when OPENAI_API_KEY is set; otherwise browser.
  • Browser supports GPT + Gemini only; use --engine api for Claude/Grok/Codex or multi-model runs.
  • Browser attachments:
    • --browser-attachments auto|never|always (auto pastes inline up to ~60k chars then uploads).
  • Remote browser host:
    • 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

  • Stored under ~/.oracle/sessions (override with ORACLE_HOME_DIR).
  • Runs may detach or take a long time (browser + Pro often does). If the CLI times out: do not 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, boundaries).
  • Exact question + what you tried + the error text (verbatim).
  • Constraints ("don't change X", "must keep public API", etc).
  • Desired output ("return patch plan + tests", "give 3 options with tradeoffs").

Attachments

  • Leave .env, key files, and auth tokens out of attachments unless the user asks to include them.

"Exhaustive prompt" restoration pattern

For long investigations, write a standalone prompt + file set so you can rerun days later:

  • 6-30 sentence project briefing + the goal.
  • Repro steps + exact errors + what you tried.
  • Attach all context files needed (entrypoints, configs, key modules, docs).

Oracle runs are one-shot; the model doesn't remember prior runs. "Restoring context" means re-running with the same prompt + --file … set (or reattaching a still-running stored session).

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

1password

FreeSummaryAI rating 100

Set up and authenticate the 1Password CLI, then supply stored passwords and API keys to commands or configuration. The skill covers desktop integration, service accounts, and interactive sign-in while keeping secrets out of chat and logs.

  • Setting up the 1Password CLI
  • Supplying API keys to commands
  • Using service account authentication in CI
openclaw/openclaw392.4KUpdated Oct 18, 2026

acp-router

FreeSummaryAI rating 80

Route requests from OpenClaw to external coding agents such as Claude Code or Cursor. Start or continue sessions using ACP, a protocol for connecting agents, or relay prompts directly through acpx while preserving conversation context.

  • Starting a Claude Code session in a thread
  • Continuing work with an external coding agent
  • Relaying prompts directly through acpx
openclaw/openclaw392.4KUpdated Oct 18, 2026

add-model-provider

FreeSummaryAI rating 100

Add a model provider to OpenClaw and verify it with a real response. The skill validates configuration, keeps credentials in environment or file references, and reports test results and any default model changes.

  • Adding a model provider to OpenClaw
  • Configuring credentials through environment or file references
  • Checking whether a model returns a real response
openclaw/openclaw392.4KUpdated Oct 18, 2026

agent-transcript

FreeSummaryAI rating 90

Prepare an agent activity transcript for a GitHub pull request or issue. Extract relevant prompts, decisions, and results from local logs, remove sensitive material, and preview the edited record before separately authorized publication.

  • Preparing an agent activity record for a pull request
  • Extracting task-relevant prompts and results from local logs
  • Previewing a transcript with sensitive information removed
openclaw/openclaw392.4KUpdated Oct 18, 2026

apple-notes

FreeSummaryAI rating 100

Manage Apple Notes on macOS through memo, a command-line tool. Create, browse, search, edit, delete, and move notes between folders, or export selected notes to HTML or Markdown for use outside the app.

  • Creating notes with titles
  • Finding notes by folder or approximate search
  • Editing notes and organizing them into folders
openclaw/openclaw392.4KUpdated Oct 18, 2026

apple-reminders

FreeSummaryAI rating 70

Manage Apple Reminders from your Mac with remindctl, a terminal tool. View tasks by date, add or edit reminders, organize lists, and mark tasks complete or delete them, including personal to-dos that sync to iOS.

  • Review today’s tasks and overdue reminders
  • Add personal to-dos with due dates
  • Organize tasks visible on an iPhone or iPad
openclaw/openclaw392.4KUpdated Oct 18, 2026

See all skills by openclaw

Report a problem with this skill