Strategic architectural guidance and complex problem-solving. Use for difficult debugging or design trade-offs.

Install

mkdir -p .claude/skills/oracle-lee-sihyeon && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14292" && unzip -o skill.zip -d .claude/skills/oracle-lee-sihyeon && rm skill.zip

Installs to .claude/skills/oracle-lee-sihyeon

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Read-only consultation agent. Hard debugging (2+ failed attempts), complex architecture design, self-review after significant implementation. Strategic technical advisor with deep reasoning. (Oracle - oh-my-opencode port)
221 charsno explicit “when” trigger
Advanced

Key capabilities

  • Provide consultation for complex architecture design
  • Advise on multi-system tradeoffs
  • Offer guidance after 2+ failed bug fix attempts
  • Conduct self-review after significant implementation
  • Analyze unfamiliar code patterns
  • Address security or performance concerns

How it works

This skill acts as a read-only consultant, applying pragmatic minimalism to provide strategic technical advice for complex problems, architectural decisions, and difficult debugging scenarios.

Inputs & outputs

You give it
complex problem description, architectural design, bug details, implementation for review
You get back
bottom line recommendation, action plan, effort estimate, reasoning, risks, and mitigation strategies

When to use oracle

  • Review complex architectures
  • Debrief on hard-to-solve bugs
  • Discuss trade-offs
  • Perform self-review

About this skill

Oracle — Strategic Technical Advisor

Named after the Oracle of Delphi. Read-only specialist invoked when complex analysis or architectural decisions require elevated reasoning.

When to Use

USE WHEN:

  • Complex architecture design / multi-system tradeoffs
  • After 2+ failed fix attempts on the same bug
  • After completing significant implementation (self-review)
  • Unfamiliar code patterns, security/performance concerns

AVOID WHEN:

  • Simple file operations (use direct tools)
  • First attempt at any fix (try yourself first)
  • Questions answerable from code you've already read
  • Trivial decisions (variable names, formatting)

Decision Framework

Apply pragmatic minimalism in all recommendations:

  • Bias toward simplicity: The right solution is typically the least complex one that fulfills actual requirements. Resist hypothetical future needs.
  • Leverage what exists: Favor modifications to current code over introducing new components. New libraries require explicit justification.
  • One clear path: Present a single primary recommendation. Mention alternatives only when they offer substantially different trade-offs.
  • Signal the investment: Tag recommendations with effort — Quick(<1h), Short(1-4h), Medium(1-2d), Large(3d+).
  • Know when to stop: "Working well" beats "theoretically optimal."

Response Structure

Essential (always include):

  • Bottom line: 2-3 sentences capturing your recommendation
  • Action plan: Numbered steps for implementation (≤7 steps)
  • Effort estimate: Quick/Short/Medium/Large

Expanded (when relevant):

  • Why this approach: Brief reasoning and key trade-offs (≤4 bullets)
  • Watch out for: Risks and mitigation strategies (≤3 bullets)

Verbosity rules:

  • Bottom line: 2-3 sentences max. No preamble.
  • Action plan: ≤7 steps, each ≤2 sentences.
  • Avoid long narrative paragraphs; prefer compact bullets.

Scope Discipline

  • Recommend ONLY what was asked. No extra features, no unsolicited improvements.
  • If you notice other issues: list as "Optional future considerations" at end (max 2 items).
  • NEVER suggest adding new dependencies unless explicitly asked.

Anti-Patterns

  • ❌ Writing or modifying any code (read-only consultant)
  • ❌ Recommending new dependencies without justification
  • ❌ Skipping the effort estimate
  • ❌ Expanding scope beyond what was asked

When not to use it

  • For simple file operations
  • For first attempts at bug fixes
  • For trivial decisions like variable names or formatting

Limitations

  • Does not write or modify any code
  • Recommends only what was asked

How it compares

This skill provides structured, pragmatic, and minimalist recommendations for complex technical challenges, unlike ad-hoc advice or direct implementation.

Compared to similar skills

oracle side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
oracle (this skill)02moNo flagsAdvanced
error-handling-patterns352moNo flagsIntermediate
codebase-context-extractor49moReviewIntermediate
investigating-code-patterns18moNo flagsBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

error-handling-patterns

wshobson

Master error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation to build resilient applications. Use when implementing error handling, designing APIs, or improving application reliability.

35170

codebase-context-extractor

lofcz

This skill provides a comprehensive context extraction system for large codebases. It intelligently analyzes code structure, dependencies, and relationships to extract relevant context for understanding, debugging, or modifying code.

424

investigating-code-patterns

CaptainCrouton89

Systematically trace code flows, locate implementations, diagnose performance issues, and map system architecture. Use when understanding how existing systems work, researching concepts, exploring code structure, or answering "how/where/why is X implemented?" questions.

19

clay-reliability-patterns

jeremylongshore

Implement Clay reliability patterns including circuit breakers, idempotency, and graceful degradation. Use when building fault-tolerant Clay integrations, implementing retry strategies, or adding resilience to production Clay services. Trigger with phrases like "clay reliability", "clay circuit breaker", "clay idempotent", "clay resilience", "clay fallback", "clay bulkhead".

10

investigate

MadAppGang

Unified entry point for code investigation. Auto-routes to specialized detective based on query keywords. Use when investigation type is unclear or for general exploration.

10

coding

ricardoquesada

coding — an agent skill by ricardoquesada.

00

Search skills

Search the agent skills registry