AgentSkillsCN

Consult

咨询

SKILL.md
<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->

name: consult description: "Use when user asks to "consult gemini", "ask codex", "get second opinion", "cross-check with claude", "consult another AI", "ask opencode", "copilot opinion". Queries another AI CLI tool and returns the response."

/consult - Cross-Tool AI Consultation

You are executing the /consult command. Your job is to consult another AI CLI tool, get its response, and present the results to the user.

Constraints

  • •NEVER expose API keys in commands or output
  • •NEVER run with permission-bypassing flags (--dangerously-skip-permissions, bypassPermissions)
  • •MUST use safe-mode defaults (-a suggest for Codex, --allowedTools "Read,Glob,Grep" for Claude)
  • •MUST enforce 120s timeout on all tool executions
  • •MUST validate --tool against allow-list: gemini, codex, claude, opencode, copilot (reject all others)
  • •MUST validate --context=file=PATH is within the project directory (reject absolute paths outside cwd)
  • •MUST quote all user-provided values in shell commands to prevent injection
  • •NEVER execute tools the user has not explicitly requested

Arguments

Parse from $ARGUMENTS:

  • •question: What to ask the consulted tool (required unless --continue)
  • •--tool: Target tool: gemini, codex, claude, opencode, copilot (interactive picker if omitted)
  • •--effort: Thinking effort: low, medium, high, max (interactive picker if omitted)
  • •--model: Specific model name (interactive picker if omitted). Free text.
  • •--context: Auto-include context: diff (git diff), file=PATH (attach specific file), none (default)
  • •--continue: Continue last consultation session, or --continue=SESSION_ID for specific session

Execution

Phase 1: Parse Arguments

Extract these values from $ARGUMENTS:

  1. •Look for --tool=VALUE or --tool VALUE where VALUE MUST be one of: gemini, codex, claude, opencode, copilot (reject others)
  2. •Look for --effort=VALUE or --effort VALUE where VALUE MUST be one of: low, medium, high, max
  3. •Look for --model=VALUE or --model VALUE (any string, including quoted strings like "my model")
  4. •Look for --context=VALUE where VALUE is: diff, file=PATH, or none
  5. •Look for --continue (optionally --continue=SESSION_ID)
  6. •Remove all matched flags (including their values) from $ARGUMENTS. Handle quoted flag values (e.g., --model "gpt 4") by removing the entire quoted string. Everything remaining is the question.

If no question text and no --continue flag found, show:

code
[ERROR] Usage: /consult "your question" [--tool=gemini|codex|claude|opencode|copilot] [--effort=low|medium|high|max]

Phase 2: Interactive Parameter Selection

MUST resolve ALL missing parameters interactively before Phase 3. ONLY skip this phase if ALL of --tool, --effort, AND --model are explicitly provided by the user in $ARGUMENTS. Do NOT silently default any parameter.

Step 2a: Handle --continue

If --continue is present:

  1. •

    Read the session file at {AI_STATE_DIR}/consult/last-session.json

    Platform state directory:

    • •Claude Code: .claude/
    • •OpenCode: .opencode/
    • •Codex CLI: .codex/
  2. •

    If the file exists, restore the saved tool, session_id, and model from it

  3. •

    If the file does not exist, show [WARN] No previous session found and proceed as a fresh consultation

Step 2b: Batch Selection (tool + effort)

First, detect which tools are installed by running all 5 checks in parallel via Bash:

  • •where.exe <tool> 2>nul && echo FOUND || echo NOTFOUND (Windows)
  • •which <tool> 2>/dev/null && echo FOUND || echo NOTFOUND (Unix)

Check for: claude, gemini, codex, opencode, copilot.

If zero tools are installed: [ERROR] No AI CLI tools found. Install at least one: npm i -g @anthropic-ai/claude-code, npm i -g @openai/codex, npm i -g opencode-ai

Then use a SINGLE request_user_input call to ask all missing parameters at once. Include only the questions for parameters NOT already provided in $ARGUMENTS:

code
request_user_input:
> **Codex**: Each question MUST include a unique `id` field (e.g., `id: "q1"`).
  questions:
    - header: "AI Tool"                          # SKIP if --tool provided
      question: "Which AI tool should I consult?"
      options (only if installed):
        - label: "Claude"       description: "Deep code reasoning"
        - label: "Gemini"       description: "Fast multimodal analysis"
        - label: "Codex"        description: "Agentic coding"
        - label: "OpenCode"     description: "Flexible model choice"
        - label: "Copilot"      description: "GitHub-integrated AI"

    - header: "Effort"                           # SKIP if --effort provided
      question: "What thinking effort level?"
      options:
        - label: "Medium (Recommended)"  description: "Balanced speed and quality"
        - label: "Low"                   description: "Fast, minimal reasoning"
        - label: "High"                  description: "Thorough analysis"
        - label: "Max"                   description: "Maximum reasoning depth"

Map tool choice to lowercase: "Claude" -> "claude", "Codex" -> "codex", etc. Map effort choice: "Medium (Recommended)" -> "medium", "Low" -> "low", "High" -> "high", "Max" -> "max".

IMPORTANT: Do NOT skip any missing parameter. Do NOT silently default --effort to "medium" or --tool to any value. Present pickers for ALL unresolved parameters.

Step 2c: Model Selection (MUST ask if no --model)

After tool is resolved (from Step 2b or $ARGUMENTS), present a model picker with options specific to the selected tool. The user can always type a custom model name via the "Other" option.

For Claude:

code
request_user_input:
> **Codex**: Each question MUST include a unique `id` field (e.g., `id: "q1"`).
  questions:
    - header: "Model"
      question: "Which Claude model?"
      options:
        - label: "sonnet (Recommended)"  description: "Sonnet 4.5 - balanced speed and intelligence"
        - label: "opus"                  description: "Opus 4.6 - most capable, adaptive thinking"
        - label: "haiku"                 description: "Haiku 4.5 - fastest, lightweight"

For Gemini:

code
request_user_input:
> **Codex**: Each question MUST include a unique `id` field (e.g., `id: "q1"`).
  questions:
    - header: "Model"
      question: "Which Gemini model?"
      options:
        - label: "gemini-3-pro"          description: "Most capable, strong reasoning"
        - label: "gemini-3-flash"        description: "Fast, 78% SWE-bench"
        - label: "gemini-2.5-pro"        description: "Previous gen pro model"
        - label: "gemini-2.5-flash"      description: "Previous gen flash model"

For Codex:

code
request_user_input:
> **Codex**: Each question MUST include a unique `id` field (e.g., `id: "q1"`).
  questions:
    - header: "Model"
      question: "Which Codex model?"
      options:
        - label: "gpt-5.3-codex"        description: "Latest, most capable coding model"
        - label: "gpt-5.2-codex"        description: "Strong coding model"
        - label: "gpt-5.2"              description: "General purpose GPT-5.2"
        - label: "gpt-5-codex-mini"     description: "Cost-effective, 4x more usage"

For OpenCode:

code
request_user_input:
> **Codex**: Each question MUST include a unique `id` field (e.g., `id: "q1"`).
  questions:
    - header: "Model"
      question: "Which model? (type via Other for paid: anthropic/claude-opus-4-6, openai/gpt-5.3-codex)"
      options:
        - label: "opencode/big-pickle"             description: "Free - Zen stealth model, 200K context"
        - label: "opencode/minimax-m2.1-free"      description: "Free - 230B MoE, strong multilingual coding"
        - label: "opencode/kimi-k2.5-free"         description: "Free - 1T multimodal, strong coding and agentic"
        - label: "opencode/trinity-large-preview"  description: "Free - 400B sparse MoE by Arcee AI, 512K context"

For Copilot:

code
request_user_input:
> **Codex**: Each question MUST include a unique `id` field (e.g., `id: "q1"`).
  questions:
    - header: "Model"
      question: "Which Copilot model?"
      options:
        - label: "claude-sonnet-4-5"        description: "Default Copilot model"
        - label: "claude-opus-4-6"          description: "Most capable Claude model"
        - label: "gpt-5.3-codex"              description: "OpenAI GPT-5.3 Codex"
        - label: "gemini-3-pro"             description: "Google Gemini 3 Pro"

Map the user's choice to the model string (strip " (Recommended)" suffix if present). Pass the selected model to the skill via --model.

IMPORTANT: Do NOT skip this step. Do NOT silently use a default model. If --model was not explicitly provided in $ARGUMENTS, you MUST present this picker. The model lists above are current as of Feb 2026 - the user may type any model name supported by their tool via the "Other" option.

Phase 3: Invoke Consult Skill

With all parameters resolved (tool, effort, model, question, and optionally context, continue), invoke the consult skill using the Skill tool:

code
Skill: consult
Args: "[question]" --tool=[tool] --effort=[effort] --model=[model] [--context=[context]] [--continue=[session_id]]

Example: "Is this the right approach?" --tool=gemini --effort=high --model=gemini-3-pro

The skill handles the full consultation lifecycle: it resolves the model from the effort level, builds the CLI command, packages any context, executes the command via Bash with a 120-second timeout, and returns a plain JSON result.

Phase 4: Parse Skill Output

The skill returns a plain JSON object containing: tool, model, effort, duration_ms, response, session_id, and continuable. Parse the JSON directly from the skill output.

Phase 5: Present Results

After parsing the JSON, format and display the result as human-friendly text:

code
Tool: {tool}, Model: {model}, Effort: {effort}, Duration: {duration_ms}ms.

The results of the consultation are:
{response}

For continuable tools (Claude/Gemini), also display: Session: {session_id} - use /consult --continue to resume

Save session state for continuable tools (Claude, Gemini) to {AI_STATE_DIR}/consult/last-session.json.

Platform state directory:

  • •Claude Code: .claude/
  • •OpenCode: .opencode/
  • •Codex CLI: .codex/

On failure: [ERROR] Consultation Failed: {specific error message}

Error Handling

ErrorOutput
No question provided[ERROR] Usage: /consult "your question" [--tool=gemini|codex|claude|opencode|copilot] [--effort=low|medium|high|max]
Tool not installed[ERROR] {tool} is not installed. Install with: {install command from skill}
Tool execution fails[ERROR] {tool} failed: {error}. Try a different tool with --tool=[other]
Timeout (>120s)[ERROR] {tool} timed out after 120s. Try --effort=low for faster response
No tools available[ERROR] No AI CLI tools found. Install: npm i -g @anthropic-ai/claude-code
Session not found[WARN] No previous session found. Starting fresh consultation.
API key missing[ERROR] {tool} requires API key. Set {env var} (see skill for details)

Example Usage

bash
/consult "Is this the right approach for error handling?" --tool=gemini --effort=high
/consult "Review this function for performance issues" --tool=codex
/consult "What alternative patterns would you suggest?" --tool=claude --effort=max
/consult "Suggest improvements" --tool=opencode --model=github-copilot/claude-opus-4-6
/consult "Continue from where we left off" --continue
/consult "Explain this error" --context=diff --tool=gemini
/consult "Review this file" --context=file=src/index.js --tool=claude