dig
Clarify ambiguities in plans with structured questions and auto-decide rules
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Clarify ambiguities in plans with structured questions and auto-decide rules
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
Process issues sequentially: /dev per issue in isolated sub-agent → CI wait → merge → next
E2E development: investigate → dig → decompose → implement → test → review → PR
Break a task into ordered subtasks with dependencies
Investigate codebase for an issue in a forked context (context isolation)
Audit codebase for tech debt, code quality, and architecture issues — then create GitHub Issues
Create a pull request for the current branch using the project's PR template
| name | dig |
| description | Clarify ambiguities in plans with structured questions and auto-decide rules |
| user-invocable | true |
| allowed-tools | ["ToolSearch"] |
Resolve ambiguities before implementation by generating structured questions with options. Auto-decides choices that follow established project patterns.
From the investigation results, identify every decision point:
| # | Ambiguity | Category | Auto-decidable? |
|---|---|---|---|
| 1 | ... | architecture / api-design / data-flow / concurrency / error-handling / naming / testing | yes/no |
For auto-decidable ambiguities, check the project's CLAUDE.md, rules/*.md, and existing codebase patterns to determine the answer.
How to auto-decide:
Common decision categories:
For non-auto-decidable ambiguities:
For non-auto-decidable ambiguities in the architecture, api-design, or concurrency categories, consult Codex for alternative approaches before asking the user.
Skip this step for: naming, testing, error-handling, data-flow categories (these are resolved by codebase patterns or user preference).
ToolSearch("select:mcp__codex__codex")
mcp__codex__codex(
prompt: "Given these unresolved design decisions, explore alternatives:
## Ambiguities
{list of non-auto-decidable architecture/api-design/concurrency ambiguities with their options}
## Codebase Context
{relevant patterns from Step 2, existing conventions}
For each ambiguity:
1. Evaluate the proposed options
2. Suggest any additional alternatives not yet considered
3. Recommend the best option with reasoning
4. Flag any risks or trade-offs"
)
Incorporate Codex recommendations into the options presented to the user in Step 4.
If ToolSearch fails to find Codex or the call errors:
Present remaining unknowns with AskUserQuestion:
## Dig Results: {requirement}
### Auto-Decided
| # | Decision | Rule | Result |
|---|----------|------|--------|
| 1 | Where to place X | CLAUDE.md: "feature code in src/features/" | src/features/x/ |
### Investigated
| # | Decision | Finding | Result |
|---|----------|---------|--------|
| 2 | Error handling approach | Existing pattern in src/api/client.kt uses Result<T> | Result<T> |
### User-Decided
| # | Decision | Choice | Reason |
|---|----------|--------|--------|
| 3 | Public API surface | Option A: minimal | user preference |
### Assumptions (if any)
| # | Assumption | Risk |
|---|-----------|------|