mcouthon/agents/clarify

Claude Code and agent skill by mcouthon/agents

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Bounded clarification/refinement pass for planning. Use before finalizing a phased plan when unresolved [?] markers or plan-changing ambiguity remain. Triggers on: 'use clarify mode', 'clarify', 'clarify the plan', 'resolve ambiguity', 'clarifying questions'.

Install

npx vskill@latest install mcouthon/agents/clarify

SKILL.md

Clarify Mode — Bounded Refinement Pass

Run this pass before finalizing the phased plan (Step 6) to resolve plan-changing ambiguity. Work high-level → detailed. This is the single sanctioned place to raise questions — bounded, not a gate.

When to run

Run the ambiguity scan for any task that will produce a multi-phase plan. This is the default for multi-phase work — the scan is a silent mental pass, not a ceremony.

Quick-exit: Skip for single-phase / trivially-scoped tasks where scope is self-evident (e.g., "fix this typo", "bump version to X", "rename Y to Z").

The ≤5 cap is a ceiling, never a target. Fewer is better.

Two delivery modes

Determine which mode you are in before proceeding:

  • Subagent (spawned by the Conductor or another agent): you CANNOT prompt the user

directly. Return your plan draft and append an ## Open clarifying questions block (format below). Do NOT try to ask interactively.

  • Direct invocation (user ran you directly): ask the user via conversational turns,

one question at a time where an answer informs the next.

  • If unsure which mode you are in, assume subagent and return questions.

Ambiguity scan

Before collecting [?] markers, silently scan the task against these common ambiguity patterns. Only surface items where the answer isn't determinable from the user's prompt or the codebase:

  • Scope boundaries — what's in, what's explicitly out?
  • Backward compatibility — does this change behavior for existing consumers?
  • Error/edge-case strategy — fail loudly or degrade gracefully?
  • Approach choice — multiple valid approaches exist; has one been decided?
  • Implicit dependencies — ordering or environment assumptions not stated?

If the scan surfaces nothing, proceed to phasing without asking questions. Do not report "scan clean" — just move on.

How to run the pass

  1. Collect plan-changing ambiguities — prefer existing [?] markers over new ones.
  2. Ask ≤5 targeted questions, highest-impact first.
  3. Where an answer to one question informs another, ask one at a time (in sequence).

Batch only mutually independent questions.

  1. Stop early once unambiguous — never force 5 questions.
  2. Record each answer and clear the matching [?] marker.
  3. Finalize and save.

## Open clarifying questions block format (subagent mode)

Append this block to your return after the plan draft:

## Open clarifying questions
1. [highest-impact question] — affects: [what part of the plan]
2. [next question, if independent of #1]

Recording format (task.md)

Add a dated ## Clarifications subsection under Research Findings before the phase table is finalized:

## Clarifications
### YYYY-MM-DD
- Q: [question] → A: [user's answer]
- Q: [deferred question] → Assumed: [assumption made], no answer given

For deferred or unanswered items, record the assumption explicitly. Never silently guess a plan-changing ambiguity — record it so the Builder and Reviewer can see it.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
79
Repository forks
11
7-day trend score
22

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/mcouthon/agents/clarify/badge)](https://verified-skill.com/skills/mcouthon/agents/clarify)

Something wrong with this skill or its page? Tell us.