Clarify logo

Clarify

Community
mcouthon
clarify

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'.

Overview

Publishermcouthon
Repositoryagents
Skill nameclarify
Stars
79
Forks
11
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by mcouthon on GitHub. Read the source before you install it.

Installation

Install the Clarify AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/mcouthon/agents.git /tmp/agents
mkdir -p .claude/skills
cp -r /tmp/agents/generated/claude/skills/clarify .claude/skills/clarify
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Clarify in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Clarify on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Clarify is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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.
  4. Stop early once unambiguous — never force 5 questions.
  5. Record each answer and clear the matching [?] marker.
  6. 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.

Frequently asked questions

What does the Clarify AI skill do?

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'.

Why use Clarify on TypingMind?

Because you install it once and use it with any model. Clarify is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Clarify in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mcouthon/agents/tree/main/generated/claude/skills/clarify. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Clarify?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Clarify?

As many as you like. As long as a model supports skills, you can use Clarify with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Clarify AI skill free?

Yes. It is published on GitHub by mcouthon under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇