Skip to content
Skills Library
Management & product · Planning

clarify-task

/clarify-task

Use this skill to resolve ambiguities, clarify vague criteria and make implicit assumptions explicit. Invoked at the end of /at:create-task and the start of /at:plan-task. Typical workflow: create-task → clarify-task → plan-task → impl-task → review-code → review-task → ship-task.

Repository
auto-task ↗
Licence
MIT
Last repository change
08.09.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 08.09.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Use this skill to resolve ambiguities, clarify vague criteria and make implicit assumptions explicit. Invoked at the end of /at:create-task and the start of /at:plan-task. Typical workflow: create-task → clarify-task → plan-task → impl-task → review-code → review-task → ship-task.

Original author description

Use this skill to resolve ambiguities, clarify vague criteria and make implicit assumptions explicit. Invoked at the end of /at:create-task and the start of /at:plan-task. Typical workflow: create-task → clarify-task → plan-task → impl-task → review-code → review-task → ship-task.

How it works

  1. Usage
  2. Goal
  3. Context
  4. Step 1: Understand the Task
  5. Step 2: Identify Issues
  6. Step 3: Surface and Clarify Issues with User
  7. Step 4: Update the Task
  8. Step 5: Verify
  9. Step 6: Mark Ready
Original SKILL.md headings · 72 lines, 609 words
SKILL.md preview
---
name: clarify-task
description: "Use this skill to resolve ambiguities, clarify vague criteria and make implicit assumptions explicit. Invoked at the end of /at:create-task and the start of /at:plan-task. Typical workflow: create-task → clarify-task → plan-task → impl-task → review-code → review-task → ship-task."
---

# Clarify Task

## Usage

`/at:clarify-task <task-path> [further user instructions]`

## Goal

Ensure the task is clear enough so that two reasonable agents - with access to the task content and repo only - would neither complete the task in a meaningfully different way nor disagree on whether the task is done.

## Context

This skill is typically run as part of a larger workflow:

```text
create-task → clarify-task → plan-task → impl-task → review-code → review-task → ship-task
```

As steps (e.g. clarify, plan, impl, review) typically run in new sessions, it's imperative that the task file plus repo state carry everything the next agent needs.

Task files live in the project's task store. Project config can override its location and other defaults: read `.claude/auto-task.config.md` (project, committed) and `.claude/auto-task.config.local.md` (personal overrides — win on conflict) if they exist. `/at:config` owns the defaults and the precedence rules.

When another skill invokes this one (`/at:create-task` Step 6, `/at:auto-task` Step 0.3), run Steps 1–2 in a fresh subagent so the task is read cold, and Steps 3 onward on the main thread: a subagent can neither ask the user (Step 3) nor spawn the Step 5 verifier.

## Step 1: Understand the Task

- Read the task and explore the relevant parts of the codebase to make sure you fully understand what the task is about and ground your questions.
- If you detect ambiguity, vagueness or implicit assumptions, do another round of deeper exploration and try to resolve.

## Step 2: Identify Issues

If after completing Step 1 you conclude that two reasonable agents - with access to the task content and repo only - would either complete the task in a meaningfully different way or disagree on whether the task is done, flag it to the user.

Triggers (non-exhaustive):

- Motivation missing - task says *what* but not *why*.
- Incomplete content - trailing-off sentences, TODOs, TBDs, "should we...?", etc.
- Acceptance criteria weak - vague, untestable, or missing boundary/edge cases (see `/at:create-task` § Acceptance criteria).
- Unclear scope - a criterion two reasonable agents would read differently.
- Semantic ambiguity - same term, field, column, etc. meaning different things (e.g. "days" = calendar or trading?).
- Implicit assumptions - things the implementer must assume that aren't stated.

## Step 3: Surface and Clarify Issues with User

If anything from the previous step needs clarification, flag it to the user using the AskUserQuestion tool - if necessary do multiple rounds.

Make sure that each feedback item:

- Has a number for reference.
- States the issue clearly and succinctly.
- Proposes a recommended answer with one-line reasoning, and names the alternative if (and only if) applicable/reasonable - to make it easy for a user to confirm or override.

If there are no substantial issues to surface or none left, reply with a short one-liner saying that the task seems clear.

## Step 4: Update the Task

Integrate the feedback from Step 3 into the task file.

When editing the task file:

- Strictly follow the `/at:create-task` skill's "Guidance" section and "Step 3: Write the task".
- Do not make any edits beyond what's strictly necessary to integrate the feedback (exception: fixing obvious typos - please do without asking).

## Step 5: Verify

Spawn a sub-agent to re-run Steps 1–2 on the updated task and report any remaining issues. If new issues surface, address them via Steps 3–4. Cap at 3 rounds.

## Step 6: Mark Ready

Finally, set the task status to `ready-for-dev` — by default, edit the frontmatter `status:` field and commit with a `(task/NNN)` subject suffix; if the project config defines a task-status command, use that instead.

Versions

RepositoryScoreLicence
This page · patforna/auto-task100MIT
tojim00d/Orbit-skills100MIT

Database snapshot: 13.11.2026 · package version ec7b6a868d12 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100plan-task
    Use to write an implementation plan for a well-defined task. Typical workflow: create-task → clarify-task → plan-task → impl-task → review-code → review-task → ship-task.
  • 100impl-task
    Use to implement a task by executing its implementation plan. Typical workflow: create-task → clarify-task → plan-task → impl-task → review-code → review-task → ship-task.
  • 90clarify
    Use when a single DAE artifact has ambiguities to resolve. Triggers — "/engineer.clarify", "clarify this spec", "resolve ambiguities", "this is vague — tighten it".
  • 100clarify
    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'.
  • 100clarify
    Use when a spec exists and must be de-risked before planning — hunt its ambiguities, unstated assumptions and edge cases, ask the few build-changing questions, bake the answers back into the spec. The rsc SDD gate between `specify` (writes the spec) and `plan` (designs the…
  • 100clarify-goal
    This skill asks questions to define a research goal. You use it when the scope, assumptions, or success criteria are unclear.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.