Skip to content
Agent Orchestration
Skill

/clarify

Use when a single DAE artifact has ambiguities to resolve. Triggers — "/engineer.clarify", "clarify this spec", "resolve ambiguities", "this is vague — tighten it".

BOOST
From plugin
atdd
15928 skills8 agents4 commands2 hooks
Install
$ npx -y skills add swingerman/engineer --skill clarify --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/clarify

Context preview

The summary Claude sees to decide when to auto-load this skill.

Use when a single DAE artifact has ambiguities to resolve. Triggers — "/engineer.clarify", "clarify this spec", "resolve ambiguities", "this is vague — tighten it".

SKILL.md

clarify.SKILL.md
name: clarify
description: Use when a single DAE artifact has ambiguities to resolve. Triggers — "/engineer.clarify", "clarify this spec", "resolve ambiguities", "this is vague — tighten it".

clarify

Resolve ambiguities in **one** DAE artifact through an iterative interview. A cross-cutting quality gate — runs on any artifact at any pipeline stage.

The clarify *pattern* is also embedded inside artifact-producing skills for their own in-flight ambiguities; this standalone skill is for ad-hoc cleanup after the fact.

When to use

On any one of: `feature.md`, `acs.md`, `spec.md`, `plan.md`, `CHARTER.md`. Invoked as `/engineer.clarify <slug> <artifact>` or `/engineer.clarify <path>`.

**Not for:** cross-artifact contradictions (`consistency-check`); changing what a feature does (`feature-edit`); resolutions that cascade across files (clarify the source here, then `feature-edit`).

Workflow

1. **Resolve + load** — resolve the methodology root + manifest via `${CLAUDE_PLUGIN_ROOT}/scripts/dae_resolve.py` (see `references/resolving.md`); locate the target artifact. Also load its parent contract for grounding (`feature.md` for acs/spec/plan; `CHARTER.md` for feature.md). 2. **Identify ambiguities** — within this one artifact: language interpretable two ways, underspecified requirements, undefined domain terms, unclear scope boundaries, internal contradictions. Cross-*artifact* contradictions are out of scope (→ `consistency-check`). If none found, say so and stop. 3. **Resolve one at a time** — per ambiguity, quote the ambiguous line and ask one question — multiple-choice (AskUserQuestion) when bounded, open-ended otherwise. Iterate until resolved or the user stops. 4. **Edit in place** — encode each resolution into the target artifact; show old→new, confirm before writing. Edit **only** the target artifact. 5. **Flag downstream staleness** — do NOT cascade. Identify downstream artifacts a resolution may have invalidated; list them in the handoff; recommend `feature-edit` (which owns cascade). 6. **Handoff** — emit a summary.

Handoff

Emit per `${CLAUDE_PLUGIN_ROOT}/references/handoff-summary.md`. `checkpoint: null`. If downstream staleness flagged: `human_action_needed: yes`, `recommended_next`: "/engineer.feature-edit to propagate".

References

  • [Foundation Design](https://www.notion.so/3585ecdee0e2811bbc67ff4913c03207) — artifact schemas
  • The DAE methodology page — clarify as embedded pattern + standalone skill
Read more
Ships withatdd

A methodology kit for engineering-led AI development — spec-driven, test-driven, charter-bound. ATDD + mutation testing + deterministic guardrails. AI agents do the typing. Engineers stay in charge of architecture, behavior contracts, and verification.

Get the whole plugin

Other skills on atdd.