Skip to content
Agent Orchestration
Skill

/hoyeon-clarify

Hoyeon ambiguity-resolution interview for Codex. Use when the user invokes "$hoyeon-clarify", "/clarify", asks to keep asking until clear, remove ambiguity, clarify requirements/design/domain/plan, or says Korean phrases like "모호한 게 없게", "명확해질 때까지", "질문 계속해", or "Q&A로 정리".

BOOST
@team-attentionteam-attention@team-attention
From plugin
hoyeon
17337 skills29 agents7 hooks
Install
$ npx -y skills add team-attention/hoyeon --skill hoyeon-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/hoyeon-clarify

Context preview

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

Hoyeon ambiguity-resolution interview for Codex. Use when the user invokes "$hoyeon-clarify", "/clarify", asks to keep asking until clear, remove ambiguity, clarify requirements/design/domain/plan, or says Korean phrases like "모호한 게 없게", "명확해질 때까지", "질문 계속해", or "Q&A로 정리".

SKILL.md

hoyeon-clarify.SKILL.md
name: hoyeon-clarify
description: |
  Hoyeon ambiguity-resolution interview for Codex. Use when the user invokes
  "$hoyeon-clarify", "/clarify", asks to keep asking until clear, remove
  ambiguity, clarify requirements/design/domain/plan, or says Korean phrases
  like "모호한 게 없게", "명확해질 때까지", "질문 계속해", or "Q&A로 정리".

hoyeon-clarify

This is the Codex-facing wrapper for Hoyeon's canonical `clarify` skill.

Canonical skill:

  • Installed root: `__HOYEON_PLUGIN_ROOT__/skills/clarify/SKILL.md`
  • Repo-local fallback: `skills/clarify/SKILL.md` from the current Hoyeon repo

When this skill is invoked:

1. Read the canonical skill file above before executing the workflow. 2. Follow the one-question-at-a-time ambiguity-resolution loop. 3. Write Q&A state under `.hoyeon/clarify/<topic-slug>/`. 4. Use `hoyeon-clarity-auditor` at audit boundaries when native adapters are loaded. If unavailable, do a compact direct audit and record the fallback. 5. Use `hoyeon-code-explorer` when code/docs can answer a question better than the user can. 6. Do not implement, write final `requirements.md`, mutate `plan.json`, or create ADRs unless the user explicitly asks for that handoff.

The output contract remains the canonical Hoyeon contract: `.hoyeon/clarify/<topic-slug>/qa-log.md` and, when sufficient, `.hoyeon/clarify/<topic-slug>/clarity-summary.md`.

Read it on GitHub ↗
Ships withhoyeon

All you need is requirements. A Claude Code plugin that derives requirements from your intent, verifies every derivation, and delivers traced code — without you writing a plan. AI can build anything. The hard part is knowing what to build — precisely.

Get the whole plugin
Stats
JavaScriptCSSBashRubyGit
+6 tags
GitHubMarkdownAnthropicOpenAIGeminiMCP
173
Stars
23
Forks
Maintained
Maintenance
Shell
Language
MIT
License
5mo ago
Last commit
9mo ago
Created
4h ago
Added

Repo: team-attention/hoyeon

In this plugin
37 skills29 agents7 hooks
See everything inside

Other skills on hoyeon.

See all 37 skills in hoyeon