From soloflow
Runs a conversational clarification loop when a raw idea is ambiguous, using a checklist, scope-decomposition gate, and one-question-at-a-time probing before structured extraction or planning.
How this skill is triggered — by the user, by Claude, or both
Slash command
/soloflow:clarify-ideaThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill encodes a short conversational clarification loop to run **before** structured idea extraction or task refinement, when the raw input is too ambiguous to extract cleanly. It is **instructional** — the calling agent drives the loop using its own `AskUserQuestion` tool. This skill does not spawn subagents.
This skill encodes a short conversational clarification loop to run before structured idea extraction or task refinement, when the raw input is too ambiguous to extract cleanly. It is instructional — the calling agent drives the loop using its own AskUserQuestion tool. This skill does not spawn subagents.
Apply this checklist to the raw input. If any item is missing or unclear, invoke the loop:
If all five are present, skip this skill and proceed directly to extraction. Running the loop on an already-clear input is a cost, not a benefit.
Opt-out signals the caller must honor:
--skip-clarify anywhere in the argumentsconfig.phases.clarify === false in .soloflow/config.json or config/defaults.yaml"This is too simple to need clarification."
The ambiguity checklist is the judge, not your intuition. Cheap to run, cheap to skip. Do not debate whether to invoke — apply the checklist.
If the input spans multiple independent subsystems or deliverables (e.g., "redesign onboarding AND add a notifications center AND refactor the API client"), stop immediately. Do NOT begin clarification on the whole thing.
Use AskUserQuestion:
Clarify only the selected piece. The others can be captured as separate ideas later.
Rules (hard):
AskUserQuestion at a time. Never batch clarification questions. Each answer informs the next question.Grep / Glob (or a single WebSearch for unfamiliar domain terms) is fine to frame better candidate answers. Never use research as a substitute for asking the user.Keep going until the checklist at the top of this file is satisfied — every item has a clear answer.
Once you believe the checklist is satisfied, present an explicit confirmation via AskUserQuestion:
You MUST NOT proceed to extraction until "Extract now" is selected. This is a hard gate — the anti-pattern is declaring readiness yourself and skipping the user confirmation.
If the user picks "Keep clarifying," return to the clarification loop. There is no retry limit; loop until the user confirms.
When the gate passes, produce a clarified brief in this exact shape and hand it to the caller:
## Raw Input
{Verbatim $ARGUMENTS the user passed in}
## Clarification Transcript
- Q: {question 1}
A: {user answer 1}
- Q: {question 2}
A: {user answer 2}
{...}
## Synthesis
{One concise paragraph restating the now-clarified ask, incorporating every
answer above. This is the canonical interpretation the downstream
idea-extractor should treat as the ask.}
The synthesis paragraph is canonical. The raw input and transcript are context only.
This skill is designed to be invoked by any command that accepts a free-form user ask and needs to disambiguate before structuring — currently /soloflow:idea-extractor, and reusable by /soloflow:quick for ambiguous bug reports.
npx claudepluginhub kesteva/soloflow --plugin soloflow-devClarifies ambiguous requests using 5W1H decomposition and ambiguity scoring, generating up to 3 structured clarifying questions before execution.
Analyzes ambiguous task requests using 5W1H decomposition to surface assumptions and generate up to 3 targeted clarifying questions before execution.
Clarifies vague user requests via iterative Q&A loop and parallel subagent codebase exploration. Outputs scoped context brief for precise planning. Triggers on 'I want to...' or ambiguous scopes.