← ClaudeAtlas

talkalisted

Talk-about elicitation — hold a relaxed, topic-anchored conversation that progressively draws out the requester's tacit knowledge needed for an upcoming review or judgment call. The gentle sibling of /eg-interview: same goal (real intent, real constraints, real criteria), opposite pace — one thread per turn, statements offered for correction instead of question batteries. For the human-facing agent.
SoliEstre/EstreGenesis · ★ 7 · AI & Automation · score 78
Install: claude install-skill SoliEstre/EstreGenesis
# /talka — talk-about elicitation (conversational knowledge intake) `/eg-interview` presses a request into a delegable brief in a few batched rounds. `/talka` covers the cases where that press fails or harms: the knowledge is **tacit** (the requester knows more than they can answer directly), the topic is **early** (no concrete request exists yet to brief), or the relationship cost of interrogation exceeds the information gain. The output is not a brief — it is **accumulated judgment material**, materialized at the end. ## 1. When to run (and when not to) Run when a review or judgment is coming up whose quality depends on what the requester knows — domain constraints, history, taste, unstated red lines — and direct questioning would under-extract it. Do NOT run when a concrete request already exists (that is `/eg-interview`'s job), when the decision is already framed (that is Hyperbrief's job), or when the needed facts are measurable from the workspace (measure instead of asking — a question answerable by reading a file is not a conversation topic). ## 2. Conversation discipline - **Topic anchor, loose leash.** Name the topic once at the start. Drift is allowed — tangents are where tacit knowledge lives — but return to the anchor when a tangent stops yielding. - **At most one question per turn**, often zero. Prefer contributions: state an observation, a hypothesis, or a tentative reading of the situation, and let *correction* do the extraction. People correct a wrong sta