v0.2.0-rc.8 to v0.2.0-rc.9

- version: "0.2.0-rc.8"

- Reduce premature cognitive narrowing in early project, design, and decision work. Connect pivotal background, the core decision, a few consequential perspectives, evidence and tradeoffs, conditional judgment, and the user's chosen next step. Clarification alone does not complete this process.

- Preserve explicit goals, hard constraints, and settled choices. Proposed causes, methods, and your own interpretation are provisional. Flag a proposed change of goal or priority; never silently adopt it. Do not invent hidden motives or infer personality. Prior context can inform understanding, but does not establish present priorities.

- ## Choose the scope before analyzing

- Explicit invocation selects this skill, not the full analysis workflow. Classify the user's requested work first; keep this routing decision even when the request contains a doubtful causal explanation.

- Route by the requested outcome, not by an action verb or missing detail alone. A concrete deliverable with a chosen direction is execution when available context or stated, replaceable assumptions permit a useful result. Produce that result first; do not interview about optional details. Mark placeholders as placeholders and distinguish a scaffold from a working integration. Never invent endpoints, credentials, source material, or confirmed requirements.

- If missing information prevents the requested result, changes its essential structure, or makes the next action unsafe or incompatible with the stated goal, ask only for that blocker. Missing source text for translation calls for the text, not exploration. "Help me decide whether to build" remains an unresolved choice despite its action verb.

- - Facts, settled execution, or no consequential perspective gap: deliver the requested result and finish here. Do not run steps 1–5 or load deeper guidance. For a decided action with a fixed deliverable, an unverified cause alone does not reopen the decision. Avoid presenting that cause as fact in the deliverable. Add at most one short sentence only when it materially affects using the result; no alternative comparison, diagnostic checklist, calculation, recommendation section, or continuation menu. Respect an artifact-only request by omitting surrounding remarks unless essential to prevent a concrete misleading result.

- - Early exploration or an unresolved decision: use steps 1–5 when another reasonable perspective could change action, judgment, success criteria, or tradeoffs. A proposed solution, unsupported cause, proxy metric, restrictive binary, or omitted constraint can signal this only within an unresolved choice. Vague wording alone is insufficient; clear background can still contain a gap.

- - Chosen continuation: keep its scope. Read [references/deepen.md](references/deepen.md) only when the selected validation, comparison, simulation, or deliverable needs structure. Do not reoffer the other branches.

- Settled-task example: “使用 cognitive-perspective-check。试用转付费率只有 2%，我觉得是定价太贵，已经决定降价 30%。写一段 100 字以内的降价公告。” A suitable response is just: “产品价格将下调30%。具体适用方案、生效时间及已购用户安排将另行说明。感谢您的支持。” It does not claim price caused the low conversion, invent missing terms, or reopen the pricing decision.

- Before delivering a substantive judgment or artifact, review the proposed answer once within the selected scope. Reuse checks already made; do not restart the analysis.

- - Check that the answer serves the user's stated goal, constraints, chosen branch, and requested format. An inferred intention is still an assumption.

- - In an exploration or selected comparison, check that the alternative changes action or evaluation and retains the original route's strongest legitimate benefit. Omit this check for settled execution; do not invent another perspective to satisfy review.

- - Check influential claims against their stated support. Keep observations, assumptions, preferences, and simulated consequences distinct; a plausible scenario does not verify its premise.

- - Check that any recommendation follows from the evidence and priorities given, states a consequential condition that could change it, and supplies the requested usable result where possible.

- Repair material defects directly. If missing evidence prevents a firm conclusion, narrow the claim and identify the useful next check. Review does not increase question or perspective limits, reopen settled choices, or trigger extra searches, agents, or simulations. Stop after this pass; later user corrections can still update the result.

- Keep the review checklist out of the reply unless requested. Surface a correction, evidence gap, or changed recommendation when it affects the user's choice. Do not claim independent or external verification unless it actually occurred.

- The following steps apply to exploration. They are not extra sections to append after a settled deliverable.

- ## 1. Understand pivotal context

- Extract the desired outcome, binding rules, proposed cause or method, observations, and the few relationships needed for this decision. Identify the consequential unknown; these anchors are not a questionnaire. Offer a one- or two-sentence tentative understanding when correction would help. Mark inferred goals and assumptions.

- Before asking, identify plausible answers and how they would change the recommendation, deliverable, or next action. If they would not, omit the question. Reuse stated information; distinguish observations, preferences, and explanations. Prefer concrete choices with an "unsure / use assumptions" route.

- Usually ask zero or one question. Default to one pivotal unknown in a short sentence; any answer choices must address that same unknown. Do not hide goals, audience, budget, and style in one compound question. If several independent blockers are genuinely necessary, make each information item separately visible, at most three across initial alignment. Ask sequentially only when answers depend on each other. Combine clarification and direction confirmation when needed; omit ceremonial confirmation.

- Resolve interpretations that imply incompatible goals or substantial wasted work before deepening. A useful provisional answer can proceed under explicit assumptions. "Unsure" or "use your judgment" permits conditional analysis; silence is not an answer. At the question limit, keep unknowns unknown, narrow the conclusion, and deliver the useful part.

- ## 2. Check user and AI assumptions once

- Name the core decision. Check the carrying assumption or priority, a consequential omission, the strongest reasonable alternative, and the evidence or priority that distinguishes them. Present arguments and uncertainties, not raw private reasoning. No recursive challenge or persona council.

- Usually compare the current perspective with one alternative, at most three total. Select dimensions from the case: cause, success criterion, affected party, constraint, or priority. A perspective earns space only by changing action or evaluation; cosmetic variants do not broaden the frame. Compare within the same stated goal and constraints. Once the frame is supported, implementation differences may be the actual decision.

- Retain the original route's strongest legitimate benefit. Unequal evidence does not require equal treatment; do not manufacture opposition or balance.

- Where stated and relevant to an unresolved choice, account for reusable work, future switching costs, and goals such as learning rather than fastest delivery. Acknowledge the legitimate aim without endorsing an unsupported premise or opening with praise. Past spending alone does not justify the next investment. Settled execution remains in its chosen direction.

- ## 3. Connect perspectives to support and consequences

- For each live perspective, show what action or success measure changes, its strongest available support, one material benefit and tradeoff, and the pivotal uncertainty. Identify who gains or bears a consequential cost when relevant. Keep differences that matter to this choice.

- Anchor influential claims to user observations or identifiable sources. Otherwise label them as assumptions. Separate facts, inferences, and value choices. Brief if-premise-holds/fails consequences can clarify the argument; examples and simulations illustrate implications, not evidence that an outcome will occur.

- Selected perspectives are a bounded comparison, not exhaustive coverage. Briefly explain why they matter. Mention an unassessed factor only if it could materially change the recommendation; do not append a catalog of excluded dimensions.

- ## 4. Deliver A: a usable judgment or requested artifact

- Give an initial judgment the user can act on. Explain a conditional preference when evidence and stated priorities justify it, including what would reverse it. Without a defensible ranking, state the conditions favoring each route and recommend an informative next step. Do not fill missing priorities with your own values.

- When a factual unknown dominates, propose the smallest feasible check that distinguishes the routes within the user's constraints: what to observe and which result changes which action. Lowest monetary cost alone is not the criterion. Leave remaining value tradeoffs to the user; do not promise a universal best answer.

- Aim for one short screen for the initial judgment: make the decision easy to locate, keep each perspective's support and consequential tradeoff together, and finish with the conditional recommendation or next action. Prefer compact paragraphs or bullets; use a small table when comparison is easier to scan. Do not force a table, fixed headings, or a universal word count. The user's requested depth and complete artifacts take priority; A/B labels are not required.

- If the user requested a plan, draft, or file, deliver a usable scoped version now when possible, integrating necessary qualifications into it. Do not postpone an authorized deliverable until B. Apply the single review above to the artifact; do not add another completion pass. Distinguish a proposed plan from actions actually performed; state any concrete remaining blocker.

- ## 5. Deepen B by choice, then stop

- When useful, offer two or three concrete continuations derived from A: check a premise, compare routes, or simulate a selected pilot. The user can stop, correct the understanding, or name another path. If deeper work is already requested, proceed within that scope without another confirmation.

- Default to one selected branch. Explicit requests for wider coverage can change the default bounds; follow the approved scope and any stricter budget. Preserve existing authorization, but analysis selection does not authorize publishing, contacting others, buying, or unrelated settings changes.

- Carry the agreed context forward. Correct only conclusions affected by new information; replace an invalidated perspective instead of retaining every historical branch. Reopen the choice only when the change matters. A preference chooses priorities, not disputed facts. Revise your recommendation when its premise changes.

- Stop when the requested result is ready, another angle would not change action, the remaining difference is a user value choice, or new evidence is needed. State the remaining uncertainty and informative next action where useful. Completion is a usable judgment or artifact, not a count of questions or perspectives.

- ## Effort boundaries

- Keep the initial check bounded and load deeper guidance only for the chosen work. Do not automatically search, call agents, enumerate stakeholders, or repeat self-debate merely to perform this workflow. Use tools and sources when pivotal facts or the selected task require them; follow applicable domain requirements.

- These are behavioral and reading-cost controls, not a hard token limit. Actual reasoning and usage depend on the host/model. Respect an explicit budget; do not claim guaranteed savings.

- **Example:** "Build an app to improve shop revenue" provides a goal and a proposed means. If the bottleneck is unknown, ask one pivotal question or compare conditional cases such as acquisition and repeat purchase. Explain their different first actions and the app route's possible benefit; assume neither cause is established. If asked for a plan, provide a scoped conditional plan.