@easysociable/cli 0.1.2 → 0.1.4

package/content-engine/starter/topics/_template-item.md

@@ -0,0 +1,103 @@
+---
+id: T-YYYYMMDD-XX
+date: YYYY-MM-DD
+status: scored
+account: your-handle
+profile: default
+platform: x
+pillar: P1
+lane: teach
+generation_mode: demand
+source_type: inbox | user | need | product | recommendation
+purpose: produce | library | discard
+scout_label: demand | ally | foil | craft_only
+capture_id:
+need_ids:
+product_ids: none
+product_fit: none
+recommendation_ids: none
+---
+
+# 选题判断卡
+
+> 这是一条准备讨论的内容机会，不是最终发布标题。
+
+**结论：** ready | backlog | parked  
+**状态原因：** 一句话说明为什么得到这个结论  
+**适合谁：** 一句话说明具体受众和场景  
+**核心判断：** 一句话说明这条内容真正要讨论什么  
+**下一步：** 开始生成 / 补需求 / 补证据 / 修改角度 / 放弃
+**产品连接：** none | P-… · direct | adjacent · 一句话说明连接方式
+**生成路径：** demand | demand_to_offer | demand_to_review | review | offer_education | profile_thesis
+
+## 这条内容要解决什么问题？
+
+用 2–4 句话说明现实问题。不要复述标题。
+
+## 他们现在相信什么？
+
+写出受众当前的错误判断或困惑。
+
+## 我们准备讲哪一刀？
+
+说明我们的独特角度，不写完整标题，也不要把来源内容改写成我们的观点。
+
+## 为什么现在值得讲？
+
+说明发生了什么变化，以及为什么当前受众需要面对它。不是新闻摘要。
+
+## 看完后应该改变什么？
+
+用“之前 → 之后”表达用户认知或行动上的变化。
+
+## 凭什么这么判断？
+
+用人话列出 Needs、Product、Recommendation、Capture 或其他依据。
+
+## 当前缺口
+
+还缺什么需求证据、案例、用户反馈或产品事实。没有缺口就写“无”。
+
+## 建议形式
+
+平台、Lane 和推荐内容形式。暂时不写完整脚本。
+
+---
+
+## 评分与追踪附录
+
+以下内容服务于复核、机器读取和后续交接，不是主阅读面。
+
+### Score
+
+Numbers only. Do not repeat the card above in a note column.
+
+| dim | 0–10 |
+|-----|------|
+| context | |
+| audience | |
+| conflict | |
+| insight | |
+| evidence | |
+
+**opp:** · **aud:** · **verdict:**
+
+### Trace
+
+- source:
+- capture_id: (inbox `C-…` only)
+- need_ids:
+- product_ids:
+- product_fit:
+- recommendation_ids:
+- lane:
+- generation_mode:
+- raw:
+- src: likes / replies / bookmarks / views @ time
+- swipe: none | S…
+- atoms: none | …
+- claim: none | C…
+
+### Constraints
+
+Writer must-nots. Keep short. Empty is allowed.

package/{skills/easysociable-content → content-engine}/starter/topics/scoring.md

@@ -14,7 +14,9 @@ Scores whether a topic **deserves to exist as content**, not whether it can be w
 ## Pipeline (do not skip)
 
 ```text
-watchlist / inbox / url / discovery signal
+Needs / Products / Recommendations → editorial judgment
+  → user accepts
+inbox / url / need / user idea
   → 0) Hard filters
   → 1) Scout gate (purpose + label)     ← most signals die here
   → 2) Opportunity five-dim score        ← only for produce candidates
@@ -24,7 +26,23 @@ watchlist / inbox / url / discovery signal
 
 Library-only signals may skip (2)–(3) — see Scout purposes below.
 
-Watchlist scans create **Discovery** records first. Topic scoring runs only after the user explicitly promotes a Discovery (or names another explicit input).
+Topic scoring runs only after an explicit input and editorial judgment. Product or recommendation fit is context, not evidence of audience demand.
+
+Need match (`need_ids` non-empty) → default `scout_label=demand`. Do not create an `N-` from a product claim or headline.
+
+Product fit is a separate optional annotation:
+
+```text
+Needs = demand evidence
+Products = offer facts
+Topics = editorial judgment over the evidence
+```
+
+Use `product_ids` only when the Topic honestly connects to an active product
+entry. Use `product_fit=direct` when the Topic addresses a problem the product
+solves, `adjacent` when it builds context without being a pitch, and `none`
+when no product connection is needed. Product fit does not increase a score,
+replace `need_ids`, or make a Topic `ready`.
 
 ---
 
@@ -33,7 +51,6 @@ Watchlist scans create **Discovery** records first. Topic scoring runs only afte
 - Off **profile pillars** (unless user override)
 - Hits audience **Not for** (F4F, pure crypto shill, comment-gate junk as the only substance, etc.)
 - Requires invented personal metrics/experience to write honestly
-- Wrong network for the watchlist row (e.g. X tools on a `tiktok` handle)
 
 ---
 
@@ -84,6 +101,8 @@ Only required for `purpose: produce`. Optional brief notes for `library`.
 **Principle:** these five dimensions answer **"is this worth saying?"** — not "can it be written well?"  
 Presentation concerns (framework, structure, format) belong at Brief stage.
 
+Write reasons in the topic's **readable judgment layer**. The `## Score` table is numbers only — do not duplicate the card in a note column. Verdict (`ready` / `backlog` / `parked`) belongs in the decision summary, then echoed as one line under Score.
+
 | Key | Name | What to judge | Weight |
 |-----|------|---------------|--------|
 | `context` | Context | What changed? Why now? Timing, freshness, relevance to the audience's world | **15%** |
@@ -116,6 +135,15 @@ Score using these checks (note which hit):
 2. **Buyer shape** — who buys/acts matches audience buyer as defined there
 3. **Wedge land** — can honestly teach or contrast toward this account’s product/wedge without inventing claims
 
+If product fit is `direct`, load the cited product entry and verify that the
+Topic's problem and proposed CTA are inside its `Problem`, `Mechanism`, and
+`Not solving` sections. If the product is not needed, score the Topic on its
+audience and wedge without forcing a mention.
+
+**Need-source exception:** when `source_type=need` **and** `need_ids` is non-empty, matching **at least one need gloss** counts as one strong audience check. Do **not** require a full ICP (`audience.md` / `pillars.md` may still be hypothesis). Non-need sources do not get this exception. `ready` is still `opp_score ≥ 7.5` **and** `audience ≥ 6`.
+
+Needs default `scout_label=demand`. Still pass hard filters. `frequency ≥ 3` may strengthen context `why_now`; do **not** fold it into `src_*`.
+
 | Range | Guide |
 |-------|-------|
 | 8–10 | ≥2 checks strong; clear buyer + pain |
@@ -131,7 +159,7 @@ Score using these checks (note which hit):
 | 5–7 | Some tension but the gap is soft or already widely acknowledged |
 | 0–4 | No real conflict; topic is an observation or list with nothing to challenge |
 
-When scoring, the agent must write the `current_belief` and `belief_gap` on the topic item — not just a score. If you can't articulate what the audience currently believes wrong, the conflict score cannot be above 5.
+When scoring, write the false belief and the gap once under 「他们现在相信什么」 — not just a score, and not a second time in the Score table. If you can't articulate what the audience currently believes wrong, the conflict score cannot be above 5.
 
 **Insight (25%)**
 
@@ -149,6 +177,29 @@ When scoring, the agent must write the `current_belief` and `belief_gap` on the
 | 5–7 | Evidence exists but generic or secondhand |
 | 0–4 | No evidence beyond assertion; "experts say" with no expert named |
 
+A verbatim need quote is `observation` evidence. List the quote (or a paraphrase **and** the `N-` id) under `## Evidence.available`. Without an `N-` / `C-` / user-lived experience, evidence cannot be above 5. Mechanism / lived experience is still required to reach 8–10.
+
+Product documentation is evidence of what the product does, not evidence that
+the audience wants it. Do not use a product entry to manufacture a Need or to
+raise the audience score.
+
+### Generation-mode gates
+
+Before scoring, set the smallest honest `generation_mode`:
+
+| mode | Required |
+|------|----------|
+| `demand` | `need_ids` + Profile |
+| `demand_to_offer` | `need_ids` + `product_ids` + Profile |
+| `demand_to_review` | `need_ids` + `recommendation_ids` + Profile |
+| `review` | `recommendation_ids` + named evidence + Profile |
+| `offer_education` | `product_ids` + product mechanism + Profile |
+| `profile_thesis` | Profile + Pillar |
+
+Do not use `review` when the only evidence is vendor marketing. Review entries
+must state limitations, research date, and commercial disclosure where
+relevant. Product-only and recommendation-only inputs do not imply demand.
+
 When `evidence < 5`, agent should flag an **evidence gap** on the topic item and may suggest **research** before finalizing the score. Topics can be re-scored after research fills the gap.
 
 ---