@easysociable/cli 0.1.3 → 0.1.5

package/README.md

@@ -13,22 +13,22 @@ Requires Node.js 20+. Content Engine workbench also needs `python3`.
 ## Quick start
 
 ```bash
-# Visual skills + MCP for Codex / Claude Code
+# Default skills + MCP for Codex / Claude Code (template + slideshow)
 easysociable install --yes
-
-# Local content engine (markdown + workbench) — no Agent host required
-easysociable engine init --root /workspace --yes
-easysociable engine serve --engine /workspace/Content Engine --no-open
 ```
 
-Then tell the Agent to follow `Content Engine/CLAUDE.md`.
-
-Optional pointer skill for hosts that discover work via SKILL.md:
+Default install does **not** include `easysociable-content`. Add it when you want the Content Engine pointer skill:
 
 ```bash
 easysociable install --skills content,template,slideshow --yes
+easysociable engine init --root /workspace --yes
+easysociable engine serve --engine /workspace/Content Engine --no-open
 ```
 
+Then tell the Agent to follow `Content Engine/CLAUDE.md`. The starter includes
+separate `products/` (owned offers) and `recommendations/` (third-party review
+subjects) libraries; neither is a substitute for `needs/`.
+
 Lazy-auth guidance lives in the package at `skills/ONBOARDING.md`.
 
 ## Content Engine
@@ -36,12 +36,15 @@ Lazy-auth guidance lives in the package at `skills/ONBOARDING.md`.
 | Command | Purpose |
 |---------|---------|
 | `easysociable engine init [--root] [--yes] [--serve]` | Scaffold starter (never overwrites) |
-| `easysociable engine serve [--engine] [--no-open]` | Build + start workbench on `:8765` |
-| `easysociable engine build [--engine]` | Rebuild `workbench/index.html` |
+| `easysociable engine serve [--engine] [--no-open]` | Sync workbench runtime from CLI, rebuild, start on `:8765` |
+| `easysociable engine build [--engine]` | Sync workbench runtime from CLI, then rebuild `workbench/index.html` |
 | `easysociable engine detect` | Find engines under search roots |
 | `easysociable engine validate --root …` | Starter completeness |
 | `easysociable engine validate --run …` | Run / pack checks before render |
 
+The Workbench exposes Products and Recommendations as separate read-only
+indexes. Topics can cite either one without forcing a product connection.
+
 Default `--root` / `--engine` parent is `/workspace` when that directory exists, otherwise the current working directory.
 
 ## Authentication

package/content-engine/scripts/starter.mjs

@@ -11,7 +11,9 @@ export const ENGINE_PATHS = {
   runs: 'runs',
   exports: 'exports',
   topics: 'topics',
-  discovery: 'discovery',
+  needs: 'needs',
+  products: 'products',
+  recommendations: 'recommendations',
   swipe: 'swipe',
   profiles: 'profiles',
   inbox: 'inbox',

package/content-engine/scripts/workbench.mjs

@@ -30,21 +30,26 @@ export function portInUse(port = WORKBENCH_PORT) {
   })
 }
 
-export function ensureWorkbench(engine) {
+/** `update: false` = init (missing only). `update: true` = build/serve refresh from package. */
+export function ensureWorkbench(engine, { update = false } = {}) {
   const destDir = join(engine, 'workbench')
   mkdirSync(destDir, { recursive: true })
   const copied = []
+  const updated = []
   const skipped = []
   for (const name of WORKBENCH_FILES) {
     const dest = join(destDir, name)
-    if (existsSync(dest)) {
+    const from = join(WORKBENCH_SRC, name)
+    if (existsSync(dest) && !update) {
       skipped.push(name)
       continue
     }
-    copyFileSync(join(WORKBENCH_SRC, name), dest)
-    copied.push(name)
+    const existed = existsSync(dest)
+    copyFileSync(from, dest)
+    if (existed) updated.push(name)
+    else copied.push(name)
   }
-  return { destDir, copied, skipped }
+  return { destDir, copied, updated, skipped }
 }
 
 export function buildWorkbench(engine) {
@@ -68,7 +73,7 @@ export async function startWorkbench(engine, { noOpen = false } = {}) {
   if (!python) {
     return { ok: false, code: 'PYTHON3_REQUIRED', message: 'python3 is required for the workbench. Install Python 3 and retry.' }
   }
-  ensureWorkbench(engine)
+  ensureWorkbench(engine, { update: true })
   const built = buildWorkbench(engine)
   if (!built.ok) return built
   const url = WORKBENCH_URL
@@ -112,9 +117,9 @@ async function main() {
   if (!options.engine) throw new Error('--engine is required')
   const engine = resolve(options.engine)
   if (options.command === 'build') {
-    ensureWorkbench(engine)
+    const workbench = ensureWorkbench(engine, { update: true })
     const built = buildWorkbench(engine)
-    output(built, options.json)
+    output({ workbench, ...built }, options.json)
     if (!built.ok) process.exitCode = 2
     return
   }

package/content-engine/starter/CLAUDE.md

@@ -9,7 +9,6 @@ This folder is the local **Content Engine** for EasySociable.
 
 - Folder tree: **English** (`Content Engine/`). Do not ask language.
 - Default **account:** first **active** handle in `accounts/_index.md` (starter: `your-handle` — replace it)
-- Default **platform:** `x` (watchlist / catalog filter when unset)  
 - **开一单:** do **not** silent-default platform — **ask**; multi-select → **N runs**  
 - Do not invent metrics, customers, or quotes the user did not provide
 
@@ -18,10 +17,17 @@ This folder is the local **Content Engine** for EasySociable.
 1. Read **`accounts/_index.md`** for the handle (default: first active row)  
 2. Get `profile_id`, `voice`, `platforms`, `default_platform`, `overrides`  
 3. Load **`profiles/<profile_id>/pillars.md`** + **`audience.md`** (core + current platform section)  
-4. Voice: if account `voice` is `profile` or empty → **`profiles/<profile_id>/voice.md`** (includes **Identity** + tone); else load the explicit path. Never invent bio facts not in Identity.  
+4. Voice: if account `voice` is `profile` or empty → **`profiles/<profile_id>/voice.md`** (Identity + **Experience** + **Values** + Persona); else load the explicit path. Never invent bio facts not in Identity / Experience.  
+   `boundaries.md`: missing → **hard-gate fail**. Write empty starter (`## Not covering` / `## Never claim` headings), then interview; **never invent boundaries**.  
+   `stories.md` / `expression.md`: missing → `profile: partial`, continue.  
+   Do not invent bio / stories / values absent from those files. Topics listed in `boundaries.md` → stop; do not write.  
 5. If `overrides` is **non-empty**, read that path (e.g. `accounts/overrides/<handle>.md`) and apply last  
 6. Craft: **always** load `platforms/<platform>.md` for the active platform (see `platforms/README.md` for id → file; `instagram` → `ig.md`). Missing file → stop and tell the user; do not invent craft rules.  
 7. Catalog filter: swipe/atoms/claims where `platforms` matches **and** (`profiles` is `*` **or** contains `profile_id`)
+8. If a Topic or draft mentions an offer, load `products/_index.md` and the
+   cited `products/entries/P-*.md`. Never invent product pricing, entitlements,
+   proof, or outcomes. Product fit is optional; educational content may have no
+   product.
 
 ## File map
 
@@ -31,21 +37,26 @@ This folder is the local **Content Engine** for EasySociable.
 | `profiles/_index.md` | Profile registry |
 | `profiles/<id>/pillars.md` | Topic pillars (what to talk about) |
 | `profiles/<id>/audience.md` | Readers + platform emphasis |
-| `profiles/<id>/voice.md` | Identity + tone |
+| `profiles/<id>/voice.md` | Identity + Experience + Values + Persona |
+| `profiles/<id>/stories.md` | Story inventory (cite or none) |
+| `profiles/<id>/boundaries.md` | Creator must-avoid (Not covering / Never claim) |
+| `profiles/<id>/expression.md` | Expression likes / dislikes |
+| `profiles/<id>/lanes.md` | Publishing lanes; distinct from pillars |
 | `accounts/_index.md` | handle → profile, platforms, voice, overrides |
 | `accounts/overrides/<handle>.md` | Optional account deltas |
 | `platforms/*.md` | Platform craft only |
 | `inbox/_index.md` | Capture registry |
 | `inbox/entries/C-*.md` | Per-capture working notes |
+| `needs/_index.md` | Audience-quote registry |
+| `needs/entries/N-*.md` | Per-need quote + sightings |
+| `products/_index.md` | Owned product registry and lifecycle |
+| `products/entries/P-*.md` | Owned product facts, boundaries, pricing and claims |
+| `recommendations/_index.md` | Third-party tool/product registry and Profile associations |
+| `recommendations/R-*.md` | Review subject facts, evidence and disclosure |
 | `raw/_index.md` | Authoritative source registry |
 | `raw/*.md` | Source bodies |
 | `topics/_index.md` | Topic queue (one row per topic + `item` + src engagement) |
-| `topics/items/T-*.md` | Content Opportunity (structured fields + scores) |
-| `topics/WATCHLIST.md` | Watchlist router (per-profile files) |
-| `discovery/_index.md` | Analyzed watchlist signals and promotion status |
-| `discovery/D-*.md` | Readable Source Digest, source limits, and workflow state |
-| `topics/watchlists/<profile_id>.md` | Profile-scoped radar handles |
-| `topics/watchlists/_shared.md` | Shared radar (`*`, all profiles) |
+| `topics/items/T-*.md` | Opportunity card (human half) + Score/Trace appendix |
 | `topics/scoring.md` | Scout gate + opportunity five-dim (context/audience/conflict/insight/evidence) |
 | `swipe/_index.md` | Structures (+ `profiles` column) |
 | `wiki/atoms/_index.md` | Atoms (+ `profiles`) |
@@ -60,22 +71,23 @@ This folder is the local **Content Engine** for EasySociable.
 | User intent | Action |
 |-------------|--------|
 | capture / 记一下 (+ link) | **§ Capture** only — **not** topics by default |
-| 加 watchlist / 更新 WATCHLIST | Edit `topics/watchlists/<profile>.md` or `_shared.md` (**ask profile** if unset; set **`platform`**) |
-| 按 watchlist 选题 / 扫 list 选题 | **§ Discovery** — **ask profile if unset**; filter **`platform`** (default `x`); analyze signals before promoting Topics |
-| 扫 TikTok/LinkedIn/… watchlist | Same; only rows where `platform` matches (after profile resolve) |
+| 记需求 / 用户原话 / 评论导出 | **§ Needs** only |
+| **扫需求选题** | **§ Topics** from `needs/` where `status=captured`; max 5 `produce` |
 | 扫 inbox 选题 | **§ Topics** — from captures without topic yet (max 5) |
-| 扫 watchlist / 发现内容 | **§ Discovery** — create Discovery records; do not create Topics directly |
-| 生成 topic (no source specified) | **§ Topics** — ask for the input/source; never choose an existing Discovery silently |
+| 生成 topic (no source specified) | **§ Topics** — offer captured needs or ask which explicit input to use |
 | 链接直接选题 / 把 C-xxx 做成选题 | **§ Topics** — create T- (may link capture) |
-| 开一单 / 用 T-xxx 开一单 | **§ Open a run** — **ask platform(s)** if unset; multi-select → **N runs** (bind `topic_id` if from T-) |
+| 采访我 / 完善人设 / interview me / who am I as a creator / 建立 profile | **§ Interview** — persist after each dimension; no slideshow |
+| 开一单 / 用 T-xxx 开一单 | **Hard gate first**, then **§ Open a run** — **ask platform(s)** if unset; multi-select → **N runs** (bind `topic_id` if from T-) |
 | Quick draft | Resolve profile; selection; draft in chat |
 | 收成 swipe/atom/claim | **§ Library ingest** after approval |
 | 选题后同意进 inbox | Capture that URL/C-link then optional library offer |
 | Post URL after ship | feedback + **§ Published index** |
 | 复盘 / 批准晋级 | Claims promote + published index |
 | Update pillars/audience | Edit **`profiles/<id>/…`** |
+| 更新产品 / 产品库 | Edit **`products/`**; keep dates and source of truth |
+| 推荐 / 评测第三方产品 | Edit **`recommendations/`**; record evidence and disclosure |
 | Update account binding | Edit **`accounts/_index.md`** |
-| 出图 | **§ PagePack + render** |
+| 出图 | **Hard gate first**, then **§ PagePack + render**. Fail → list missing files; no handoff unless user says **强制继续** / **force continue** |
 
 ---
 
@@ -171,72 +183,91 @@ Optional: if user also says「同时选题/打分」, run **§ Topics** for this
 
 ---
 
-## § Discovery (watchlist signal analysis)
+---
+
+## § Products (offer facts)
+
+### When
 
-**Role:** Understand external signals faithfully before deciding whether they become our content opportunities. Discovery is not a Topic queue and does not generate publish-ready copy.
+User defines, updates, prices, retires, or asks about a product or offer.
 
-### Flow
+### Role
+
+Products are the **supply-side fact layer**. They are not audience needs,
+external discoveries, or content opportunities.
 
 ```text
-watchlist signal → Discovery → Topic (only when explicitly promoted) → Brief
+Need (demand evidence) + Profile (identity) + optional Product (offer facts)
+  → Topic (editorial judgment)
+  → Run
 ```
 
-### Discovery rules
+### Rules
 
-1. Create one `D-YYYYMMDD-XX` record for each meaningful watchlist signal; discard noise before analysis.
-2. Write `## Source Digest` as a short, natural-language note:
-   one sentence, what happened, the author's argument, supporting material, native language, and limits.
-3. Do not add our audience, product, thesis, ownership, or candidate Topic to a new Discovery.
-4. Keep source engagement as context only; it is not evidence for our claims.
-5. When a user explicitly promotes a Discovery, create a Topic and run the Topic opportunity evaluation there.
+- Read the cited `products/entries/P-*.md` before using product facts in a
+  Topic, brief, draft, CTA, or product answer.
+- A Topic may cite `product_ids: none`; do not force a product connection.
+- A Topic may cite `recommendation_ids: none`; recommendations are third-party
+  review subjects, not owned products.
+- `product_fit` describes relevance, not a readiness verdict. Product fit never
+  replaces `need_ids`, evidence, audience, or opportunity scoring.
+- Do not turn a product promise into a Need quote. Do not turn a Need quote
+  into a product capability.
+- Keep exact pricing and entitlements in the dated product entry. Do not copy
+  stale prices into other files.
+- Do not invent proof, customers, outcomes, metrics, or testimonials.
 
-### Discovery status
+### Product fit
 
-`unread` → `read` → `saved` | `promoted` | `rejected`
+Use one of:
 
-### Discovery Card
+| fit | Meaning | Typical CTA |
+|-----|---------|-------------|
+| `direct` | The Topic directly addresses a problem the product solves | `educate` / `invite` / `sell` |
+| `adjacent` | The Topic builds context but is not a product pitch | `educate` / `mention` |
+| `none` | No honest product connection is needed | `none` |
 
-```text
-🔎 Discovery D-YYYYMMDD-XX
-【Source】 @handle · url · platform
-【Source digest】 what happened … · author argues … · support …
-【Limits】 what the source does not establish …
-【Status】 unread | read | saved | promoted | rejected
-【Next】 none / revisit / promote to Topic
-```
+Product fit is written on the Topic human card and inherited by the Brief.
+For third-party reviews, use `recommendation_ids`, not `product_ids`. Load the
+recommendation entry and disclose affiliate, sponsorship, or other commercial
+relationships before drafting.
 
-### Stop rules
+### Topic generation modes
 
-- Do not create a Topic merely because a source has high engagement.
-- Do not force every Discovery into the current product wedge.
-- Do not present a source summary as our own claim.
-- Do not generate candidate opportunities inside Discovery.
-- Do not use 5C as the default reading format.
+Use the smallest honest mode:
+
+| mode | Required inputs |
+|------|-----------------|
+| `demand` | Needs + Profile |
+| `demand_to_offer` | Needs + Product + Profile |
+| `demand_to_review` | Needs + Recommendation + Profile |
+| `review` | Recommendation + Profile + evidence |
+| `offer_education` | Product + Profile + mechanism |
+| `profile_thesis` | Profile + Pillar |
+
+Needs are the default source. Product or Recommendation presence never proves
+audience demand and never raises a Topic to `ready` by itself.
 
 ---
 
 ## § Topics (Opportunity evaluation)
 
 **Role:** Evaluate **Content Opportunities** — whether a topic deserves to exist as content. Does not replace capture or runs.  
-**Principle:** Topics are not titles. They are opportunities with a context, audience, conflict, insight, and evidence potential.
+**Principle:** Topics are not titles. They are a judgment card the content owner can read in one minute. Five-dim scores are a gate in the appendix, not the reading surface.
 
 ### Layout
 
 | Path | Role |
 |------|------|
 | `topics/scoring.md` | Scout → opportunity **15/20/25/25/15** (context/audience/conflict/insight/evidence); ready = opp≥**7.5** **and** aud≥**6** |
-| `topics/WATCHLIST.md` | Watchlist router |
-| `topics/watchlists/<profile_id>.md` | Per-profile radar (**scheme B**) |
-| `topics/watchlists/_shared.md` | Shared rows for all profiles (`*`) |
 | `topics/_index.md` | Queue: one row per topic, **`item`** link, **`src_*` engagement** |
-| `topics/items/T-YYYYMMDD-XX.md` | Content Opportunity (structured fields + scores) |
+| `topics/items/T-YYYYMMDD-XX.md` | Decision card (summary + judgment) + Score/Trace/Constraints (appendix) |
 | `topics/_template-item.md` | Template |
 
 ### Defaults
 
-- Max **5** new **`produce`** topics per promotion session; watchlist discovery itself has no Topic output cap
-- Scout first: `purpose` = `discard` | `library` | `produce`; `scout_label` = `demand` | `ally` | `foil` | `craft_only`
-- Opportunity dims (produce only): `context` `audience` `conflict` `insight` `evidence` (0–10 + note each) → `opp_score`
+- Scout first: `purpose` = `discard` | `library` | `produce`; `scout_label` = `demand` | `ally` | `foil` | `craft_only`. Needs default `scout_label=demand`.
+- Opportunity dims (produce only): `context` `audience` `conflict` `insight` `evidence` (0–10) → `opp_score`. Reasons live in the readable judgment layer, not in a score-table note column.
 - `ready` requires **opp_score ≥ 7.5 and audience ≥ 6**
 - `src_likes` / `src_replies` / `src_bookmarks` (+ views if known) + `engagement_at` on **index** when source is external
 - Do **not** fold `src_*` into opp_score; among **ready** only, prefer replies/bookmarks over views
@@ -246,85 +277,57 @@ watchlist signal → Discovery → Topic (only when explicitly promoted) → Bri
 | User intent | inbox/raw | topics |
 |-------------|-----------|--------|
 | `记一下` + URL | **Yes** (default) | Only if also asked to score as topic |
-| `按 watchlist 选题` | **Default NO** | Run **§ Discovery** first; create Discovery records, not Topics directly |
+| `扫需求选题` | **Default NO** | Scout + score ≤5 produce from `needs/` `status=captured`; `source_type=need`; set `need_ids`; **never** put `N-` in `capture_id`. After a `produce` T- is written, set those `N-` to `promoted` and append the T- on `topic_ids` (index + entry). Discard / library: leave `captured` or `retired` |
 | `扫 inbox 选题` | Existing only | Scout + score ≤5 produce; set `capture_id`; skip captures already linked to a T- |
 | `把 C-xxx 做成选题` | Keep | Create T- with `capture_id` (still Scout + opportunity score) |
 | `链接直接选题` | Default NO unless user agrees capture | Create T- + src engagement |
 | `把 T-xx 收进 inbox` | Yes for that source | Backfill `capture_id` on T- |
 
-After a Discovery batch, report **unread / read / saved / promoted / rejected** counts. Topic promotion is explicit and happens after Discovery, not during the scan.
-
 ### Create topic steps
 
-**Input gate:** A Topic must have an explicit input. Accept a user idea/brief, a URL, a Capture ID, or a Discovery ID named by the user. If the user only says “generate a topic” without naming a source, ask which input to use; do not select from the Discovery index, watchlist, or inbox by preference.
+**Input gate:** A Topic must have an explicit input. Accept: user idea/brief, Capture `C-…`, Need `N-…`, Product `P-…`, Recommendation `R-…`, or a profile thesis. If the user only says “generate a topic” without naming a source:
+
+1. If needs exist with `status=captured`, offer **扫需求选题**.
+2. Otherwise ask which explicit input to use.
 
 1. Hard filters (`scoring.md`); else skip.
 2. **Scout gate** — set `purpose` + `scout_label`; if `discard`, do not create T-.
 3. If `produce` (or user forces score):
-   a. Fill **structured opportunity fields**: context (what_changed, why_now), audience (who, current_belief, icp_checks), conflict (old_model, new_reality, belief_gap), insight (potential_insight, why_nonobvious), evidence (available, type, gaps).
-   b. Score all 5 opportunity dims (0–10 + note each) → `opp_score`.
-   c. Write `topics/items/T-….md`.
-4. If `library`: optional light item with `status: library`, or capture offer only.
-5. Add row on `topics/_index.md` (`item` + `src_*` when external).
-6. Output **Opportunity Card** in chat.
+   a. Write the **decision card** first (`topics/_template-item.md` upper half): 结论, 状态原因, 适合谁, 核心判断, 下一步, then the readable judgment sections: 要解决的问题, 受众当前相信什么, 我们准备讲哪一刀, 为什么现在, 看完后的改变, 依据, 当前缺口, 建议形式. Keep the summary short; no enum lists, heat, or weighted arithmetic in the readable layer.
+   b. Score all 5 opportunity dims (0–10) → `opp_score`. Put **numbers only** in `## Score`. Do not repeat the card as table notes.
+   c. Fill `## Trace` (ids, src heat) and `## Constraints` (writer must-nots). Write `topics/items/T-….md`.
+4. If `library`: optional light item with `status: library`, or capture offer only. Source needs stay `captured` (or `retired` if the user discards).
+5. Add row on `topics/_index.md` (`item` + `src_*` when external). `one_liner` = the card title sentence.
+6. If this T- was `produce` from `N-` ids: update each `needs/_index.md` row + entry to `status=promoted` and `topic_ids` containing this T-. Skip if no T- was written (`discard`).
+7. Output the **Decision Card** in chat — same shape as the readable layer, not a score walkthrough.
 
-**Important:** the structured fields (current_belief, belief_gap, potential_insight) are not decorative — they are the raw material the Brief Engine inherits. If you cannot articulate a belief gap, the conflict score cannot be above 5.
+**Important:** 「他们现在相信什么」must name the false belief. If you cannot, conflict cannot score above 5. Brief inherits the readable judgment layer, not the Score table.
 
 ### Opportunity Card
 
+Paste the decision summary and readable judgment sections. Do not walk five scores in the main body.
+
 ```text
-📋 Opportunity T-YYYYMMDD-XX
-【Opportunity】 … (one sentence — what's the content opportunity)
-【Source】 watchlist @handle (profile … · platform …) | inbox C-… | user | url
-【Scout】 purpose … · label … · note …
-【Src engagement】 likes … · replies … · bookmarks … (@ time)
-
-【Context】 what changed (1 line) → score …
-【Audience】 who + ICP check (1 line) → score …
-【Conflict】 current belief → reality (1 line) → score …
-【Insight】 non-obvious perspective (1 line) → score …
-【Evidence】 available + gaps (1 line) → score …
-【Opp score】 … · audience floor …
-
-【Profile fit】 pillar … · audience pain …
-【Verdict】 ready | backlog | parked | library
-【Weak dims】 (any dim < 6 → name it + suggest: research / reframe / discard)
-【Suggested selection】 swipe/atoms/claim (none OK)
-【Next】 开一单 / 改 angle 重打分 / 研究 evidence / 放弃 / 收进 inbox / 入库
+📋 选题判断卡 T-YYYYMMDD-XX
+【结论】 ready | backlog | parked
+【状态原因】 …
+【适合谁】 …
+【核心判断】 …
+【下一步】 开始生成 / 补需求 / 补证据 / 修改角度 / 放弃
+【要解决的问题】 …
+【他们现在相信什么】 以为 X → 其实 Y
+【我们准备讲哪一刀】 …
+【为什么现在值得讲】 …
+【看完后的改变】 之前 … → 之后 …
+【依据】 …
+【当前缺口】 …
+【建议形式】 …
 ```
 
 ### Topic → run
 
 On `用 T-xxx 开一单`: **ask platform(s)** if unset (multi-select OK). Create **one run per platform**, same `topic_id`, prefill selection per platform, mark topic `promoted` + list run ids on `topics/_index` `run` column.
 
-### Watchlist (scheme B — per profile)
-
-**Layout:** `topics/WATCHLIST.md` (router) + `topics/watchlists/<profile_id>.md` + `topics/watchlists/_shared.md`.
-
-**Resolve profile before scan or add:**
-
-1. User gives **profile_id** → use it.  
-2. User gives **account** → `accounts/_index` → `profile_id`.  
-3. **Neither → ask** (list profiles from `profiles/_index`; do **not** silently default).  
-
-**Load set:** active rows in `_shared.md` ∪ `watchlists/<profile_id>.md`.  
-**Platform filter:** user-specified, else default **`x`**; `全部平台` = all platforms in the set.  
-**Always set `platform` on each row.** Same brand on two networks → two rows.  
-**Shared across all profiles** → `_shared.md` (ids `#S-01…`). Two profiles only → copy row into both files.  
-**Add handle:** write to the chosen profile file (or `_shared` if user says shared / 全 profile).
-
-### Do not
-
-- Auto-dump watchlist scans into inbox
-- Skip Scout gate or opportunity scoring on `produce` topics
-- Skip structured opportunity fields (context/audience/conflict/insight/evidence) on `produce`
-- Skip per-dimension notes on `produce`
-- Exceed 5 **produce** topics per scan
-- Mark `ready` on high `src_*` or high opp_score alone (need audience ≥ 6 too)
-- Score conflict > 5 without articulating the `current_belief` and `belief_gap` in writing
-- Scan wrong network for a row (e.g. X tools on a `tiktok` handle)
-- Silently assume profile when user did not name profile or account
-
 ---
 
 ## § Swipe / atom library
@@ -338,12 +341,91 @@ On `用 T-xxx 开一单`: **ask platform(s)** if unset (multi-select OK). Create
 
 ---
 
+## § Interview
+
+Triggers: 采访我 / 完善人设 / interview me / who am I as a creator / 建立 profile.
+
+Follow `easysociable-content/workflows/INTERVIEW.md` for questions. Persist after each dimension; do not wait until the end.
+
+- Append `## Experience` / `## Values` to existing `voice.md` if those headings are missing. Do not rewrite filled Identity rows.
+- Missing `boundaries.md` → write empty starter, then interview. **Never invent boundaries.**
+- Do not scan the watchlist. Do not create a slideshow. Do not ingest needs in this section.
+
+### Hard gate (refuse 出图 / PagePack / `create_run`)
+
+Identity **only** Role / What I build / Point of view — no `(fill)`, non-empty. Public handle MAY stay `(fill)`. `boundaries.md` exists with Not covering **and** Never claim non-empty. If `needs/` exists, also `needs/_index.md` ≥ 3 `N-` rows; if `needs/` is absent, skip that count.
+
+Fail → list missing files; stay here. User must say **强制继续** / **force continue**. Optional check:
+
+```bash
+easysociable engine validate --root . --require-knowledge
+```
+
+### Completion
+
+Hard gate vs first-session (`profile: partial`) vs complete seven dimensions (`profile: complete`) — same table as INTERVIEW.md. Experience / Values / expression are not the hard gate. Needs hard gate is ≥ **3** original quotes; first-session **target** is **5**.
+
+---
+
+## § Needs (audience quotes)
+
+Triggers: 记需求 / 用户原话 / 评论导出 / capture audience quotes / user needs.  
+扫需求选题 → **§ Topics** (this section only writes `N-` records).
+
+Follow `easysociable-content/workflows/NEEDS.md` when this engine's copy of the workflow is the newer one; this section wins if both exist.
+
+### Layout
+
+| Path | Role |
+|------|------|
+| `needs/_index.md` | Quote registry |
+| `needs/entries/N-YYYYMMDD-XX.md` | Verbatim quote + sightings + optional gloss |
+| `needs/_template.md` | Entry shape |
+
+### Status machine (only these words)
+
+```text
+captured  → just written, or still captured after a synonym merge (frequency ≥ 1)
+promoted  → and only when a T- exists whose need_ids contain this N-; topic_ids lists that T-
+retired   → user discarded
+```
+
+- Never `clustered`. Merge is not a status.
+- Never mark `promoted` without that `T-`. `topic_ids` non-empty ≡ `promoted`.
+- After § Topics writes a `produce` T- from this `N-`, flip this row + entry to `promoted` and append the T- on `topic_ids`. Discard / library stay `captured` or `retired`.
+- Scan input: `status=captured` (`topic_ids` empty). Max 5 `produce`.
+- Quote cell = verbatim. Gloss is optional and separate.
+- Do not invent quotes. Do not treat watchlist hooks as needs.
+- `N-` never goes in topic `capture_id`.
+
+### Ingest
+
+1. New entry from `_template.md` + row at top of `_index.md`.
+2. Chat card:
+
+```text
+✅ Need N-YYYYMMDD-XX
+【Quote】 …
+【Source】 comment | dm | consult | faq | student | other
+【Frequency】 1
+【Stored】 needs/_index + needs/entries/N-….md
+【Merge】 new | merged into N-… (frequency now k, status still captured)
+```
+
+3. Synonym merge: propose → user yes → same `N-` stays `captured`, `frequency += 1`, append sighting. Retire a mistaken duplicate.
+
+Hard gate: `needs/_index.md` ≥ **3** `N-` rows once `needs/` exists (empty index fails). Target **5**. Prefer scanning needs before inbox.
+
+---
+
 ## § Open a run
 
 ### When
 
 User wants a tracked job: "开一单", "open a run", "按完整流程", or a multi-step post with gates.
 
+**Hard gate first** (same as § Interview). Fail → list missing files; do not create `runs/<slug>/` unless **强制继续** / **force continue**.
+
 ### Model (one platform = one Run)
 
 - **One folder = one platform draft** (native rewrite).  
@@ -438,13 +520,15 @@ The brief inherits reasoning from the Topic Opportunity and focuses on **what to
 
 **Step 1 — Inherit from Topic Opportunity**
 
-When the run is from T-xxx, copy the topic's structured fields into `brief.md` `## Inherited`:
-- `context` (from topic's what_changed / why_now)
-- `audience` (from topic's who / current_belief)
-- `conflict` (from topic's belief_gap)
-- `insight` (from topic's potential_insight)
+When the run is from T-xxx, copy the **readable judgment layer** into `brief.md` `## Inherited`:
+- `context` ← 「为什么现在值得讲」
+- `audience` ← 「适合谁」
+- `conflict` ← 「他们现在相信什么」
+- `insight` ← 「我们准备讲哪一刀」
+- `outcome` ← 「看完后的改变」
+- `evidence` ← 「凭什么这么判断」 + 「当前缺口」
 
-Sharpen these for the specific platform/angle — do not re-derive from scratch. If T-xxx has no structured fields (legacy topic), derive them before proceeding.
+Sharpen these for the specific platform/angle — do not re-derive from scratch. If T-xxx is a legacy five-section score sheet, derive the readable judgment layer before proceeding. Do not inherit the Score table as prose.
 
 **Step 2 — Walk the decision tree**
 
@@ -625,25 +709,29 @@ Planned platform needs multi-page images (linkedin / ig / tiktok), not pure X te
 
 ### Preconditions
 
+0. **Hard gate** (same as § Interview). Fail → list missing files; no slideshow/template handoff unless **强制继续** / **force continue**.  
 1. Run exists; brief OK; editor OK; **rubric SHIP**.  
-2. Per-platform `page_count` / `deck_hint` sensible.  
-3. Prefer swipe with page roles; else explicit roles from brief.
+2. Per-platform `page_count` / `deck_hint` follows the **arc**, not a five-family catalog.  
+3. Prefer a swipe whose beats are an argument; else name a one-line arc from the brief.  
+4. **Forbidden default:** Cover → Point → Steps → Recap → CTA (those are P0 family names, not a pack recipe).
 
 ### Agent steps
 
 1. Write **`runs/<slug>/pack.md`** (from `_template/pack.md`; `pack-<platform>.md` OK):  
    - this run is already one platform  
+   - **Arc** one-liner + recipe **before** Pages  
    - slots, language, pillar, swipe_id, claim_id  
+   - page 1 `role` is not automatically `cover`  
 2. **Pack Card** in chat — user may `改 pack：…`.  
-3. **Render:**  
-   - If slideshow skill available: render → files under **`exports/<slug>/`** → set pack `job_id`, `export_path`, status `done`; set `runs/_index` `pack`/`export` to yes.  
-   - If **not** available: status `not_requested` / blocked — **do not fake images**.  
-4. User **图 OK** or revise slots and re-render.
+3. Hand off to **easysociable-slideshow**: it picks templates by platform + canvas + slot shape, then opens Studio. Topology lock means a wrong arc needs a **new Run**, not slot rewrite.  
+4. **Render / Download:** pixels leave the product from Studio Download (not CLI render). After the user downloads, copy files under **`exports/<slug>/`** if needed; set pack `job_id`, `export_path`, status `done`; set `runs/_index` `pack`/`export` to yes. If slideshow skill is **not** available: status `not_requested` / blocked — **do not fake images**.  
+5. User **图 OK** or revise slots (same topology) / new Run (different arc).
 
 ### Pack Card
 
 ```text
 📑 Pack  RUN-…  platform=linkedin|tiktok|ig
+【Arc】 one-liner / recipe
 【Pages】 N
 【deck_hint】 …
 【Outline】 P1… Pn
@@ -659,6 +747,8 @@ Planned platform needs multi-page images (linkedin / ig / tiktok), not pure X te
 - Invent metrics in slots  
 - Skip SHIP before quality pack  
 - Store binaries inside `runs/` (use **exports/**)  
+- Default Cover → Point → Steps → Recap → CTA  
+- Skip the Arc line and fill P0 family names as a tutorial  
 
 ---
 
@@ -725,13 +815,12 @@ Reply 批准 … / 否决 / 再观察
 
 ### Self-check (Topic / Opportunity)
 
-- [ ] Structured opportunity fields filled (context/audience/conflict/insight/evidence) on `produce`
-- [ ] `current_belief` and `belief_gap` articulated in writing (not just a score)
-- [ ] `potential_insight` stated — what's non-obvious
-- [ ] 5-dim scores with per-dim notes
-- [ ] `opp_score` weighted correctly; `audience` floor checked
-- [ ] Weak dims (< 6) flagged with suggestion
-- [ ] Opportunity Card output in chat
+- [ ] Decision card filled (结论 / 状态原因 / 适合谁 / 核心判断 / 下一步)
+- [ ] Readable judgment filled (问题 / 当前相信什么 / 我们的角度 / 为什么现在 / 看完后的改变 / 依据 / 缺口 / 形式)
+- [ ] False belief named in 「他们现在相信什么」 (not just a conflict score)
+- [ ] Readable sections are concise; heat and arithmetic only under `## 评分与追踪附录`
+- [ ] Score table is numbers only; opp + aud + verdict line present
+- [ ] Opportunity Card in chat matches the human half (not a five-score walkthrough)
 
 ### Self-check (Run)