@gobing-ai/knowledge-kit 0.1.11 → 0.1.13

package/plugins/kk/skills/content-safety/references/platforms/surfdash.md

@@ -0,0 +1,36 @@
+# Salty Talk / Surfing (surfdash) — platform reference
+
+`surfing.salty.vip` 是本项目自有的静态发布站点（Robin Min 自有域名，栏目「AI 乱炖」，zh/en/ja 三语）。
+这是**自有渠道**，不是第三方分发平台：没有平台审核队列、字级词表或 AI 标注接口可引用。
+本文件存在的意义是把「自有站点没有平台规则」这件事写清楚，避免审核流程把「无三方平台规则」
+误判成证据缺口并默认 BLOCK。
+
+| Field | Value |
+|-------|-------|
+| Official source | 自有站点，无第三方协议页；本文件由站点维护者（Robin Min）本人核定 |
+| Scope | `surfing.salty.vip` 文章页（正文、frontmatter 的 title/description/key_points/cover） |
+| Effective date | 本文件创建日即生效（自有平台规则由维护者裁定） |
+| Last verified | 2026-11-05（创建） |
+| Evidence status | 维护者本人口径，非三方引用；无字级禁用词表 |
+
+## Evidence distinctions
+
+- **维护者裁定（本文件的权威来源）**：站点是自有域名下的小型技术/资讯栏目，采用与本项目其他
+  台一致的通用内容纪律；没有平台方提供的可引用条款。
+- **通用纪律（沿用技能默认）**：披露/AI 声明、来源可靠性、隐私/PII、医疗/投资类内容红线全部
+  沿用技能 default；本文件不新增平台规则。
+
+## Review items
+
+| ID | Item | Grade |
+|----|------|-------|
+| SD-01 | 来源诚实性：对外引用（媒体/论文/Blog）须给出真实出处链接；「综述性转述未读原文」是 sourcing gap，按 note 记录并在站点正文保持既有 hedging；**不要**因为转述来自聚合页/未读原文而 block——这与 apple-podcasts 的 AP-06 严格度不同，自有站点由维护者自行判断并复核。 | note |
+| SD-02 | 数字与事实核对：与源链接一致的数字/日期/机构名出现冲突时按技能通用规则处理（correctable → revise；冲突无解 → block）。 | note→judge |
+| SD-03 | 可识别个人信息（听众或第三方的私人信息、联系方式、住址等） | desensitize→block if unfixable |
+| SD-04 | roku/医疗/投资劝诱内容技能默认红线不变（本文件不放开任何默认红线）。 | default |
+
+## Open questions / escalation
+
+- 自有站点无第三方审核 → 本文件不应产生 `evidenceGap: true` 类 BLOCK；任何「surfdash 无 reference
+  文件」的发现都指向本文件缺失，而不是内容风险。
+- 若未来站点引入广告或国家安全审查类规则，本文件需要更新。

package/plugins/kk/skills/content-safety/references/platforms/xhs.md

@@ -0,0 +1,39 @@
+# 小红书 (Xiaohongshu / xhs) — platform reference
+
+Review-item IDs here are **this skill's bookkeeping numbers**, not official platform rule codes.
+与 xiaoyuzhou.md 同一格式约定：这是本技能基于操作者已核验证据的保守立场，不是平台条文。
+
+| Field | Value |
+|-------|-------|
+| Official source | <https://www.xiaohongshu.com/community/>（社区公约/创作细则入口，多级页面） |
+| Scope | 笔记（图文/视频长文）、封面图、话题标签、昵称简介 |
+| Effective date | unknown（社区公约页面未标注可引用的版本生效日期） |
+| Last verified | 2026-11-05（写本文件时按操作者已有账号审查经验整理，未逐字读官方更新后全文） |
+| Evidence status | **未获官方逐字条文**；以下审核项是本技能的保守立场，不是平台条文；与小宇宙 0189 事件类似，任何具体下架理由以官方为主，本技能按保守项判断 |
+
+## Evidence distinctions
+
+- **官方规则（已知存在，未逐字核对）**：小红书有《社区公约》与《创作规范》，对违法违规、医疗
+  健康、财产投资、隐私、低质同质化、AI 生成内容有原则性条款；公开文本不提供逐字词表。
+- **操作者经验（保守立场来源）**：账号为个人技术分享（栏目「AI 乱炖」衍生），非新闻机构、无
+  医疗/金融资质、不带货；发帖以图文长文/播客预告为主。
+- **编辑建议（本技能）**：以下审核项是本技能基于上述证据的保守立场，不是平台条文。
+
+## Review items
+
+| ID | Item | Grade |
+|----|------|-------|
+| XH-01 | 资质口径：不得呈现「新闻资讯播报」形态或暗示持有新闻资质（技术/科普类分享不受影响；同 xiaoyuzhou.md XY-01 的操作者裁定 2026-10-10，按 note 记录，不逐集 escalate）。 | note |
+| XH-02 | 医疗健康/药品/诊疗建议：以医疗结论、疗效、用药指导为主线的内容（本栏目主题为 AI 技术/产业资讯，正常不会触发；一旦触发按 block）。 | block |
+| XH-03 | 投资/理财：以个股买卖建议、收益承诺为主线的内容（对 quadrature/Anthropic 等估值表述属于普通事实转述，不是建议；命中后再 judge）。 | block |
+| XH-04 | AI 生成内容标识：平台对 AI 生成内容有标注要求（** 未逐字核对当前接口规则，按公共常见要求保守处理**）。本栏目发布为「AI 辅助创作」的播客预告/图文 —— 操作者已在账号简介披露 AI 辅助；单条内容不再逐条 escalate。 | note |
+| XH-05 | 可识别个人信息（听众或第三方的私人信息、联系方式、住址等） | desensitize→block if unfixable |
+| XH-06 | 时政/公共事务主线：同 xiaoyuzhou.md XY-02（政策管制、军事、公共政策争议为主线的内容按 block）。 | block |
+
+## Open questions / escalation
+
+- 无官方字级词表 → 任何「词命中即下架」的断言都不成立；同理，无词表不等于安全。
+- AI 标注、内容审核新规变化频繁 → 每次提审前按 XH-04 复核；`RISK` 或证据缺口一律人工复审
+  （`escalate: true`），不得静默 PASS。
+- 资质口径、时政主线与个人信息的红线全部沿用技能默认，本文件只 diminute XH-04 的逐条 escalate
+  （业务上固定披露已存在）。

package/plugins/kk/skills/explain-things/SKILL.md

@@ -7,6 +7,7 @@ description: >-
   "how does X work", "ELI5", "like I'm 5", or "show me". Normal explanations are
   concise inline views; the ELI5 register is opt-in. This is not for content authoring,
   research, judging, publishing, or package/code review workflows.
+requires: [local-fs]
 ---
 
 # explain-things

package/plugins/kk/skills/image-authoring/SKILL.md

@@ -7,6 +7,7 @@ description: >-
   "list the image formats and styles". Three operations — generate,
   extract-style, list-presets — over named format and style presets, with a
   confirmation gate before any paid generation.
+requires: [cli:kk, cli:spur, local-fs]
 ---
 
 # image-authoring — image generation agent surface (generate | extract-style | list-presets)

package/plugins/kk/skills/itc-generating/SKILL.md

@@ -7,6 +7,7 @@ description: >-
   writing method", "generate an IT technical draft on X", "create a technical
   article for WeChat/English platforms". Orchestrates topic (outline + draft),
   optional storm-research, and optional content-judge without enlarging those skills.
+requires: [cli:kk, local-fs]
 ---
 
 # itc-generating — IT technical draft generation (method + orchestration)

package/plugins/kk/skills/publish/SKILL.md

@@ -6,6 +6,7 @@ description: >-
   `kk executor run` / `kk fanout` for file-cli and script channels; sequences
   agent-default CMS channels as workflow `agent.run` steps. Does not own
   transport.
+requires: [cli:kk, local-fs]
 ---
 
 # publish — leftover channel operator surface

package/plugins/kk/skills/smart-seo/SKILL.md

@@ -6,6 +6,7 @@ description: >-
   this saved audit", "explain these SEO findings", or "check GEO readiness". Read-only results: no
   site mutation, no ranking and no citation promises.
 version: 0.1.0
+requires: [cli:kk, cli:spur, local-fs]
 ---
 
 # smart-seo — evidence-grounded SEO/GEO audits

package/plugins/kk/skills/storm-research/SKILL.md

@@ -8,6 +8,7 @@ description: >-
   (prepare → ingest → generate → render) over the 0056 works layout. Research is separate from
   authoring: topic owns init→outline→draft and this skill never merges into topic.
 version: 0.1.0
+requires: [cli:kk, local-fs]
 ---
 
 # storm-research — STORM daily research (topic sentence XOR markdown file → content.md)

package/plugins/kk/skills/taste-unslop/SKILL.md

@@ -5,6 +5,7 @@ description: >-
   voice and substance — "make this sound human", "remove the AI tells", "audit this
   copy for canned patterns", "restore my voice after AI editing". Not for code,
   translation-only work, or proofreading that must preserve style.
+requires: [local-fs]
 ---
 
 # taste-unslop

package/plugins/kk/skills/topic/SKILL.md

@@ -7,6 +7,7 @@ description: >-
   Runs the topic-core authoring loop (init → outline → draft) through four
   operations with explicit operator gates and safe resume. knowledge-kit's
   cohesive topic-authoring core, harvested from the WT 7-stage wrappers.
+requires: [cli:kk, cli:spur, local-fs]
 ---
 
 # topic — topic-core authoring (create | init | outline | draft)

package/plugins/kk/skills/web-automation/SKILL.md

@@ -9,6 +9,7 @@ description: >-
   web-automation skill. Owns method and evidence; transport stays in kk
   plugins; orchestration is a @gobing-ai/ts-dual-workflow-engine
   transition-flow (see docs/design/web-automation-engine.md).
+requires: [cli:spur, local-fs]
 ---
 
 # web-automation — discover, enhance, automate with a real browser

package/plugins/kk/skills/xhs-images/SKILL.md

@@ -7,6 +7,7 @@ description: >-
   closing) grounded in the source, renders them through the image-gen executor
   with the xhs-card/xhs-knowledge presets, packages a publishable Content, and
   hands off to kk:publish channel xhs. Never publishes directly.
+requires: [cli:kk, local-fs]
 ---
 
 # xhs-images — source-grounded XHS card series (plan → render → package → handoff)

package/plugins/kk/workflows/kk-collect.yaml

@@ -48,10 +48,10 @@ states:
     onEnter:
       - kind: shell
         options:
-          # Reporting only: a ledger failure must never abort a tick before the lock is even taken.
-          onError: continue
           command: >-
             kk ledger sync --workflow kk-collect
+        # Reporting only: a ledger failure must never abort a tick before the lock is even taken.
+        onError: continue
       - kind: shell
         options:
           # stamp: the pinned var, else the UTC minute (R4). work_dir: `.works/kk-collect/<stamp>` (R4),
@@ -92,13 +92,13 @@ states:
         # revocation warns (captured:false) and only disables Board previews.
         # onError: continue keeps the lock-releasing failure path intact instead of a hard abort.
         options:
-          onError: continue
           command: >-
             kk board capture --workflow kk-collect --run "${vars.__runId}"
             --work-dir "${vars.work_dir}" --stamp "${vars.stamp}"
             --definition-digest "${vars.__definitionDigest}"
             --setting "limit=${vars.limit}" --setting "horizon_hours=${vars.horizon_hours}"
             > "${vars.work_dir}/board-capture.json"
+        onError: continue
       - kind: shell
         # onError: continue on both ingestion actions, with the artifact guard below as the positive
         # success contract: a state-machine aborts the run on a failed action without taking a

package/plugins/kk/workflows/kk-daily-ai-voice2.yaml

@@ -221,10 +221,10 @@ nodes:
     action:
       kind: shell
       options:
-        onError: continue
         command: >-
           kk plugin check wechatmp-pub xhs-pub --timeout 60000
           || echo "session-preflight: a publish channel's saved session was refused — fix it before this run's publish step with: bun plugins/publishings/<channel>-pub/src/profile-check.ts login (wechatmp or xhs)"
+      onError: continue
 
   - id: extract
     description: >-
@@ -509,7 +509,7 @@ nodes:
     # 0238 R3: reads 21-plan/<date>_03_plan_plan.json, so it must not start before the plan
     # producers settle. `script-style` stays first in the list: a done dependency in the mix keeps
     # this node runnable when the plan-authoring nodes are disabled (all-skipped deps skip a node).
-    dependsOn: [script-style, plan-translate, plan-translate-retry]
+    dependsOn: [script-style, plan-translate, plan-translate-retry, article]
     condition:
       kind: shell
       options:
@@ -620,8 +620,8 @@ nodes:
           kk store pool-count "${vars.work_dir}/21-plan/${vars.run_date}_04_quality-control-content_candidates.json" --min 1
     action:
       kind: shell
+      onError: continue
       options:
-        onError: continue
         command: >-
           OMNIVOICE_SPEED=1.06 kk stage daily-generate "${vars.work_dir}" "${vars.run_date}" "${vars.plugins_path}" "${vars.transcode_mp3}" "${vars.vdriver}" "1" "${vars.episode_max_minutes}" "${vars.episode_min_minutes}"
 
@@ -641,8 +641,8 @@ nodes:
           && ! jq -e '(.metadata.generator == "kk:voxcpm-tts" or .metadata.generator == "kk:gemini-tts") and .metadata.qc.passed == true' "${vars.work_dir}/30-audio/${vars.run_date}_11_generate_content.json"
     action:
       kind: shell
+      onError: continue
       options:
-        onError: continue
         command: >-
           kk stage daily-generate "${vars.work_dir}" "${vars.run_date}" "${vars.plugins_path}" "${vars.transcode_mp3}" "gemini" "1" "${vars.episode_max_minutes}" "${vars.episode_min_minutes}"
 
@@ -689,7 +689,7 @@ nodes:
       options:
         command: >-
           kk stage daily-voice-audit "${vars.work_dir}" "${vars.run_date}" "${vars.plugins_path}"
-        onError: continue
+      onError: continue
 
   - id: duration
     description: "Measured duration gate: under episode_min_minutes the run refuses and closes as no-content (refusal artifact + emptied candidates, exit 0 — 0266); above episode_max_minutes it still fails loud. Duration is authoritative."
@@ -829,7 +829,9 @@ nodes:
 
   - id: translate
     description: >-
-      Agent translates both scaffolded locale drafts in place. The two draft paths are read from the
+      Agent translates both scaffolded locale drafts into <run_date>_21_translate_<locale>.md under the
+      work dir (2026-11-04: both executor sandboxes refuse writes into the Surfdash checkout, and the
+      step still exits 0); translate-refine installs them over the drafts. The two draft paths are read from the
       marker files at their fixed paths (no var projection after the fan-out: concurrent setVars is
       last-writer-wins, design §6), and an empty marker means that locale is absent. The local
       validation node gates final Surfdash publish so its strict all-locale CMS policy is met.
@@ -837,15 +839,6 @@ nodes:
     action:
       kind: agent.run
       options:
-        # 20261012 hardening: this is the LAST agent step and a translation failure must not abort
-        # the overall report/podcast close, yet the step carried no tolerance and no retry sibling — a stochastic
-        # executor failure here aborted the DAG *after* surfdash and podcast had published, so
-        # publish-classify, mark-published, run-report and ledger never ran for an otherwise complete
-        # day. Tolerating the failure is safe because a scaffold is an unpublished draft: the prompt
-        # below is what flips `draft: true` → `draft: false`, so an untranslated locale stays off the
-        # site, and `daily-publish-completeness` now reads that flag and reports the locale as failed
-        # instead of calling a scaffold `done`.
-        onError: continue
         role: scribe
         agent: ${vars.agent}
         timeoutMs: 600000
@@ -856,11 +849,20 @@ nodes:
           Translate the en/ja draft posts of the zh article. Read the two marker files at these fixed paths — each holds one draft path, or is empty when that locale was not scaffolded:
           English: ${vars.work_dir}/31-publish/${vars.run_date}_20_translate-localize_en-post-path.txt
           Japanese: ${vars.work_dir}/31-publish/${vars.run_date}_20_translate-localize_ja-post-path.txt
-          For each: if the marker is empty or unreadable, skip that locale. Otherwise edit the named file in place — translate the frontmatter title and the whole markdown body to natural English/Japanese respectively. Keep frontmatter keys, dates, URLs, code, and the assets/ image reference untouched. Set draft: false (the translated post publishes to the site) and remove any canonical: frontmatter line pointing at a different locale's URL.
+          For each: if the marker is empty or unreadable, skip that locale. Otherwise read the named draft but do NOT edit it (it sits in the Surfdash checkout, outside your writable workspace): write the complete translated file — frontmatter and body — to ${vars.work_dir}/31-publish/${vars.run_date}_21_translate_en.md (English) or ${vars.work_dir}/31-publish/${vars.run_date}_21_translate_ja.md (Japanese); a later stage installs it over the draft. Translate the frontmatter title and the whole markdown body to natural English/Japanese respectively. Keep frontmatter keys, dates, URLs, code, and the assets/ image reference untouched. Set draft: false (the translated post publishes to the site) and remove any canonical: frontmatter line pointing at a different locale's URL.
           Also translate these frontmatter values into the target locale, keeping all other keys untouched: description, seo_title, seo_description, and each key_points item. Each stays one coherent standalone sentence that summarizes the same story as the zh source — never splice fragments from different items or stories into one, and key_points must keep exactly the same number of items as the zh post. The 2026-10-23 run failed this: spliced description/key_points had to be hand-repaired before sync.
           Series names are fixed product identity, never invented or freely translated: the en series name is "Daily AI Stew" (show "Salty Talk"); the ja series name is "デイリーAIシチュー" (show "咸話咸説"). Never emit 毎日AIブレンド, ごった煮, "Daily AI Medley", "hodgepodge", "Daily AI Briefing", or the zh name 每日AI乱炖 in en/ja prose or link text (a URL keeps whatever it contains). Openers: en "Your Daily AI Stew from Robin, on Salty Talk."; ja "咸話咸説のデイリーAIシチュー、Robin がお届けします。" Listen links: en "[listen to Daily AI Stew · <date>](<url>)", ja "[デイリーAIシチュー · <date> を聴く](<url>)". In each key_points item keep the "Label — sentence" shape: the label before " — " stays a short phrase of at most 14 characters (ja) / 28 (en), never truncated with "…". The local translate-validate stage rewrites known retired names deterministically and fails the publish gate on leftovers.
           Keep frontmatter valid YAML: double-quote any value containing ': '. Read the surfdash translator glossary if present at the surfdash checkout root under .agents/skills/surfdash-translator/glossary.md and apply its terminology.
-          Do not wait for operator confirmation. Each edited file must end fully in its target language.
+          Do not wait for operator confirmation. Each written file must end fully in its target language.
+      # 20261012 hardening: this is the LAST agent step and a translation failure must not abort
+      # the overall report/podcast close, yet the step carried no tolerance and no retry sibling — a stochastic
+      # executor failure here aborted the DAG *after* surfdash and podcast had published, so
+      # publish-classify, mark-published, run-report and ledger never ran for an otherwise complete
+      # day. Tolerating the failure is safe because a scaffold is an unpublished draft: the prompt
+      # above is what flips `draft: true` → `draft: false`, so an untranslated locale stays off the
+      # site, and `daily-publish-completeness` now reads that flag and reports the locale as failed
+      # instead of calling a scaffold `done`.
+      onError: continue
 
   # 2026-10-24: the locale translation carried `onError: continue` with NO retry sibling, so a
   # failed executor left the en/ja drafts untranslated and the old sync stage could not distinguish
@@ -874,15 +876,15 @@ nodes:
       options:
         command: >-
           test "$(cat "${vars.work_dir}/31-publish/${vars.run_date}_20_translate-localize_zh-post-path.txt" 2>/dev/null)" != ""
-          && { for L in en ja; do M="${vars.work_dir}/31-publish/${vars.run_date}_20_translate-localize_$L-post-path.txt"; P="$(cat "$M" 2>/dev/null)"; [ -z "$P" ] && continue; grep -q '^draft: *false' "$P" || { echo "untranslated: $L ($P)"; exit 0; }; done; exit 1; }
+          && { for L in en ja; do M="${vars.work_dir}/31-publish/${vars.run_date}_20_translate-localize_$L-post-path.txt"; P="$(cat "$M" 2>/dev/null)"; [ -z "$P" ] && continue; O="${vars.work_dir}/31-publish/${vars.run_date}_21_translate_$L.md"; grep -q '^draft: *false' "$O" || { echo "untranslated: $L ($O)"; exit 0; }; done; exit 1; }
     action:
       kind: agent.run
       options:
-        onError: continue
         role: reviewer
         agent: ${vars.agent_retry}
         timeoutMs: 600000
         input: *translate-input
+      onError: continue
 
   - id: translate-refine
     description: "Run the Surfdash-owned refine pass over zh/en/ja locally before the locale fingerprint is admitted; no CMS, git, or remote side effect"