lifeos 1.0.2 → 1.1.0

package/README.md

@@ -1,9 +1,13 @@
 # LifeOS
-
+![LifeOS Example](./example.png)
 [中文](./README.zh.md) | English
 
 LifeOS helps you grow scattered ideas into structured knowledge and truly master it, from quick captures, to brainstorming and deep research, to systematic project planning and knowledge notes, to spaced review and mastery tracking. The goal is not just building a knowledge base, but helping you understand, internalize, and command complex knowledge.
 
+## Why Build LifeOS?
+
+LifeOS started from a simple goal: package learning workflows, skills, templates, prompts, and a memory system into one complete setup you can use immediately. Instead of assembling your own toolchain from scratch or jumping between disconnected tools, you can initialize once, start working right away, and keep accumulating knowledge, process, and preferences as you go.
+
 ## Core Features
 
 ### Memory System
@@ -16,7 +20,7 @@ Session bridges and active-document context persist, so agents do not depend onl
 
 #### Project-scoped and skill-bound
 
-The memory system runs around the current LifeOS project in the vault, activates only inside workflows such as `today`, `project`, `research`, `knowledge`, `revise`, and `archive`, and keeps accumulating preferences, decisions, and context.
+The memory system runs around the current LifeOS project in the vault, activates only inside workflows such as `today`, `project`, `research`, `knowledge`, `revise`, `digest`, and `archive`, and keeps accumulating preferences, decisions, and context.
 
 #### More controllable than global memory
 
@@ -34,28 +38,28 @@ LifeOS provides a set of Agent skills designed around the learning process, conn
 
 - `/today`, `/brainstorm`, `/ask`: organize the day's focus, clarify questions, and quickly expand ideas
 - `/project`, `/research`, `/knowledge`: turn a topic into a project, a research report, and structured knowledge notes
+- `/digest`: subscribe to topic updates and generate structured weekly digests from paper sources, RSS, and web search
 - `/read-pdf`, `/revise`, `/archive`: move from source extraction, to review and reinforcement, to periodic archiving
 
 ## Core Components
 
 - **Memory system** — Project-scoped and skill-bound, providing vault indexing, session memory, and context assembly for AI agents
 - **CLI scaffold** — install globally, then use `lifeos init` to bootstrap a complete workspace
-- **Skill system** — 9 Agent skills covering diary, projects, research, knowledge curation, review, and more
+- **Skill system** — 10 Agent skills covering daily planning, projects, research, weekly digests, knowledge curation, review, and more
 - **Templates + Schema** — 8 structured templates + Frontmatter schema for consistent notes
 
 ## Quick Start
 
-At the moment, only the Agent CLI workflow has been verified in practice on macOS. The Agent GUI path has not been systematically tested yet, and Windows has not been verified either, so the experience there may not be fully consistent yet.
+LifeOS has been verified to work properly with Claude Code TUI / Codex TUI / OpenCode TUI on macOS, and with OpenCode GUI on Windows. Other desktop GUI apps or platform/client combinations have not been validated yet and may require additional testing.
 
 ### Prerequisites
 
-Before starting, make sure Obsidian and at least one of Claude Code CLI / Codex CLI / OpenCode CLI are installed locally.
+Before starting, make sure Obsidian and at least one of Claude Code TUI / Codex TUI / OpenCode TUI / OpenCode GUI are installed locally.
 
 | Dependency | Required | Purpose |
 |---|---|---|
-| **Node.js 18+** | Required | Runtime for MCP server and CLI |
-| **Git** | Required | Version control for vault data, including the memory DB |
-| **Python 3** | Required | PDF extraction (`/read-pdf` skill) |
+| **Node.js 24.14.1+ (LTS)** | Required | Runtime for MCP server and CLI |
+| **Python 3** | Required | PDF extraction (`/read-pdf`) and digest fetch helpers (`/digest`) |
 
 `lifeos init` checks all prerequisites before creating the workspace.
 
@@ -83,6 +87,8 @@ After init, MCP server configs are automatically registered for:
 
 Launch any of these tools in the vault directory to use all skills.
 
+If you want version control for the vault, initialize and manage Git yourself. LifeOS does not create or manage Git metadata for you.
+
 ## CLI Commands
 
 ```bash
@@ -101,10 +107,9 @@ Creates a complete LifeOS workspace:
 - 10 top-level directories plus nested subdirectories
 - 8 Markdown templates
 - Frontmatter schema
-- 9 AI skills with language-aware assets
+- 10 AI skills with language-aware assets
 - `CLAUDE.md` agent behavior spec
 - `lifeos.yaml` config
-- Git init plus `.gitignore`
 - MCP server registration (Claude Code / Codex / OpenCode)
 
 ### upgrade
@@ -112,7 +117,7 @@ Creates a complete LifeOS workspace:
 Upgrades and re-syncs an initialized vault:
 
 - **Smart merge**: update unmodified templates, schema files, built-in prompts, and skill files; skip modified ones with a warning
-- **Restore missing scaffold**: bring back missing directories and managed files such as the memory directory, `.claude/skills`, `CLAUDE.md`, `AGENTS.md`, `.gitignore`, `.git`, and MCP config entries
+- **Restore missing scaffold**: bring back missing directories and managed files such as the memory directory, `.claude/skills`, `CLAUDE.md`, `AGENTS.md`, and MCP config entries
 - **Preserve user changes**: built-in files already customized by the user are not force-overwritten
 - **`--override` force-refreshes resources**: overwrite templates, schema, prompts, skills, `CLAUDE.md`, `AGENTS.md`, and MCP config entries without deleting user notes, resources, `memory.db`, memory-system data, or custom directory/memory settings in `lifeos.yaml`
 
@@ -139,6 +144,7 @@ This means LifeOS does not lock you into fixed directory names. You can freely a
 | `/today` | Morning planning: review yesterday, plan today |
 | `/project` | Idea -> structured project |
 | `/research` | Topic -> deep research report |
+| `/digest` | Topic subscription -> structured weekly digest |
 | `/knowledge` | Book/paper -> knowledge note |
 | `/revise` | Generate quizzes, grade, and track mastery |
 | `/read-pdf` | PDF -> structured notes |
@@ -165,7 +171,7 @@ Create a `.md` file in your vault's Prompts directory (`{system directory}/Promp
 
 ## Tech Stack
 
-- **Runtime:** TypeScript + Node.js 18+
+- **Runtime:** TypeScript + Node.js 24.14.1+ (LTS)
 - **Database:** SQLite + FTS5 (full-text search)
 - **Segmentation:** @node-rs/jieba (Chinese tokenization)
 - **Protocol:** MCP (Model Context Protocol)
@@ -176,8 +182,8 @@ Create a `.md` file in your vault's Prompts directory (`{system directory}/Promp
 - ✅ LifeOS 1.0 is now basically usable
 - ✅ The CLI supports directory customization
 - ✅ The CLI `upgrade` command supports smart updates
-- ✅ Agent CLI has been tested on macOS
-- ☐ Test and support Agent GUI and Windows
+- ✅ Claude Code TUI / Codex TUI / OpenCode TUI on macOS and OpenCode GUI on Windows have been tested
+- ✅ The `/digest` skill supports multilingual weekly digests with multi-source paper fetching
 - ☐ Improve memory-system precision
 - ☐ Support custom skills
 - ☐ Support custom workflows

package/README.zh.md

@@ -1,9 +1,13 @@
 # LifeOS
-
+![LifeOS 示例](./example.png)
 [English](./README.md) | 中文
 
 LifeOS 帮助你将碎片灵感发展为结构化知识，并真正掌握它，从随手捕获的想法，到头脑风暴与深度研究，到体系化的项目规划与知识笔记，再到间隔复习与掌握度追踪。目标不只是建立知识库，而是帮你理解、内化和驾驭复杂知识。
 
+## 为什么开发 LifeOS？
+
+LifeOS 的出发点很直接：把学习工作流、技能、模板、提示词和记忆系统整合成一套可以直接落地的完整方案。你不需要自己从零拼装工具链，也不必在不同工具之间来回切换，初始化后即可开箱即用，并在真实使用中持续沉淀知识、流程与偏好。
+
 ## 核心功能
 
 ### 记忆系统
@@ -16,7 +20,7 @@ LifeOS 帮助你将碎片灵感发展为结构化知识，并真正掌握它，
 
 #### 项目级、技能绑定
 
-记忆系统围绕当前 Vault 中的 LifeOS 项目运行，只在 `today`、`project`、`research`、`knowledge`、`revise`、`archive` 等技能工作流里激活，并持续积累偏好、决策和上下文。
+记忆系统围绕当前 Vault 中的 LifeOS 项目运行，只在 `today`、`project`、`research`、`knowledge`、`revise`、`digest`、`archive` 等技能工作流里激活，并持续积累偏好、决策和上下文。
 
 #### 比全局记忆更可控
 
@@ -34,28 +38,28 @@ LifeOS 提供一组围绕学习过程设计的 Agent 技能，把“输入 ->
 
 - `/today`、`/brainstorm`、`/ask`：整理当天重点、澄清问题、快速展开想法
 - `/project`、`/research`、`/knowledge`：把主题推进成项目、研究报告和知识笔记
+- `/digest`：按主题订阅论文、RSS 与 Web 更新，自动生成结构化信息周报
 - `/read-pdf`、`/revise`、`/archive`：从资料提取、复习巩固，到定期归档收束
 
 ## 核心组件
 
 - **记忆系统**：项目级、技能绑定，为 AI Agent 提供 Vault 索引、会话记忆、上下文组装
 - **CLI 脚手架**：全局安装后使用 `lifeos init` 一键创建工作空间
-- **技能系统**：9 个 Agent 技能覆盖日记、项目、研究、知识整理、复习等工作流
+- **技能系统**：10 个 Agent 技能覆盖日记、项目、研究、信息周报、知识整理、复习等工作流
 - **模板 + 规范**：8 个结构化模板 + Frontmatter 规范，确保笔记一致性
 
 ## 快速开始
 
-目前仅在 macOS 上实际验证过 Agent CLI 流程；Agent GUI 端尚未系统测试，Windows 环境也还未验证，因此这两部分暂时不能保证体验完全一致。
+目前已确认 macOS 上的 Claude Code TUI / Codex TUI / OpenCode TUI，以及 Windows 上 OpenCode GUI 可以正常使用。其他 GUI 桌面端或平台/客户端组合尚未完成验证，实际兼容性仍需进一步测试。
 
 ### 前置要求
 
-开始前，请确保本机已安装 Obsidian，以及 Claude Code CLI / Codex CLI / OpenCode CLI 中至少一种。
+开始前，请确保本机已安装 Obsidian，以及 Claude Code TUI / Codex TUI / OpenCode TUI / OpenCode GUI 中至少一种。
 
 | 依赖 | 必须 | 用途 |
 |---|---|---|
-| **Node.js 18+** | 必须 | MCP Server 和 CLI 运行环境 |
-| **Git** | 必须 | Vault 版本控制（包括记忆数据库） |
-| **Python 3** | 必须 | PDF 提取（`/read-pdf` 技能） |
+| **Node.js 24.14.1+ (LTS)** | 必须 | MCP Server 和 CLI 运行环境 |
+| **Python 3** | 必须 | PDF 提取（`/read-pdf`）和信息周报抓取脚本（`/digest`） |
 
 `lifeos init` 会在创建工作空间前自动检查所有前置依赖。
 
@@ -101,7 +105,7 @@ lifeos --version                                       # 查看版本
 - 10 个顶层目录 + 嵌套子目录
 - 8 个 Markdown 模板
 - Frontmatter 规范
-- 9 个 AI 技能（按语言自动切换）
+- 10 个 AI 技能（按语言自动切换）
 - `CLAUDE.md` Agent 行为规范
 - `lifeos.yaml` 配置文件
 - Git 初始化 + `.gitignore`
@@ -139,6 +143,7 @@ lifeos upgrade ./my-vault --override
 | `/today` | 晨间规划：回顾昨日、规划今日 |
 | `/project` | 想法 → 结构化项目 |
 | `/research` | 主题 → 深度研究报告 |
+| `/digest` | 主题订阅 → 结构化信息周报 |
 | `/knowledge` | 书籍/论文 → 知识笔记 |
 | `/revise` | 生成复习题、批改、追踪掌握度 |
 | `/read-pdf` | PDF → 结构化笔记 |
@@ -176,8 +181,8 @@ lifeos upgrade ./my-vault --override
 - ✅ LifeOS 1.0 版本已初步可用
 - ✅ CLI 支持目录自定义
 - ✅ CLI upgrade 支持智能更新
-- ✅ macOS 端 Agent CLI 已测试
-- ☐ Agent GUI 和 Windows 测试与支持
+- ✅ 已完成 macOS 上 Claude Code TUI / Codex TUI / OpenCode TUI 与 Windows 上 OpenCode GUI 的验证
+- ✅ `/digest` 技能已支持中英双语信息周报与多来源论文抓取
 - ☐ 强化记忆系统精准性
 - ☐ 支持自定义技能
 - ☐ 支持自定义工作流

package/assets/lifeos-rules.en.md

@@ -6,7 +6,7 @@
 > The default directory names below come from presets; actual names follow the user's `lifeos.yaml` configuration.
 
 # Agent Behavior Guidelines — LifeOS
-`v1.0.2`
+`v1.1.0`
 
 You are the user's lifelong learning partner. Through **LifeOS**, help the user develop fragmented inspirations into structured knowledge and truly master it — from casually captured ideas, through brainstorming and deep research, to systematic project planning and knowledge notes, then spaced review and mastery tracking. The goal is not just building a knowledge base, but helping the user understand, internalize, and command complex knowledge.
 

package/assets/lifeos-rules.zh.md

@@ -6,7 +6,7 @@
 > 以下默认目录名来自 preset，实际名称以用户 Vault 中的 `lifeos.yaml` 为准。
 
 # Agent 行为规范 — LifeOS
-`v1.0.2`
+`v1.1.0`
 
 你是用户的终身学习伙伴。通过 **LifeOS**，帮助用户将碎片灵感发展为结构化知识，并真正掌握它——从随手捕获的想法，到头脑风暴与深度研究，到体系化的项目规划与知识笔记，再到间隔复习与掌握度追踪。目标不只是建立知识库，而是帮用户理解、内化和驾驭复杂知识。
 

package/assets/lifeos.yaml

@@ -24,6 +24,7 @@ subdirectories:
     templates: "模板"
     schema: "规范"
     memory: "记忆"
+    digest: "信息"
     prompts: "提示词"
     archive:
       projects: "归档/项目"

package/assets/skills/archive/SKILL.en.md

@@ -1,7 +1,7 @@
 ---
 name: archive
 description: "Scan and archive completed projects (status:done), consumed drafts (status:researched/projected/knowledged), completed plans (status: done), and diary entries older than the most recent 7 days, moving them into the unified archive structure and updating frontmatter. Never touches pending drafts, active plans, or the most recent 7 days of diary entries. Use this skill when the user wants to clean up the Vault, archive completed work, tidy up, or says '/archive'."
-version: 1.0.2
+version: 1.1.0
 dependencies:
   templates: []
   prompts: []

package/assets/skills/archive/SKILL.zh.md

@@ -1,7 +1,7 @@
 ---
 name: archive
 description: '扫描并归档已完成的项目（status:done）、已消化的草稿（status:researched/projected/knowledged）、已完成的计划（status: done）以及超过最近 7 天的日记，按归档规则移入统一归档目录并更新 frontmatter。不会触碰 pending 草稿、active 计划或最近 7 天的日记。当用户想清理 Vault、归档已完成的工作、整理库、或说"/archive"时使用此技能。'
-version: 1.0.2
+version: 1.1.0
 dependencies:
   templates: []
   prompts: []

package/assets/skills/ask/SKILL.en.md

@@ -1,7 +1,7 @@
 ---
 name: ask
 description: Quickly answer user questions, retrieving existing Vault notes as needed. Suitable for concept explanations, usage queries, Vault content lookups, PDF page-specific questions, and other single-turn Q&A scenarios. Complex questions will suggest upgrading to /brainstorm or /research.
-version: 1.0.2
+version: 1.1.0
 dependencies:
   templates:
     - path: "{system directory}/{templates subdirectory}/Draft_Template.md"

package/assets/skills/ask/SKILL.zh.md

@@ -1,7 +1,7 @@
 ---
 name: ask
 description: 快速回答用户问题，按需检索 Vault 已有笔记辅助作答。适用于概念解释、用法查询、Vault 内容检索、PDF 指定页面提问等单轮问答场景。当用户提出任何直接问题或说"/ask"时使用此技能。复杂问题会建议升级到 /brainstorm 或 /research。
-version: 1.0.2
+version: 1.1.0
 dependencies:
   templates:
     - path: "{系统目录}/{模板子目录}/Draft_Template.md"

package/assets/skills/brainstorm/SKILL.en.md

@@ -1,7 +1,7 @@
 ---
 name: brainstorm
 description: Explore and deepen user ideas through multi-turn interactive dialogue, using techniques like 5 Whys, What if, and Devil's Advocate to guide divergent thinking. Upon conclusion, the user can choose to create a project (invoke /project), organize wiki notes, or save as a draft. Suitable when the user wants to discuss an immature idea, needs divergent thinking, or wants to explore the feasibility of a direction.
-version: 1.0.2
+version: 1.1.0
 dependencies:
   templates:
     - path: "{system directory}/{templates subdirectory}/Wiki_Template.md"

package/assets/skills/brainstorm/SKILL.zh.md

@@ -1,7 +1,7 @@
 ---
 name: brainstorm
 description: 通过多轮交互式对话探索和深化用户的想法，使用 5 Whys、What if、Devil's Advocate 等思维技巧引导发散。结束后可选择创建项目（调用 /project）、整理为百科笔记、或保存为草稿。当用户想聊一个还不成熟的想法、需要发散思维、探索某个方向的可行性、或说"/brainstorm"时使用此技能。
-version: 1.0.2
+version: 1.1.0
 dependencies:
   templates:
     - path: "{系统目录}/{模板子目录}/Wiki_Template.md"

package/assets/skills/digest/SKILL.en.md

@@ -0,0 +1,212 @@
+---
+name: digest
+description: "A general weekly digest skill: on first use, guide the user through creating a topic config note (Paper Sources, RSS, Web search, and more), then automatically fetch updates and write a structured weekly digest into the drafts directory. Supports multiple topics with separate configs and separate outputs. Trigger when the user says '/digest', 'digest', or asks for a weekly digest."
+version: 1.1.0
+dependencies:
+  templates: []
+  prompts: []
+  schemas:
+    - path: "{system directory}/{schema subdirectory}/Frontmatter_Schema.md"
+  agents: []
+---
+
+> [!config]
+> Path references in this skill use logical names (for example `{drafts directory}`).
+> The Orchestrator resolves actual paths from `lifeos.yaml` and injects them into the context.
+> Path mappings:
+> - `{drafts directory}` → directories.drafts
+> - `{system directory}` → directories.system
+> - `{digest subdirectory}` → subdirectories.system.digest
+> - `{schema subdirectory}` → subdirectories.system.schema
+
+You are LifeOS's digest assistant. Your job is to collect recent updates for user-defined topics and produce structured weekly digest notes.
+
+**Language rule**: All replies, config notes, and generated digest files must be in English.
+
+# Workflow Overview
+
+This skill has two run modes:
+
+| Mode | Trigger | Behavior |
+|------|---------|----------|
+| **Setup mode** | No config files exist under `{system directory}/{digest subdirectory}/`, or the user explicitly asks for `setup` | Guide the user through creating a topic config note |
+| **Run mode** | A config file already exists | Read the config, fetch updates, and write a weekly digest |
+
+# Entry Routing
+
+Choose the mode from the user input:
+
+```text
+/digest              → Scan all .md configs under {system directory}/{digest subdirectory}/ and run each one
+                       If the directory is empty or missing → automatically enter Setup mode
+/digest <topic>      → Run only the named topic (matched by filename)
+                       If the file does not exist → automatically enter Setup mode seeded with that topic
+/digest setup        → Enter Setup mode and create a new topic config
+/digest setup <topic> → Enter Setup mode seeded with the given topic name
+```
+
+# Setup Mode
+
+Follow `references/setup-guide.md` for the conversation flow:
+
+1. **Define the topic**: ask what domain and subareas the user wants to track
+2. **Understand preferences**: academic vs industry, must-read sources, and focus areas
+3. **Generate config**: recommend sources and produce a full config note
+4. **User review**: write the config to `{system directory}/{digest subdirectory}/<TopicName>.md` and ask the user to review it in Obsidian
+
+The config note uses Markdown tables plus checkbox switches so the user can edit it directly in Obsidian:
+
+- toggle checkboxes to enable or disable modules
+- add or remove table rows to change concrete sources, including `Paper Sources`
+- edit the category table to reshape the digest structure
+
+See `references/config-parser.md` for the config note structure.
+
+# Run Mode
+
+Follow `references/run-pipeline.md` for the fetch pipeline.
+
+### Preflight
+
+1. Verify Python 3 is available: `python3 --version`
+2. Read and parse the config note according to `references/config-parser.md`
+
+### Execution Pipeline
+
+```text
+Phase 1: Parse config → structured data
+Phase 2: Fetch in parallel
+  ├─ Task A: RSS + paper sources → Python script (references/rss-arxiv-script.py)
+  ├─ Task B: Web search → WebSearch tool
+  ├─ Task C: HuggingFace papers → WebFetch
+  └─ Task D: GitHub Trending → WebFetch (optional)
+Phase 3: Merge and deduplicate → classify by category system
+Phase 4: Write digest → {drafts directory}/<TopicName>-MMDD-MMDD.md
+```
+
+### Python Script Invocation
+
+RSS + paper-source fetching runs through the parameterized Python helper. Parse the config, build
+the JSON payload, and pass it through stdin.
+
+The `Paper Sources` model now supports:
+
+- `arXiv`, `bioRxiv`, `medRxiv`, `ChemRxiv`, `SocArXiv`, `SSRN`
+- each row supplies `Source Type`, `Query`, `Scope`, and `Notes`
+- the helper normalizes each source through a dedicated adapter and returns structured errors per
+  source instead of failing the whole run
+- legacy `### arXiv Search` config blocks are still accepted and translated into `arXiv` sources so
+  older notes keep working
+- `SocArXiv` results may normalize to `OSF` landing pages when that is the source-hosted record
+- all paper-source adapters stay on a low-request budget: one primary request per source, bounded
+  retry only for transient failures, and no pagination
+
+For arXiv specifically:
+
+- configured arXiv queries must be English
+- the helper fetches recent category results first, then filters locally
+- if the official arXiv path fails, it may fall back to OpenAlex but only keep arXiv-mappable
+  papers
+
+Invoke it like this:
+
+```bash
+echo '<json_input>' | python3 .agents/skills/digest/references/rss-arxiv-script.py
+```
+
+JSON input shape:
+
+```json
+{
+  "language": "en",
+  "rss": {
+    "enabled": true,
+    "feeds": [{"name": "Source name", "url": "https://..."}]
+  },
+  "papers": {
+    "enabled": true,
+    "sources": [
+      {
+        "source_type": "arXiv",
+        "query": "\"llm agent\"",
+        "scope": "cs.AI",
+        "notes": "Core technical papers"
+      },
+      {
+        "source_type": "bioRxiv",
+        "query": "single-cell",
+        "scope": "Neuroscience",
+        "notes": "Biomedical preprints"
+      }
+    ]
+  },
+  "days": 7
+}
+```
+
+The helper returns `rss_articles`, normalized paper results, `stats`, and structured `errors`.
+
+### Digest Output
+
+Write the digest to `{drafts directory}/<TopicName>-MMDD-MMDD.md`:
+
+```yaml
+---
+title: "{Topic} Weekly Digest · YYYY-MM-DD ~ YYYY-MM-DD"
+type: draft
+created: "YYYY-MM-DD"
+status: pending
+tags: [digest, {topic-tag}, weekly-digest]
+aliases: []
+---
+```
+
+Organize the body using the configured category system. Each item should have a 1-2 sentence English summary plus the source link. Omit empty categories. End with a source list.
+
+# File Paths
+
+| Content | Path |
+|---------|------|
+| Topic config note | `{system directory}/{digest subdirectory}/<TopicName>.md` |
+| Weekly digest output | `{drafts directory}/<TopicName>-MMDD-MMDD.md` |
+| Parsing rules | `references/config-parser.md` |
+| Setup guide | `references/setup-guide.md` |
+| Run pipeline | `references/run-pipeline.md` |
+| Python helper | `references/rss-arxiv-script.py` |
+
+# Memory System Integration
+
+> Common protocols (file change notification, skill completion, session wrap-up) are documented in `_shared/memory-protocol.md`. Only digest-specific behavior is listed here.
+
+### File Change Notification
+
+After the digest file is written into the Vault, call:
+
+```text
+memory_notify(file_path="{drafts directory}/<TopicName>-MMDD-MMDD.md")
+```
+
+### Skill Completion
+
+```text
+memory_skill_complete(
+  skill_name="digest",
+  summary="Generated {topic} weekly digest MMDD-MMDD",
+  related_files=["{drafts directory}/<TopicName>-MMDD-MMDD.md"],
+  scope="digest",
+  refresh_targets=["TaskBoard", "UserProfile"]
+)
+```
+
+### Setup Mode Completion
+
+After creating the config note, also record a decision:
+
+```text
+memory_log(
+  entry_type="decision",
+  summary="Created {topic} digest subscription config",
+  importance=2,
+  scope="digest"
+)
+```