boss-briefing

Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals

6 stars

Best use case

boss-briefing is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals

Teams using boss-briefing should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/boss-briefing/SKILL.md --create-dirs "https://raw.githubusercontent.com/sehoon787/my-claude/main/skills/core/boss-briefing/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/boss-briefing/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How boss-briefing Compares

Feature / Agentboss-briefingStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# boss-briefing

Vault health check skill. Analyzes workflow patterns, syncs profile, recovers from session gaps, and proposes persona rules based on temporal agent call sequences.

> **Relationship with other skills:**
> - `briefing-vault` handles vault templates and initialization
> - `boss-briefing` handles sync, analysis, and pattern detection
> - `stop-profile-update.js` still runs as a fallback if this skill was not invoked during the session

## Steps

Execute all 9 steps in order. If any step fails due to missing data, log the issue and continue to the next step.

### Step 1: Read state.json

Read `.briefing/state.json` to get session metadata:
- `date` — last session date
- `workCounter` — file edit count this session
- `sessionMessageCount` — user message count this session
- `lastVaultSync` — ISO timestamp of last /boss-briefing run
- `sessionStartHead` — git HEAD or `YYYY-MM-DD:cwd` identifier

If state.json does not exist or is empty, use defaults: `{ date: "", workCounter: 0, sessionMessageCount: 0, lastVaultSync: "", sessionStartHead: "" }`.

### Step 2: Previous session gap detection

Compare the `date` field from state.json with today's date.

If the gap is >= 1 day:
1. Scan `.briefing/sessions/` for the most recent session file (by filename date prefix)
2. Report the gap: "Last session was on YYYY-MM-DD (N days ago). Topic: <extracted from filename>"
3. Read the most recent session file and provide a brief recovery summary of what was last worked on

If gap is 0 (same day), skip this step.

### Step 3: Analyze agent-log.jsonl sequences

Read `.briefing/agents/agent-log.jsonl`. Parse all entries from the last 30 days.

Group entries by date. For each day, extract the ordered sequence of `agent_type` values.

**Frequency patterns:** Identify any `agent_type` that appears >= 3 times in the last 7 days.

**Sequence patterns:** Look for recurring ordered sub-sequences (length >= 2) that appear in >= 2 different sessions/days. Examples:
- "explore → executor" (seen 4 times)
- "explore → executor → code-reviewer" (seen 3 times)
- "planner → executor → code-reviewer" (seen 2 times)

Report both frequency and sequence patterns.

### Step 4: Update profile.md

Rewrite `.briefing/persona/profile.md` with:

```yaml
---
date: YYYY-MM-DD
type: persona
version: 2
session_count: <incremented count>
---
```

Sections to include:

**## Philosophy** — Infer work style from data. Only populate if >= 10 agent calls exist in the last 30 days. Examples: "Prefers thorough exploration before implementation", "Review-heavy workflow with security focus".

**## Workflow Patterns** — Total agent calls (30d), most active agent type, average calls per session.

**## Workflow Sequences** — Detected temporal patterns from Step 3. Format: "Explore → executor → code-reviewer (seen 3 times)". This section is new and distinguishes boss-briefing from the old profile update.

**## Agent Affinity** — Percentage breakdown by `agent_type` over the 30-day rolling window.

**## Active Persona Rules** — List all `.md` files from `.briefing/persona/rules/` directory. Format: `- rule-name: <first line of description>`.

**## History** — Append a one-line entry every 5th session (based on `session_count % 5 === 0`). Format: "Session N (YYYY-MM-DD): <brief summary>".

**Session count idempotency:** If `sessionStartHead` is empty (no git repo), use `YYYY-MM-DD:cwd` as the session identifier to avoid double-counting.

### Step 5: Propose persona rules

For each detected SEQUENCE pattern from Step 3 that appears >= 2 times:
1. Draft a rule proposal explaining the pattern and suggesting it be formalized
2. Present the proposal to the user using conversation (ask for confirmation)
3. If confirmed, write the rule to `.briefing/persona/rules/workflow-<slug>.md`:

```yaml
---
date: YYYY-MM-DD
type: persona-rule
source: boss-briefing
pattern: "<sequence description>"
occurrences: <count>
---
```

Followed by a description of the workflow pattern and when it should be applied.

If no new sequence patterns are detected, or all existing patterns already have rules, skip this step.

### Step 6: Validate session summary

Check `.briefing/sessions/` for files matching `YYYY-MM-DD-*.md` (today's date, excluding files containing `-auto`).

If no matching file exists AND either:
- `workCounter > 0`, or
- `sessionMessageCount >= 3`

Then warn the user: "No session summary found for today. Consider writing .briefing/sessions/YYYY-MM-DD-<topic>.md before ending the session."

### Step 7: Sync INDEX.md

Read all files from these directories:
- `.briefing/sessions/`
- `.briefing/decisions/`
- `.briefing/learnings/`

Rebuild these sections in `.briefing/INDEX.md`:
- `## Recent Sessions` — newest 5 files with `[[wiki-links]]`
- `## Recent Decisions` — newest 5 files with `[[wiki-links]]`
- `## Recent Learnings` — newest 5 files with `[[wiki-links]]`

Update the `date` field in INDEX.md frontmatter to today.

Preserve any other existing sections (Overview, Open Questions, Key Links).

### Step 7b: Review Auto-Archived Files

Scan `.briefing/archives/` for files recently moved by the session-end hook (files older than 30 days that were automatically moved from `sessions/`, `decisions/`, and `learnings/`).

- Skip files with `-auto` in the name
- If recently archived files exist, list them so the user is aware of what was auto-archived

### Step 7c: Suggest Wiki Pages

Review the session's prompt history and changed files for recurring concepts:

- If a concept/keyword appears 3+ times across prompts and no `.briefing/wiki/<concept>.md` exists, suggest creating one
- Wiki page format: Definition → Key Facts → Related links
- Template available at `.briefing/wiki/_schema.md`

### Step 8: Record lastVaultSync

Read `.briefing/state.json`, merge in `{ lastVaultSync: "<current ISO timestamp>" }`, and write back.

This timestamp is checked by hooks to determine whether /boss-briefing has been run today.

### Step 9: No-git-repo graceful handling

This is not a separate step but a cross-cutting concern for all steps above:
- If `sessionStartHead` is empty, use `YYYY-MM-DD:cwd` format for session identification
- Do NOT fail or error on missing `.git` directory
- All git-dependent features should degrade gracefully

Related Skills

briefing-vault

6
from sehoon787/my-claude

Initialize, manage, and search the per-project .briefing/ vault. Obsidian-compatible persistent knowledge base.

boss-advanced

6
from sehoon787/my-claude

Advanced Boss orchestration patterns — Agent Teams leadership, 6-section delegation template, Skill vs Agent conflict resolution, Guardian pattern, and AI-slop detection.

gstack-sprint

6
from sehoon787/my-claude

3-Phase Sprint workflow — design → execute → review with user interaction at decision points

daily-briefing

10671
from anthropics/knowledge-work-plugins

Start your day with a prioritized sales briefing. Works standalone when you tell me your meetings and priorities, supercharged when you connect your calendar, CRM, and email. Trigger with "morning briefing", "daily brief", "what's on my plate today", "prep my day", or "start my day".

meeting-briefing

10671
from anthropics/knowledge-work-plugins

Prepare structured briefings for meetings with legal relevance and track resulting action items. Use when preparing for contract negotiations, board meetings, compliance reviews, or any meeting where legal context, background research, or action tracking is needed.

daily-briefing-hub

3891
from openclaw/skills

All-in-one daily briefing that combines Google Calendar events, Gmail/Outlook email highlights, weather forecast, GitHub PR and CI status, Hacker News and RSS feeds, and Todoist/ClickUp/Linear tasks into a single prioritized morning summary delivered via Telegram, Slack, WhatsApp, or Discord. Use this skill for: morning briefing, daily digest, daily summary, daily standup prep, "what's on my plate today", "brief me", "what did I miss", end-of-day recap, personalized news digest, schedule overview, inbox summary, daily notification, recurring morning update via cron, or any request to see a combined overview of calendar plus email plus tasks plus news. This is your AI chief of staff that replaces checking 6 apps every morning. Works with whatever tools you have configured — skips what's missing, uses what's available.

fulcra-morning-briefing

3891
from openclaw/skills

Compose a personalized morning briefing using sleep, biometrics, calendar, and weather data from the Fulcra Life API. Adapts tone and detail to how your human actually slept.

bosszp

3891
from openclaw/skills

BOSS直聘岗位数据爬虫 + 可视化分析工具。使用 Scrapy 爬取职位数据,存入 MySQL,用 Flask + Highcharts 生成可视化报告。当用户需要批量采集 BOSS直聘 职位数据、分析薪资分布、公司分布、岗位要求,或需要生成可视化报告时触发。

boss-cli

3891
from openclaw/skills

BOSS直聘 CLI 工具,支持职位搜索、求职申请管理、聊天、发送招呼等功能。通过逆向 BOSS直聘 API 实现,支持多城市、多筛选条件。当用户需要搜索 BOSS直聘 上的职位、查看公司信息、管理求职申请、联系 HR 时触发。

dependency-upgrade-briefing

3891
from openclaw/skills

解释依赖升级的收益、风险、回滚方案与对业务的影响。;use for dependencies, upgrade, risk workflows;do not use for 伪造上游 changelog, 替代兼容性测试.

Daily Briefing

3891
from openclaw/skills

Generates a warm, compact daily briefing with weather, calendar, reminders, birthdays, and important emails for cron or chat delivery.

morning-briefing

533
from sundial-org/awesome-openclaw-skills

Generate personalized morning report with today's reminders, Notion tasks (undone), and vault storage. Use when user asks for morning briefing, daily summary, or &quot;today's plan&quot;. Pulls from Apple Reminders (as calendar proxy) and Notion tasks DB (set NOTION_TASKS_DB or specify DB ID).