
executive
Strategic analysis, work prioritization, pattern recognition, and productivity reviews for the secretary plugin
- Installs
- 68
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/mwguerra/claude-code-plugins --skill executive- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads executive automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Executive Skill
Analyze productivity, prioritize work, detect patterns, and generate strategic recommendations.
When to Use
- User asks "What's most important?" or "What should I focus on?"
- User asks "How am I doing?" or "How productive have I been?"
- User wants productivity analysis (daily, weekly, monthly)
- Generating weekly or monthly strategic reviews
- Detecting bottlenecks, stagnation, or work distribution issues
- Recommending focus areas or schedule adjustments
- User asks about patterns or trends in their work
- User wants goal progress assessment or risk analysis
Database Location
SECRETARY_DB_PATH="$HOME/.claude/secretary/secretary.db"
Work Prioritization
Priority Scoring
Score each commitment by multiple weighted factors:
SELECT
c.id, c.title, c.due_date, c.priority, c.project, c.stakeholder,
-- Urgency (0-100)
CASE
WHEN c.due_date < date('now') THEN 100
WHEN c.due_date = date('now') THEN 80
WHEN c.due_date <= date('now', '+2 days') THEN 60
WHEN c.due_date <= date('now', '+7 days') THEN 40
ELSE 20
END as urgency,
-- Priority weight (0-40)
CASE c.priority
WHEN 'critical' THEN 40
WHEN 'high' THEN 30
WHEN 'medium' THEN 20
ELSE 10
END as priority_score,
-- Stakeholder factor (0-20)
CASE WHEN c.stakeholder IS NOT NULL THEN 20 ELSE 0 END as stakeholder_score,
-- Deferral penalty (-10 per deferral)
-10 * c.deferred_count as deferral_penalty
FROM commitments c
WHERE c.status IN ('pending', 'in_progress')
ORDER BY (urgency + priority_score + stakeholder_score + deferral_penalty) DESC;
Eisenhower Matrix
Categorize work:
URGENT + IMPORTANT -> Do First
NOT URGENT + IMPORTANT -> Schedule
URGENT + NOT IMPORTANT -> Delegate
NOT URGENT + NOT IMPORTANT -> Eliminate
Productivity Analysis
Session Metrics
-- Daily summary (last 30 days)
SELECT
date(started_at) as date,
COUNT(*) as sessions,
SUM(duration_seconds) / 3600.0 as hours,
AVG(duration_seconds) / 60.0 as avg_minutes,
COUNT(DISTINCT project) as projects
FROM sessions
WHERE started_at >= datetime('now', '-30 days') AND status = 'completed'
GROUP BY date(started_at)
ORDER BY date DESC;
Completion Rates
-- Weekly completion rate (last 90 days)
SELECT
strftime('%Y-%W', created_at) as week,
COUNT(*) as created,
SUM(CASE WHEN status = 'completed' THEN 1 ELSE 0 END) as completed,
ROUND(100.0 * SUM(CASE WHEN status = 'completed' THEN 1 ELSE 0 END) / COUNT(*), 1) as rate,
SUM(CASE WHEN status = 'deferred' THEN 1 ELSE 0 END) as deferred,
SUM(CASE WHEN status = 'canceled' THEN 1 ELSE 0 END) as canceled
FROM commitments
WHERE created_at >= datetime('now', '-90 days')
GROUP BY week
ORDER BY week DESC;
Time Distribution
-- Where is time going? (last 7 days)
SELECT
project,
SUM(duration_seconds) / 3600.0 as hours,
ROUND(100.0 * SUM(duration_seconds) / (
SELECT SUM(duration_seconds) FROM sessions
WHERE started_at >= datetime('now', '-7 days') AND status = 'completed'
), 1) as percentage,
COUNT(*) as sessions
FROM sessions
WHERE started_at >= datetime('now', '-7 days') AND status = 'completed'
GROUP BY project
ORDER BY hours DESC;
Decision Velocity
-- How often decisions are being made
SELECT
strftime('%Y-%W', created_at) as week,
COUNT(*) as total,
SUM(CASE WHEN category = 'architecture' THEN 1 ELSE 0 END) as architecture,
SUM(CASE WHEN category = 'technology' THEN 1 ELSE 0 END) as technology,
SUM(CASE WHEN category = 'process' THEN 1 ELSE 0 END) as process,
SUM(CASE WHEN category = 'design' THEN 1 ELSE 0 END) as design
FROM decisions
WHERE created_at >= datetime('now', '-90 days')
GROUP BY week
ORDER BY week DESC;
Goal Tracking
Progress Velocity
SELECT
g.id, g.title, g.goal_type, g.progress_percentage,
g.target_date, g.target_value, g.current_value, g.target_unit,
-- Days remaining
ROUND(julianday(g.target_date) - julianday('now'), 0) as days_remaining,
-- Required daily progress
ROUND((100 - g.progress_percentage) / NULLIF(julianday(g.target_date) - julianday('now'), 0), 2) as required_daily,
-- Risk status
CASE
WHEN g.target_date < date('now') AND g.progress_percentage < 100 THEN 'overdue'
WHEN (100 - g.progress_percentage) / NULLIF(julianday(g.target_date) - julianday('now'), 0) > 5 THEN 'at_risk'
WHEN (100 - g.progress_percentage) / NULLIF(julianday(g.target_date) - julianday('now'), 0) > 2 THEN 'needs_attention'
ELSE 'on_track'
END as risk_status
FROM goals g
WHERE g.status = 'active' AND g.target_date IS NOT NULL
ORDER BY days_remaining ASC;
Bottleneck Detection
Long-Pending Items
SELECT id, title, priority, project,
ROUND(julianday('now') - julianday(created_at), 0) as days_pending
FROM commitments
WHERE status = 'pending'
ORDER BY days_pending DESC
LIMIT 10;
Frequently Deferred
SELECT id, title, deferred_count, priority, project
FROM commitments
WHERE deferred_count >= 2
AND status NOT IN ('completed', 'canceled')
ORDER BY deferred_count DESC;
Blocked Work
-- Items that have been in_progress for a long time
SELECT id, title, priority, project,
ROUND(julianday('now') - julianday(updated_at), 0) as days_stale
FROM commitments
WHERE status = 'in_progress'
AND updated_at < datetime('now', '-7 days')
ORDER BY days_stale DESC;
Pattern Integration
Use detected patterns to inform recommendations:
SELECT id, title, pattern_type, category, confidence,
evidence_count, recommendations, frequency
FROM patterns
WHERE status = 'active' AND confidence >= 0.6
ORDER BY confidence DESC, evidence_count DESC;
Apply insights:
- Productivity timing - Schedule important work during peak hours
- Work style - Recommend process improvements
- Completion patterns - Adjust estimation and scheduling
- Context switching - Recommend focus blocks
- Deferral patterns - Flag items that need attention or elimination
Output Guidelines
Priority Report
# Work Priorities
## Do Today
1. **[C-0001] Fix auth bug** - Overdue, critical
- Stakeholder: Product team
- Estimated: 2 hours
2. **[C-0003] Review PR** - Due today
- Impact: Team velocity
## Schedule This Week
3. **[G-0002] API integration** - Goal at risk (60%)
- Required: +8%/day
4. **[C-0005] Update docs** - Low urgency, high value
## Consider Dropping
- [C-0010] Research task - 3x deferred, low impact
Strategic Review
# Weekly Review
## Metrics
| Metric | This Week | Trend |
|--------|-----------|-------|
| Sessions | 18 | +20% |
| Hours | 24h | +15% |
| Completed | 11 | +37% |
| Decisions | 5 | stable |
## Concerns
1. Carryover growing - 8 items >2 weeks
2. Goal G-0003 at risk - needs 20%/week
3. Context switching - 5 projects in 7 days
## Recommendations
1. Clear backlog tomorrow (2h)
2. Documentation sprint Wednesday
3. Weekly planning Friday
## Wins
- Morning productivity pattern continues
- Test coverage improving steadily
Review Types
Weekly Focus
- Top 3 priorities for the week
- Carryover items analysis
- Goal trajectory check
- Time allocation review
- Pattern-based scheduling suggestions
Monthly Strategy
- Progress on major objectives
- Decision patterns analysis (categories, reversal rate)
- Productivity trends (velocity, efficiency)
- Knowledge graph growth
- Recommendation adjustments
Recommendation Categories
- Immediate Actions - What to do right now
- Scheduling - When to do what, based on data
- Process Changes - How to improve workflows
- Risk Mitigation - What to watch for
- Celebration - What went well (motivation matters)
Error Handling
- Handle empty datasets gracefully ("Not enough data yet for analysis")
- Provide default recommendations when data is sparse
- Note when analysis is based on limited data
- Degrade gracefully if specific tables have no rows
Related Commands
/secretary:review- Generate weekly or monthly review/secretary:patterns- View detected work patterns/secretary:goals- Manage and track goals/secretary:status- Full dashboard with metrics/secretary:priorities- Ranked priority list
FAQ
What does the executive skill do?
Strategic analysis, work prioritization, pattern recognition, and productivity reviews for the secretary plugin
How do I install executive?
Run npx skills add https://github.com/mwguerra/claude-code-plugins --skill executive in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/executive/ (personal) or .claude/skills/executive/ (project).
Which AI agents can use executive?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is executive safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains executive?
It is published by mwguerra in mwguerra/claude-code-plugins. It has 68 recorded installs.
More from mwguerra/claude-code-plugins
filament-resource
mwguerra/claude-code-plugins
Generate FilamentPHP v4 resources with form, table, relation managers, and actions
resource
mwguerra/claude-code-plugins
Generate FilamentPHP v4 resources with form, table, relation managers, and actions
forms
mwguerra/claude-code-plugins
Create FilamentPHP v4 forms with fields, validation, sections, tabs, and relationships
widgets
mwguerra/claude-code-plugins
Create FilamentPHP v4 dashboard widgets - stats overviews, charts, and custom components
Popular productivity & automation skills
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
lark-doc
open.feishu.cn
飞书云文档(Docx / Wiki)内容操作:读取、创建、编辑文档,插入或下载图片附件,以及操作思维笔记。用户提供文档 URL/token(包括 doubao.com 的 /docx/、/wiki/)时使用;按 URL 路径/token 而非域名路由;/page/ 是妙搭应用,非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive;随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格(Base)操作:建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式(BaseApp/AppMode 页面与组件)、Workspace 目录、workflow、角色权限、模板中心(多维表格模板分类/列表/搜索);遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps;文件导入/导出转 lark-drive,认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走 lark-sheets/lark-base)、知识空间节点/成员管理(走 lark-wiki)、原生 Markdown 文件读写/patch/diff(走 lark-markdown)。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯:收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片(Interactive Card)、监听卡片按钮回调(card.action.trigger)。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶(添加/移除/查询置顶会话)、管理标签数据、处理卡片回调时使用。