email-draft
Use when the user asks to draft, polish, translate, or reply to an email. Produces a clean draft with subject line, greeting, body, and sign-off, plus a…
Use when the user asks for a weekly / monthly status report, project update, individual or team progress summary. Produces a tight, scannable update with what shipped, what's in flight, what's blocked, and metrics.
$ npx -y skills add shiwenwen/hope-agent --skill status-report --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/status-reportContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when the user asks for a weekly / monthly status report, project update, individual or team progress summary. Produces a tight, scannable update with what shipped, what's in flight, what's blocked, and metrics.
name: status-report
description: Use when the user asks for a weekly / monthly status report, project update, individual or team progress summary. Produces a tight, scannable update with what shipped, what's in flight, what's blocked, and metrics.
version: 1.0.0
author: Hope Agent
license: MIT
metadata:
hermes:
tags: [office, status, reporting, productivity, communication]
related_skills: [meeting-notes, email-draft]Trigger phrases: "weekly update", "monthly report", "status report", "project update", "1:1 prep", "周报", "月报", "工作汇报".
Match the cadence implied by the request:
This skill optimizes for **the reader's time, not yours**. A status report is read in 60 seconds or skipped.
# <Your Name / Team Name> — Week of <YYYY-MM-DD> ## TL;DR <2 sentences. What's the state of the world? Use plain English.> ## ✅ Shipped This Week - <bullet — outcome, not activity. Link if relevant.> - <bullet — outcome.> ## 🔄 In Flight - <project> — <what stage, expected ship date> - <project> — <what stage, expected ship date> ## ⚠️ Risks / Blockers - <risk> — <impact + what's needed to unblock> ## 📊 Metrics (optional) | Metric | This Week | Last Week | Δ | |--------|-----------|-----------|---| | <name> | <value> | <value> | <±> | ## 📅 Next Week - <top 3 priorities, in order>
1. **Gather inputs** via `recall_memory` (if scope=session/project) and `ask_user_question`:
2. **Categorize ruthlessly** — every bullet must fit exactly one bucket:
3. **Write outcomes, not activity**:
4. **Quantify when possible**:
5. **Sequence priorities by impact** — the first item in "Next Week" should be the highest-leverage thing. Don't bury it.
6. **Save state** — offer to save the report to memory or to compose an email via `email-draft`:
Save this status to memory for next week's diff? Send to <manager> as an email?
- Yesterday: <one outcome> - Today: <one focus> - Blockers: <none / specific ask>
## 🎯 Themes - <pattern across the 4 weeks: what got better, what's recurring> ## 📈 Trends | Metric | Month-over-Month | Notes | |--------|------------------|-------| | ... | ... | ... | ## 🔭 Looking Ahead (next month) - <strategic priorities, not tactical tasks>
# Q<N> Review — <Team> ## Goals Status | OKR | Target | Actual | Status | Confidence | |-----|--------|--------|--------|------------| | <name> | <metric> | <metric> | <On Track / At Risk / Off Track> | <0.0–1.0> | ## What Went Well - <pattern, not single incident> ## What Didn't - <honest pattern, with the lesson> ## Q<N+1> Bets - <top 3 priorities for next quarter, with rationale>
| Audience | Adjust | |----------|--------| | Direct manager | Include risks honestly; manager wants to help unblock | | Cross-functional team | More context; less internal jargon | | Company all-hands | Outcomes only; cut planning details | | Skip-level / exec | TL;DR + 3 bullets total; skip metrics unless they're 1-2 headline numbers | | External (board, investors) | Headline outcomes + roadmap; never blockers without solutions |
| Mistake | Fix | |---|---| | Listing every Jira ticket | Group into ≤5 outcomes, name them | | "Working on …" everywhere | Pick a stage: design / implementation / review / shipped | | Burying bad news | Lead with "TL;DR: <project> slipping by 1 week, here's why" | | Vague metrics ("better", "faster") | Specific numbers or skip the metric | | Same priorities every week | Either reframe progress or admit it's stuck | | No "next week" section | Always have one — shows you're proactive, not just reactive | | Word-soup TL;DR | Two sentences max. If you can't compress, you don't understand the state. |
Input: "Write my weekly update — I shipped the auth refactor PR, I'm finishing the dashboard search feature, the embedding migration is blocked on infra, and I want to start the i18n rewrite next week."
Output:
# Alice — Week of 2026-04-25 ## TL;DR Shipped auth refactor; dashboard search done by Friday. Embedding migration blo
🦭 会记忆、能持续推进目标、会动态编排多 Agent 的跨端桌面 AI 助手,也可服务化常驻 NAS / 云端 | A cross-device desktop AI agent with memory, autonomous goals, dynamic workflows, and headless deployment
Repo: shiwenwen/hope-agent
Use when the user asks to draft, polish, translate, or reply to an email. Produces a clean draft with subject line, greeting, body, and sign-off, plus a…
Use when the user mentions 飞书 / Feishu / Lark workspace operations: docx (云文档) read/write, bitable (多维表格) records / views / dashboards, drive (云盘)…
Hope Agent browser automation — the standard `status → tabs → snapshot → act` loop, stale-ref recovery rules, and what to do when login / 2FA / captcha /…
Hope-native review of uncommitted, staged, commit, branch, or PR changes: discover concrete regressions, independently verify candidates, and report actionable…
Hope-native baseline for implementing, fixing, refactoring, and maintaining code: inspect the repository first, protect user changes, keep scope narrow, and…
Hope-native implementation planning for non-trivial code changes: ground the plan in repository evidence, order dependencies, name critical files and risks,…