agentleFS
Duckz289Duckz289/Pipeline-to-proposal-Plugin-STANDARD/skills/weekly-summary/SKILL.md

weekly-summary

Skill2 starsChanged 4 months agoMITView on GitHub

Summarises the week from local deal memory: who was contacted, who replied, who needs a follow-up, which deals are stuck. Triggered by "tổng kết tuần", "tuần này thế nào", "deal nào cần follow", "weekly summary", "review my pipeline", "what needs attention".

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read <DATA>/deals/, <DATA>/follow-ups.md, and <DATA>/feedback.md, then return a short table.

    line 11
  2. Distinctive:

    Keep it tight and readable.

    line 14
  3. Very specific:

    Read deals/index.md for active deals.

    line 18
  4. Very specific:

    Read feedback.md filtered to the period asked for (default: last 7 days).

    line 19
  5. Very specific:

    Read follow-ups.md for overdue and upcoming items.

    line 20
  6. Distinctive:

    Never fabricate a report to look useful.

    line 56
  7. Distinctive:

    Write long. It must fit on a phone screen.

    line 63
  8. Very specific:

    If the user asks for a month or quarter, also read the archive files per ${CLAUDE_PLUGIN_ROOT}/policies/state-management.md.

    line 67

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Weekly summary

Read <DATA>/deals/, <DATA>/follow-ups.md, and <DATA>/feedback.md, then return a short table.

This is the thing a salesperson wants to screenshot — for their manager, their team, themselves. Keep it tight and readable.

How

  1. Read deals/index.md for active deals.
  2. Read feedback.md filtered to the period asked for (default: last 7 days).
  3. Read follow-ups.md for overdue and upcoming items.
  4. Count and group. Never invent numbers — only count what is actually in the files.

Output

### Tuần này (24/07 – 30/07)

- Đã liên hệ: 8 công ty
- Có phản hồi: 3
- Đã hẹn gặp: 1
- Đang chờ trả lời: 4

### Cần làm ngay
- [Quá hạn 2 ngày] ABC Logistics — follow-up proposal
- [Hôm nay] Minh An — gửi báo giá đã sửa

### Đang kẹt
- FPT — im lặng 12 ngày sau demo. Nên gửi break-up hoặc hẹn lại tháng sau.

### Sắp tới
- 02/08 — DEF Corp — gọi lần 2

Drop any section with no data. Nothing overdue → no "needs attention" section. Headings follow the user's language.

When there is no data

<DATA> is empty or has no deals:

Mình chưa có deal nào trong bộ nhớ. Bắt đầu bằng cách viết email cho một khách,
rồi báo mình kết quả — từ tuần sau mình sẽ tổng kết được.

Never fabricate a report to look useful.

Never

  • Count anything not in the files.
  • Derive a reply rate when the user has not reported enough outcomes.
  • Mention opened emails or clicked links — there is no tracking.
  • Write long. It must fit on a phone screen.

Other periods

If the user asks for a month or quarter, also read the archive files per ${CLAUDE_PLUGIN_ROOT}/policies/state-management.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.