agentleFS
oschinaoschina/gitee-agent-skills/skills/daily-digest/SKILL.md

daily-digest

Skill4 starsChanged 7 months agoMITView on GitHub

Use this skill when the user asks for a daily summary, today's to-dos, "what's on my plate today", "daily digest", "daily-digest", "show my notifications", "pending PRs and issues". Requires Gitee MCP Server to be configured.

17 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

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Use get_user_info to retrieve the currently authenticated user's information, used for filtering (e.g., only show tasks assigned to me).

    line 25
  2. Very specific:

    Use list_user_notifications to get recent notifications:

    line 29
  3. Distinctive:

    If there is nothing pending:

    line 101
  4. Distinctive:

    If there are many repositories, prioritize time-sensitive items

    line 113

“Common” is measured: kept by at least 6 in 10 of the 11 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

Note: If you have mcporter installed locally, you should use mcporter to invoke the MCP tool instead of directly calling the MCP tool. The mcporter CLI provides a more convenient interface and better error handling.

Daily Digest via Gitee MCP

Aggregate unread notifications, pending PRs, and open Issues from Gitee to generate a daily work summary.

Prerequisites

  • Gitee MCP Server configured (tools: list_user_notifications, list_repo_pulls, list_repo_issues, get_user_info)
  • Optional: user can provide a list of repositories to focus on (otherwise inferred from notifications)

Steps

Step 1: Get Current User Info

Use get_user_info to retrieve the currently authenticated user's information, used for filtering (e.g., only show tasks assigned to me).

Step 2: Fetch Unread Notifications

Use list_user_notifications to get recent notifications:

  • Filter for unread notifications
  • Categorize by type: PR-related, Issue-related, @mentions, comment replies

Step 3: Fetch Pending PRs

For repositories the user cares about (extracted from notifications or specified by the user), use list_repo_pulls:

  • Filter for state=open PRs
  • Focus on:
    • PRs assigned to me for review
    • My own PRs waiting for review
    • PRs with new comments that need a reply

Step 4: Fetch Open Issues

Use list_repo_issues:

  • Filter for state=open Issues assigned to me
  • Filter for open Issues I created

Step 5: Generate Daily Digest

# Daily Work Digest
📅 [date]  👤 [username]

---

## 📬 Unread Notifications ([N])

### @Mentions
- [repo] [Issue/PR title] - [notification summary]

### PR Comments
- [repo] PR #N [title] - [comment summary]

### Issue Updates
- [repo] Issue #N [title] - [update summary]

---

## 🔀 Pending PRs

### Needs My Review
| Repo | PR | Author | Updated |
|------|----|--------|---------|
| [repo] | #N [title] | [@author] | [time] |

### My PRs Awaiting Review
| Repo | PR | Status | Updated |
|------|----|--------|---------|
| [repo] | #N [title] | [Awaiting review / Has new comments] | [time] |

---

## 📋 My Open Issues

| Repo | Issue | Priority | Status |
|------|-------|----------|--------|
| [repo] | #N [title] | P1 | In progress |

---

## Today's Suggestions

**Handle first:**
1. [Most urgent item, e.g., a review request blocking someone else]
2. [Second priority item]

**Can defer:**
- [Low priority items]

If there is nothing pending:

# Daily Work Digest
📅 [date]

All clear! No pending PRs, Issues, or unread notifications.

Notes

  • The digest focuses on information aggregation, not deep analysis
  • If there are many repositories, prioritize time-sensitive items
  • Notifications may span multiple repositories — group them clearly

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.