agentleFS
oschinaoschina/gitee-agent-skills/skills/stale-pr-reminder/SKILL.md

stale-pr-reminder

Skill4 starsChanged 7 months agoMITView on GitHub

Use this skill when the user wants to check for stale PRs, "find old pull requests", "stale PRs", "PRs needing attention", or wants to identify pull requests that have been inactive for too long. This skill scans repositories for PRs that need action and generates a prioritized reminder report. Requires Gitee MCP Server to be configured.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Call list_repo_pulls to retrieve all open PRs:

    line 39
  2. Very specific:

    Call list_comments (resource_type: pull) to check review activity:

    line 68
  3. Distinctive:

    No code execution needed. The AI can parse timestamps directly.

    line 78
  4. Very specific:

    Check if mergeable: false (has conflicts)

    line 88
  5. Distinctive:

    Create a grouped report with links:

    line 100

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Stale PR Reminder

Scan repositories for stale Pull Requests and generate a prioritized action report.

What is a "Stale PR"?

A stale PR is a Pull Request that:

  • Has been open for a long time without updates
  • Has not received reviewer attention
  • Has merge conflicts that haven't been resolved

Staleness Levels

LevelAgeAction
🔴 Critical> 28 daysClose or rework
🟠 Severe> 14 days no updatePing author
🟡 Moderate> 7 days no reviewAssign reviewer
🟢 Mild> 3 days no activityMonitor
✅ Fresh< 3 daysNo action

Steps

Step 1: Fetch Open PRs

Call list_repo_pulls to retrieve all open PRs:

INPUT:
  - owner: repository owner
  - repo: repository name
  - state: "open"
  - sort: "created"
  - direction: "asc"
  - per_page: 100

Step 2: Get PR Details

For each PR, call get_pull_detail:

EXTRACT:
  - number: PR number
  - title: PR title
  - user.login: author username
  - created_at: creation timestamp
  - updated_at: last update timestamp
  - mergeable: false = has conflicts
  - draft: is draft PR

Step 3: Get Comments (Optional)

Call list_comments (resource_type: pull) to check review activity:

ANALYZE:
  - has_reviewer_comments: any comment from non-author
  - last_comment_date: most recent comment timestamp

Step 4: Calculate Staleness

No code execution needed. The AI can parse timestamps directly.

Today's date: 2026-03-17

For each PR:

  1. Parse created_at (format: YYYY-MM-DDTHH:MM:SSZ, e.g., 2026-01-15T10:30:00Z)
  2. Parse updated_at the same way
  3. Calculate days between created_at and today (2026-03-17)
  4. Calculate days between updated_at and today
  5. Check if mergeable: false (has conflicts)
  6. Check if draft: true

Classification rules:

  • critical: age > 28 days
  • severe: age > 14 days AND days_since_update > 14
  • moderate: age > 7 days AND no reviewer comments
  • mild: age > 3 days AND days_since_update > 3
  • fresh: otherwise

Step 5: Generate Report

Create a grouped report with links:

## Stale PR Report: {owner}/{repo}

### Critical (> 28 days)
| PR | Title | Age | Author |
|----|-------|-----|--------|
| [#{num}](https://gitee.com/{owner}/{repo}/pulls/{num}) | {title} | {age}d | @{author} |

### Severe (> 14 days no update)
| PR | Title | Age | Last Update |
|----|-------|-----|-------------|
| [#{num}](https://gitee.com/{owner}/{repo}/pulls/{num}) | {title} | {age}d | {days}d ago |

### Moderate (> 7 days no review)
| PR | Title | Age |
|----|-------|-----|
| [#{num}](https://gitee.com/{owner}/{repo}/pulls/{num}) | {title} | {age}d |

### Summary
- Critical: {count}
- Severe: {count}
- Moderate: {count}
- Fresh: {count}

Usage Examples

Example 1: Basic Check

User: "Check for stale PRs in myrepo"

AI: Scanning myrepo...
Found 10 open PRs:
- 2 Critical (> 28 days)
- 3 Severe (> 14 days)
- 5 Moderate (> 7 days)

[Shows report]

Example 2: Check Specific Author

User: "Are there any stale PRs from @alice?"

AI: Found 2 stale PRs from @alice:
- PR #42: 25 days old, needs rebase
- PR #45: 12 days old, waiting for review

Notes

  • Be diplomatic when mentioning stale PRs
  • Exclude bot PRs (dependabot, renovate) by default
  • Respect "wip", "draft", "on-hold" labels

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.