agentleFS
dmzoneilldmzoneill/skills/check-mr-feedback/SKILL.md

check-mr-feedback

Skill2 starsChanged 19 days agoApache-2.0View on GitHub

Check your open MRs for reviewer comments that need your attention. Scans for human comments (filters bots), meeting requests, code change requests, questions, approval status. Use when you want to see what feedback needs a response or before addressing review comments.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Use split_mr_comments, is_bot_comment (shared parsers)

    line 40
  2. Distinctive:

    Add follow-ups: "Respond to feedback on MR !X", "Schedule meeting for MR !X with Y"

    line 60
  3. Distinctive:

    No pending feedback if clear

    line 82

≈ “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

Check MR Feedback

Review your open MRs for feedback requiring response.

Inputs

InputTypeDefaultPurpose
projectstringautomation-analytics/automation-analytics-backendGitLab project
create_meetingsboolfalseCreate Google Meet invites for meeting requests
mr_idsarray-Specific MR IDs (default: all open)
slack_formatboolfalseSlack link format

Workflow

1. Load Persona

  • persona_load("developer")

2. Check Known Issues

  • check_known_issues("gitlab_mr_list", "")

3. Get Open MRs

  • gitlab_mr_list(project, author="@me") — open MRs
  • Filter by mr_ids if provided

4. Get Comments (up to 5 MRs)

  • gitlab_mr_comments(project, mr_id) for each MR

5. Analyze Comments

  • Use split_mr_comments, is_bot_comment (shared parsers)
  • Filter: human comments only, exclude own
  • Detect: meeting requests (meeting, call, discuss, sync, chat, walk through)
  • Detect: needs response (please, could you, ?, consider, suggest)
  • Build: {mr_id, title, comments, meeting_requests, needs_response}

6. Meeting Invites (if create_meetings)

  • Check google_calendar config
  • For each meeting request: google_calendar_quick_meeting(title, attendee_email, when="auto")
  • Or suggest tool calls if not auto-creating

7. Format Summary

  • Per MR: author, text, icon (💬/📅/❓)
  • Meeting requests: suggest google_calendar_find_meeting, google_calendar_quick_meeting

8. Memory

  • memory_session_log("Checked MR feedback", "{count} MRs with feedback")
  • Add follow-ups: "Respond to feedback on MR !X", "Schedule meeting for MR !X with Y"

9. Learn from Failures

  • VPN: learn_tool_fix("gitlab_mr_list", "no such host", "VPN", "vpn_connect()")

MCP Tools

  • persona_load
  • check_known_issues
  • gitlab_mr_list
  • gitlab_mr_comments
  • google_calendar_quick_meeting (if create_meetings)
  • memory_session_log
  • memory_append (follow_ups)
  • learn_tool_fix

Output

  • MR Feedback Summary
  • Per MR: comments with author, text, meeting/response flags
  • Meeting scheduling suggestions
  • No pending feedback if clear

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.