agentleFS
Jamie-BitFlightJamie-BitFlight/claude_skills/.claude/skills/start-milestone/SKILL.md

start-milestone

Skill67 starsChanged 53 days agoMITView on GitHub

Transitions a GitHub milestone from planning to active execution. Use when the team is ready to begin a sprint or release cycle — bulk-transitions open issue labels from status:needs-grooming to status:in-progress, updates GitHub Projects V2 Status to In Progress, and confirms before applying changes. Requires milestone number as argument. Use after /group-items-to-milestone.

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:

    If not found in the open list, call mcp__plugin_dh_backlog__backlog_list_milestones(state="all") and filter again.

    line 32
  2. Distinctive:

    If milestone is closed, report and stop.

    line 34
  3. Very specific:

    If open_issues == 0, warn: "No open issues.

    line 36
  4. Very specific:

    Use AskUserQuestion with Yes / No options.

    line 57
  5. Distinctive:

    Use the Python automation script (preferred — avoids per-issue bash loops):

    line 61

≈ “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

<milestone_number>$ARGUMENTS</milestone_number>

Start Milestone

Transition a milestone from planning to active: bulk-update labels and Project board status.

API references: milestones.md | projects-v2.md

Arguments

<milestone_number/> — milestone number (required).

/start-milestone 3

Workflow

Step 1: Resolve Milestone

Call mcp__plugin_dh_backlog__backlog_list_milestones(state="open").

From the returned list, find the entry where number == <milestone_number/>.

If not found in the open list, call mcp__plugin_dh_backlog__backlog_list_milestones(state="all") and filter again.

If milestone is closed, report and stop.

If open_issues == 0, warn: "No open issues. Add items first with /group-items-to-milestone {number}"

Step 2: List Issues

Call mcp__plugin_dh_backlog__backlog_list_issues(milestone="{title}", state="open").

The response contains a list of issues with number, title, state, and labels fields.

Step 3: Confirm

Start milestone "{title}" — {N} open issues

Issues to transition (status:needs-grooming → status:in-progress):
  #12  SAM: Error Recovery        [priority:p1, status:needs-grooming]
  #8   gitlab-skill: Remove URL   [priority:p1, status:needs-grooming]
  #14  create-backlog-item skill  [priority:p2, status:needs-grooming]

Proceed?

Use AskUserQuestion with Yes / No options. Stop without changes if No.

Step 4: Bulk Label Transition

Use the Python automation script (preferred — avoids per-issue bash loops):

uv run .claude/skills/gh/scripts/github_project_setup.py milestone start \
  --number {number}

Or, to preview changes without applying them:

uv run .claude/skills/gh/scripts/github_project_setup.py milestone start \
  --number {number} --dry-run

The script removes status:needs-grooming and adds status:in-progress to each open issue, creates the label if missing, reports per-issue results, and exits non-zero if any issue fails.

Step 5: Update Project V2

Run:

uv run .claude/skills/gh/scripts/github_project_setup.py project update-status \
  --milestone {number} --status "In Progress"

See projects-v2.md for details.

Step 6: Report

Milestone #{N} "{title}" started.

  {count} issues transitioned to status:in-progress
  {failed_count} issues failed (see details above)

Work on individual items:
  /work-backlog-item {title}

Error Handling

  • Milestone not found: list open milestones and stop.
  • Milestone already closed: report closed date and stop.
  • Label edit fails for specific issue: log and continue; report failures at end.
  • User declines confirmation: stop without changes.

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.