agentleFS
Sign inStart free
tikocitikoci/rosetta/.github/skills/pick-next-task/SKILL.md

pick-next-task

Skill54 starsChanged 4 months agoMITView on GitHub

Pick the next actionable work item from GitHub Issues. Filters open issues labeled agent-ready (spec settled, not blocked), surfaces umbrella/blocked context. Use when starting fresh work or asking 'what should I do next?'

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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. Distinctive:

    If a filter argument was supplied, match it against titles and labels.

    line 34
  2. Very specific:

    Create new issues — that's promote-idea.

    line 54
  3. Very specific:

    Run validation checks — that's verify-task.

    line 55

≈ “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

Pick Next Task

The agent's what now? verb. Reads the GitHub Issues queue and returns the next pickable issue with enough context to start work. (Named for the retired tasks/ file queue — the verb survives, the backend is now issues; see tasks/README.md.)

When to use

  • Starting a new work session and asking "what's the next thing?"
  • Picking up rosetta after a break

What "pickable" means

An issue is pickable when:

  1. It is open and labeled agent-ready — acceptance criteria are settled.
  2. It is not labeled blocked and its body names no unresolved "blocked on" issue.
  3. It is not labeled umbrella — umbrellas track themes; work happens in child issues.

Procedure

  1. List candidates.

    gh issue list --state open --label agent-ready --json number,title,labels,updatedAt

    If a filter argument was supplied, match it against titles and labels.

  2. If none are agent-ready, widen with gh issue list --state open --json number,title,labels,body (the body field is what holds "blocked on" references and umbrella checklists) and report what exists instead: discussion-stage issues (unlabeled — could be settled into readiness), blocked issues (say what each waits on), and umbrella issues (their child checklists show what could be spawned next). Also point at BACKLOG.md Inbox and open briefings/.
  3. Surface the top pick. gh issue view <n> --comments, then present: number, title, acceptance criteria, V-* validation rows, and linked briefings or archived tasks/done/T-*.md files — some issues keep their full spec in the archived task file (e.g. #26 → T-0038), so read those too.
  4. Remind the close discipline. The eventual PR must say Closes #<n> in its body; partial landings spawn follow-up issues before merge (issue-pr-linking.instructions.md).

What this skill does NOT do

  • Assign the issue or open PRs — that happens when work actually starts.
  • Create new issues — that's promote-idea.
  • Run validation checks — that's verify-task.

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.

Check your setup, free