agentleFS
AkshitIreddyAkshitIreddy/agent-skills/skills/finish-the-list/SKILL.md

finish-the-list

Skill1 starsChanged 2 months agoMITView on GitHub

Complete a requested backlog or multi-part deliverable without stopping after an intermediate milestone.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep a concise record of the requested outcomes and their completion criteria.

    line 8
  2. Distinctive:

    Use an existing issue, plan, or TODO when available.

    line 9
  3. Distinctive:

    Ask a focused question when missing information would materially change the outcome.

    line 19
  4. Distinctive:

    Run checks appropriate to the changed behavior and satisfy required project checks.

    line 30
  5. Distinctive:

    Before ending, reconcile the result with every requested outcome.

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Finish the requested work

Keep a concise record of the requested outcomes and their completion criteria. Use an existing issue, plan, or TODO when available; create a durable handoff when the task spans sessions or the user requests one.

Continue to the next actionable item after a milestone. A request to implement includes the integration and relevant verification needed for the feature to work. Progress updates and side questions do not end the broader assignment.

Scope and blockers

  • Infer routine choices from context and continue reversible, authorized work.
  • Ask a focused question when missing information would materially change the outcome; work on independent items while the answer is pending.
  • Record a blocked item with its actual missing dependency or failed approach. Try useful alternatives without repeating ineffective work.
  • Preserve explicit approval boundaries and the user's ability to stop or change direction. Persistence does not authorize unrelated work.
  • Distinguish completed outcomes from deferred, excluded, or blocked ones. Recording a gap does not make the work complete.

Finish with evidence

Run checks appropriate to the changed behavior and satisfy required project checks. Once they pass, repeat or broaden them only for a new change, failure, or unresolved concern. Report the practical limits of verification.

Before ending, reconcile the result with every requested outcome. Finish when the work is complete, the user stops it, or useful progress requires input or an external change. State remaining blockers plainly and preserve enough state to resume. Continue work already requested without asking whether to continue.

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.