agentleFS
witnesstodarkwitnesstodark/mr-mak-workspace/.claude/skills/feature-handoff/SKILL.md

feature-handoff

Skill800 starsChanged 23 days agoMITView on GitHub

Prepare a precise handoff for an agent or developer implementing a feature, continuing a task or reviewing a finished change.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the current project files and relevant terminal or report before writing a handoff.

    line 8
  2. Distinctive:

    Do not assign the user work that the receiving agent can complete itself.

    line 18

≈ “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

Feature handoff

Read the current project files and relevant terminal or report before writing a handoff. Use the evidence currently on disk, not an earlier progress message.

Include the intended behavior, affected files, useful starting points, exact skill paths, known constraints and acceptance checks. For a continuation, add what is already implemented, what remains, current test results and any running process that must not be interrupted. Keep secrets and login material out.

Make ownership clear when several agents are working. Identify files that must not be overwritten. Carry forward accepted choices and unresolved questions. Do not assign the user work that the receiving agent can complete itself.

Separate the source baseline, selected proposal, implemented behavior, agent verification and owner acceptance. A selected mockup is not a shipped feature. For assets, include stable IDs, relevant hashes, local dependency paths and actual event markers. Name the receiving scene or system, and describe how to check it at normal gameplay speed. Leave missing values unresolved rather than turning an example's timing, project names or design taste into requirements.

State who owns shared files and the expected base revision. Re-read shared state before applying the handoff; reconcile changed inputs instead of overwriting another agent's work. Keep the current specification current and put chronological implementation details in a separate log.

For a completed feature, lead with its practical result, then summarize the change and verification. Link the relevant report or artifacts. Distinguish a prepared build from an installed update and a submitted job from a reviewed asset. Read workspace-authoring when the handoff is a Workspace deliverable.

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.