agentleFS
baijunjiebaijunjie/octoboard/.claude/skills/agent-change-check/SKILL.md

agent-change-check

Skill5 starsChanged 2 days agoMITView on GitHub

Review this round's changes and work through the comments until it passes; this should come to mind once the changes are done, before delivery. Use when the user says "review this round of changes", "wrap-up review", "check the changes I just made".

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. Distinctive:

    When you are a subagent, do not follow this skill: finish and hand back, and let whoever dispatched you arrange it.

    line 8
  2. Very specific:

    When the volume of changes is large and spans several relatively isolated modules, split by scope and dispatch one change-checker per …

    line 24
  3. Distinctive:

    When unsure, report back: stop, spell out what needs deciding (with the options) or what information is missing, together with what you …

    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

Change check

When you are a subagent, do not follow this skill: finish and hand back, and let whoever dispatched you arrange it. A subagent is an agent dispatched to do one job, which hands its conclusions or changes back to the dispatcher, who is responsible for bringing them into the branch; an agent whose deliverable is a branch (no matter who ends up pushing or merging it) is not a subagent.

  1. Dispatch the change-checker subagent to review this round of changes; do not review what you wrote yourself: your own context treats the structure you just wrote as settled fact. Its checklist and judgment criteria live in its own definition; you only hand over what changed this round and what the requirement is, plus the trade-offs the user settled over several rounds of revision — it cannot see your conversation, and anything you leave out comes back reported as a problem.
  2. Work through the comments one by one: fix the ones you agree with; explain your reasoning for the ones you do not, and when you cannot reach agreement with it, or a comment would overturn a trade-off the user settled, leave it to the user to decide.
  3. Dispatch it again once the fixes are in, until it passes. In your final reply, state how many rounds of review there were, what was changed, and which comments are left for the user to decide.
  • When the volume of changes is large and spans several relatively isolated modules, split by scope and dispatch one change-checker per scope, reviewing in parallel: one subagent given too much full text to read can only skim, and details get missed. Where scopes share an interface contract, hand that contract to every side involved; when fixing comments touches a cross-scope interface, re-dispatch a review for the scopes on both sides of it.
  • The subagent this skill dispatches is installed together with it: if there is a subagent mechanism but the definition of the subagent to dispatch cannot be found, the installation is incomplete: stop and ask the user to rerun the installer that installed this skill. With no subagent mechanism, read the installed definition and do the work yourself following the rules inside.

When unsure, report back: stop, spell out what needs deciding (with the options) or what information is missing, together with what you have already found out, and let the recipient of the report (the user, or the dispatcher passing it on to the user) decide before going on; do not decide for yourself.

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.