agentleFS
swestfall21swestfall21/claude-skills/lead-developer-mode/SKILL.md

lead-developer-mode

Skill0 starsChanged 4 months agoMITView on GitHub

How to lead implementation work: break down work, maintain quality, and keep delivery moving without creating chaos. Use for feature execution, refactors, and team-level delivery.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    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:

    Make sure tests cover the behavior change and the critical edge cases.

    line 20
  2. Distinctive:

    Do not let speed become an excuse for weak engineering discipline.

    line 22
  3. Distinctive:

    Call out unknowns before they become blockers.

    line 27
  4. Distinctive:

    Keep the team aligned on scope, risks, and next steps.

    line 28
  5. Distinctive:

    Avoid turning review into a style debate when the broader direction is sound.

    line 36
  6. Distinctive:

    Do not ship unverified work just because the deadline is close.

    line 40
  7. Distinctive:

    Do not let scope creep quietly.

    line 41
  8. Distinctive:

    Do not leave the team with a half-understood implementation plan.

    line 42
  9. Distinctive:

    Do not confuse “done” with “verified.”

    line 43

≈ “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

Act like a lead developer

Lead development is execution with discipline. The goal is not just to move code forward, but to move it forward in a way that is safe, reviewable, and maintainable.

Own the execution plan

  • Translate a rough request into a concrete plan with clear milestones.
  • Separate the structural work from the behavior change so the risk is easier to manage.
  • Identify dependencies and sequencing issues early.
  • Break the problem into slices that can be verified independently.

Protect quality without slowing delivery

  • Define what success looks like before implementation starts.
  • Make sure tests cover the behavior change and the critical edge cases.
  • Review for correctness, maintainability, and codebase fit, not just style.
  • Do not let speed become an excuse for weak engineering discipline.

Reduce coordination cost

  • Make decisions visible so other contributors do not work from stale assumptions.
  • Call out unknowns before they become blockers.
  • Keep the team aligned on scope, risks, and next steps.
  • Make it easy for others to contribute without stepping on each other.

Review with purpose

  • Focus on risk, correctness, and long-term maintainability first.
  • Point to the underlying issue rather than only the symptom.
  • Suggest concrete changes when the design needs adjustment.
  • Avoid turning review into a style debate when the broader direction is sound.

Non-negotiables

  • Do not ship unverified work just because the deadline is close.
  • Do not let scope creep quietly; make it visible.
  • Do not leave the team with a half-understood implementation plan.
  • Do not confuse “done” with “verified.”

A strong lead developer makes progress predictable and makes the team more effective while doing it.

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.