PluginBench
Skill
Review
Audit score 70

do

thedotmack/claude-mem

Execute phased implementation plans by orchestrating specialized subagents for each task.

What is do?

A skill for coordinating multi-phase project execution by deploying focused subagents to handle implementation, verification, anti-pattern checks, and code quality review. Use this when you have a plan (especially from make-plan) that needs to be carried out systematically with verification at each step.

  • Deploy specialized subagents for implementation, verification, anti-pattern detection, and code quality review
  • Enforce completion verification before advancing to the next phase
  • Prevent common failure modes like inventing undocumented APIs or skipping validation
  • Coordinate branch management and context handoff between phases
  • Require evidence (commands run, outputs, files changed) from each subagent before proceeding

How to install do

npx skills add https://github.com/thedotmack/claude-mem --skill do
Claude Code
Cursor
Windsurf
Cline

How to use do

  1. 1.Provide or reference a phased implementation plan (ideally created by make-plan)
  2. 2.The orchestrator will deploy an Implementation subagent for the first phase with a clear objective
  3. 3.After implementation, subagents are deployed for verification, anti-pattern checks, and code quality review
  4. 4.Review verification results; the Commit subagent only deploys if all checks pass
  5. 5.The Branch/Sync subagent pushes verified changes and prepares context for the next phase
  6. 6.Repeat for each subsequent phase until plan completion

Use cases

Good for
  • Execute a multi-phase software implementation plan with verification at each stage
  • Coordinate complex refactoring across multiple components with quality gates
  • Run a deployment plan that requires validation and anti-pattern checks between phases
  • Manage a phased feature rollout with verification and commit gates
  • Execute infrastructure or configuration changes with documented checkpoints
Who it's for
  • Engineering teams executing detailed implementation plans
  • Developers managing complex multi-phase projects
  • Teams requiring verification and quality gates before commits
  • Projects using make-plan or similar planning tools

do FAQ

When should I use 'do' vs. just asking Claude to implement something?

Use 'do' when you have a detailed multi-phase plan that requires verification, quality gates, and coordination across multiple concerns. It's especially useful with plans created by make-plan.

What happens if a subagent reports a problem during verification?

The orchestrator stops and does not advance to the next phase. The failing phase is not committed, and you can address the issue before retrying.

Can I skip verification or commit without passing checks?

No. The skill enforces that verification passes before any Commit subagent is deployed. You can override with explicit orchestrator approval, but the default is to block.

What if an API or function seems to be missing?

The Implementation subagent is instructed to STOP and verify against documentation rather than assume the API exists. This prevents inventing undocumented parameters or non-existent functions.

How does 'do' handle large or unclear context between phases?

A Branch/Sync subagent pushes verified changes and prepares a fresh context handoff so the next phase's subagents start with a clean slate but retain plan context.

Full instructions (SKILL.md)

Source of truth, from thedotmack/claude-mem.


name: do description: Execute a phased implementation plan using subagents. Use when asked to execute, run, or carry out a plan — especially one created by make-plan.

Do Plan

You are an ORCHESTRATOR. Deploy subagents to execute all work. Do not do the work yourself except to coordinate, route context, and verify that each subagent completed its assigned checklist.

Execution Protocol

Rules

  • Each phase uses fresh subagents where noted (or when context is large/unclear)
  • Assign one clear objective per subagent and require evidence (commands run, outputs, files changed)
  • Do not advance to the next step until the assigned subagent reports completion and the orchestrator confirms it matches the plan

During Each Phase

Deploy an "Implementation" subagent to:

  1. Execute the implementation as specified
  2. COPY patterns from documentation, don't invent
  3. Cite documentation sources in code comments when using unfamiliar APIs
  4. If an API seems missing, STOP and verify — don't assume it exists

After Each Phase

Deploy subagents for each post-phase responsibility:

  1. Run verification checklist — Deploy a "Verification" subagent to prove the phase worked
  2. Anti-pattern check — Deploy an "Anti-pattern" subagent to grep for known bad patterns from the plan
  3. Code quality review — Deploy a "Code Quality" subagent to review changes
  4. Commit only if verified — Deploy a "Commit" subagent only after verification passes; otherwise, do not commit

Between Phases

Deploy a "Branch/Sync" subagent to:

  • Push to working branch after each verified phase
  • Prepare the next phase handoff so the next phase's subagents start fresh but have plan context

Failure Modes to Prevent

  • Don't invent APIs that "should" exist — verify against docs
  • Don't add undocumented parameters — copy exact signatures
  • Don't skip verification — deploy a verification subagent and run the checklist
  • Don't commit before verification passes (or without explicit orchestrator approval)