agentsclimarketplace
Sign in

Implementation plan review

Skill MaybeMonad/skills/skills/unknown-reduction/implementation-plan-review

Implementation planning workflow focused on the decisions most likely to change before coding starts. Use when the user asks for an implementation plan, plan in HTML, review the plan before implementation, focus on data models, type interfaces, UX flows, architecture choices, validation gates, or wants to reduce rework before touching code.From its SKILL.md

Install
npx -y skills add MaybeMonad/skills --skill implementation-plan-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.0 KB, 350 tokens by cl100k_base, as published. Nobody here has run it

Implementation Plan Review

Use this skill when the work is close to implementation but the user should review high-impact decisions first. The plan should make likely pivots visible, not bury them under mechanical task lists.

Workflow

  1. Inspect the territory:
    • Current code paths, schemas, components, tests, runtime constraints, product behavior, and relevant docs.
  2. Identify high-change decisions:
    • Data model or schema.
    • Type interfaces or API contracts.
    • State ownership and persistence.
    • UX flow, copy, permissions, error states.
    • Migration, rollout, compatibility, or performance constraints.
  3. Present decision points before the mechanical plan.
  4. State the recommended path and alternatives.
  5. Include validation gates:
    • Unit or integration tests.
    • Typecheck/build/lint.
    • Browser/runtime/manual checks when user-visible.
    • Data or migration verification when relevant.
  6. Add pivot triggers: discoveries that should update the plan before continuing.
  7. Put routine edits and refactors at the bottom.

Output Shape

Use this order:

  1. Goal and assumptions.
  2. Decisions to review.
  3. Recommended implementation path.
  4. Files or modules likely touched.
  5. Validation gates.
  6. Pivot triggers.
  7. Mechanical task list.

Rules

  • Do not over-specify mechanical implementation when the agent can infer it safely from local patterns.
  • Do not hide uncertain decisions in a task checklist.
  • If a prototype, interview, or reference pass would materially change the plan, recommend that before implementation.
  • Use HTML only when the plan benefits from visual structure or reviewer scanning; otherwise Markdown is enough.

What ships with it: 1 file

236 B alongside SKILL.md

agents/

Keep looking

Skills are one crate of 326,750. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.