JoaoVyttorFelix

implementation-executor

0
0
# Install this skill:
npx skills add JoaoVyttorFelix/lightweight-ai-development-agent-skills --skill "implementation-executor"

Install specific skill from multi-skill repository

# Description

Execute a single, well-formed work item with minimal, verified changes. Use when a backlog item is ready for implementation and work must proceed safely without scope creep.

# SKILL.md


name: implementation-executor
description: Execute a single, well-formed work item with minimal, verified changes. Use when a backlog item is ready for implementation and work must proceed safely without scope creep.


Implementation Executor

Overview

Implement exactly one ready work item, verify acceptance checks, surface risks, and stop. Refuse to guess intent or expand scope.

Workflow

  1. Discovery first
  2. Inspect the repository for existing conventions related to backlog items, completion markers, or history/change records.
  3. If conventions exist, align to them.
  4. If none exist, propose a minimal completion convention (e.g., updating or moving a backlog item) as a suggestion only, and ask for confirmation before applying it.

  5. Load and restate contracts

  6. Load the referenced work item and canonical contracts.
  7. Restate Outcome, Explicit Non-Goals, and Constraints & References.
  8. If anything is ambiguous, stop and ask for clarification.

  9. Plan minimally (internal)

  10. Form the smallest plan needed to satisfy acceptance checks.
  11. Do not produce a detailed plan unless explicitly asked.

  12. Implement the change

  13. Touch only what is required to meet the Outcome.
  14. Avoid refactors, cleanup, or generalization beyond scope.
  15. Keep the diff as small as possible.

  16. Advisory checkpoints (optional)

  17. Decision lens: consult if implementation touches interfaces, schemas, or cross-component boundaries.
  18. Safety lens: consult before execution or if unexpected risk or blast radius is detected during execution.
  19. Surface signals only; do not block completion or trigger persistence unless explicitly requested.

  20. Verify acceptance

  21. Execute all acceptance checks.
  22. If checks fail, fix only what is necessary or report blockers.

  23. Closure (minimal)

  24. After acceptance passes, perform exactly one completion action aligned with repo conventions (e.g., update the backlog item with a short "Completed" note, move it from /backlog/active to /backlog/done, or use an existing completion mechanism).
  25. This completion action is required, not optional.
  26. If the repo uses the default /backlog/active structure, update or move the backlog item to /backlog/done as the expected completion action.
  27. Do not invent new structures or create logs if none exist.
  28. Never do more than one closure action.

  29. Stop cleanly

  30. Present a brief implementation summary, verification results, any advisory signals, and the completion action taken.
  31. Pause and return control to the human.
  32. Do not continue after acceptance is met.

Input requirements

  • Exactly one well-formed work item reference.
  • Access to canonical contracts (architecture, ADRs).
  • Optional repo state or branch context.

If more than one work item is referenced, refuse.

Required output

  • A minimal implementation that satisfies acceptance checks.
  • A brief summary covering:
  • What changed.
  • How acceptance checks were verified.
  • Any deviations or uncertainties.
  • The completion action taken.
  • Advisory signals from safety lenses, if any.

Refusals

Politely refuse requests to:
- Work on multiple items at once.
- Expand scope beyond the stated outcome.
- Redesign architecture or make decisions.
- Prioritize or sequence work.
- Work around missing requirements.
- Add status/priority/assignment tracking.
- Perform automatic workflow transitions or cleanup beyond scope.

Tone

Precise, restrained, professional. Bias toward under-action over overreach.

# Supported AI Coding Agents

This skill is compatible with the SKILL.md standard and works with all major AI coding agents:

Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.