skills/task-plan-phase-implementation/SKILL.md
Load when the primary work is writing code and the path is clear. Provides the pre-dispatch checklist, @coder delegation structure, deviation handling, and progress tracking.
npx skillsauth add maestria-co/ai-playbook task-plan-phase-implementationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Load this skill when the task's dominant focus targets code generation and planning is finalized. For tasks with fuzzy boundaries, load task-plan-phase-investigation first. This skill omits test delegation — consult task-plan-phase-testing. Closure operations (retrospective, context refresh) reside in task-plan-phase-completion.
Before initiating any @coder step:
git status --short. Staged alterations from previous agent operations require commit or stash before dispatch — committing agents will incorporate unrelated staged files.All @coder dispatches require these components:
Step [N]: [step characterization]
Files to create/alter:
- [file/path]: [required action]
Patterns for adherence:
- [.context/standards/ or .context/architecture/ citation]
Research/architecture conclusions: [synopsis or "N/A"]
Acceptance thresholds:
- [Concrete, verifiable outcome]
- Commit all created/altered files
Following each @coder step:
git status --short — confirm zero untracked new files persist.plan.md ## Progress section: mark step finalized, append outcome notation (— [terse characterization of implementation/alterations]).When @coder reports plan deviation (alternative methodology, unexpected obstruction, distinct files altered):
plan.md ## Decisions.systematic-debugging skill before retry.Maintain plan.md currency throughout:
## Open Questions / Blockers as identified.## Key Files.systematic-debugging: Load for repeated @coder failures on identical obstacles.task-plan-phase-architecture: When deviation resolution exposes architectural obstructions, load this skill.task-plan-phase-testing: For predominantly test-focused post-implementation effort, load the test skill next.task-plan: Use to refresh plan.md at step transitions.Excluded scope: investigation, architectural audit, test delegation, retrospectives, closure files.
development
Writes and runs a test suite for a piece of code, covering happy path, edge cases, error cases, and security cases. Use when: implementation is complete and needs test coverage, a bug needs a reproduction test and fix validation, or code needs coverage before a refactor. Do not use when: the code under test is not yet implemented, or the spec is still unclear.
testing
Use when creating a new skill, editing an existing skill, or helping a user author a skill for this system. Covers structure, discoverability, quality, and discipline hardening.
development
Evidence-based verification process to run before marking any task complete. Use this skill every time you're about to report that work is done — for features, bug fixes, refactoring, or any code change. This catches the most common failure mode: declaring "done" without proof. If you're finishing up and about to tell the user the task is complete, run this checklist first.
development
Teaches agents how to discover, select, and invoke skills from the skill library. Use this skill whenever you're uncertain which skill applies to a task, when composing multiple skills for complex work, or when you need to understand what skills are available. This is your go-to when facing an ambiguous task and need to figure out the right approach before diving into implementation.