iikit-07-implement

Executes tasks.md implementation plans with TDD enforcement, parallel subagent dispatch, and per-task git commits.

1|Updated Apr 30, 2026
One-click install
npx skills add https://github.com/hafidzlvm/opencode --skill iikit-07-implement-hafidzlvm
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: iikit-07-implement
Source: https://github.com/hafidzlvm/opencode/tree/main/.tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-07-implement
Command: npx skills add https://github.com/hafidzlvm/opencode --skill iikit-07-implement-hafidzlvm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Turning a written task plan into working code often loses discipline: tests get skipped, tasks drift from the spec, and commits become untraceable. This Skill executes an Intent Integrity Kit tasks.md plan end-to-end, enforcing constitutional rules, BDD red-green cycles, and structured commit history so implementation stays aligned with the approved specification. ## Core Features & Use Cases - Task Graph Execution: Parses tasks.md for phases, dependencies, [P] parallel markers, and user story labels, then dispatches tasks sequentially or as concurrent subagent batches with file-conflict detection. - BDD/TDD Gate Enforcement: Verifies step definition coverage, assertion quality, and actual test execution before any task can be marked complete; .feature files are hash-locked and immutable. - Commit Strategies & Progress Tracking: Supports per-task or per-phase git commits with structured trailers, live dashboard regeneration, and GitHub issue closing for bugfix tasks. - Use Case: After running /iikit-05-tasks to generate a task breakdown, invoke this Skill to code each task, run the BDD test chain, checkpoint progress in tasks.md, and produce a clean bisectable commit history. ## Quick Start Run the implement phase of the iikit workflow to build the feature from the current tasks.md plan.

Frequently Asked Questions about iikit-07-implement

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I execute a tasks.md implementation plan with an AI agent?▼

Run the implement phase after generating tasks.md. The skill parses phases, dependencies, and [P] parallel markers, then codes each task, runs tests, and marks tasks complete in tasks.md as it progresses.

How does parallel task execution work during implementation?▼

Tasks marked [P] with no mutual dependencies are grouped into batches and dispatched as concurrent subagents, one worker per task. After each batch, the orchestrator checks for file conflicts, runs the full test suite, and commits each task individually.

Can I resume a partially completed implementation?▼

Yes. Tasks already marked [x] in tasks.md are skipped, and only eligible incomplete tasks are executed. The prerequisites check also supports selecting among multiple features when no active feature is set.

What happens if BDD tests fail during implementation?▼

The skill halts the phase and reports the failure. You must fix production code, never the tests or .feature files, then re-run until the green phase passes before the task can be marked complete.

When are .feature files allowed to change during implementation?▼

Never. Feature files are generated by the testify phase and hash-locked. Only step definitions and production code may be modified; if a .feature file needs changes, you must re-run /iikit-04-testify.

What is the difference between per-task and batch commit strategies?▼

Per-task creates one git commit per completed task with structured trailers mapping commits to task IDs. Batch commits once per phase, which is faster but does not map commits one-to-one to tasks.