planning-implementation
Planning Implementation
Overview
Extract every implementation task from architecture document(s) into a structured JSON task graph. The output is a DAG of tasks sized for autonomous agent workers — each task self-contained, dependency-ordered, and verifiable without access to the full architecture.
Before Planning Begins
- Get existing state: Run
dark-factory list --job $JOB --status pending --include-contentto see outstanding tasks already in the graph - Explore the codebase: Dispatch background explore agents to review files relevant to each section of the document — understand existing patterns, types, and integration points before writing tasks
- Research dependencies: Use web search to research any libraries, frameworks, or tools referenced in the architecture that you're unfamiliar with
Output Schema
Write valid JSON to the specified output path:
{
"project": "<project name>",
More from neekolas/claude-skills
writing-design-docs
Use when starting any feature, system change, or bugfix that requires architectural decisions — before writing implementation plans or code. Triggers on new projects, multi-component changes, API design, or when the user says "design", "spec", or "architecture".
40working-with-graphite
Use when managing branches and PRs with the Graphite CLI (gt). Covers creating stacked PRs, modifying mid-stack, submitting, syncing, and resolving conflicts.
35babysit-pr
Use when monitoring a PR (or a full Graphite stack of PRs) that needs CI fixes or review comment responses. Runs as a long-running session with intelligent sleep intervals. Handles failing checks, reviewer feedback, and pushes verified fixes autonomously.
34dark-factory:conductor
Orchestrate autonomous task execution. Guides an Opus session through task refinement, test scaffolding, parallel worker dispatch, verification, and failure resolution.
31