writing-planslisted
Install: claude install-skill sergeyklay/.agents
# Writing Implementation Plans
Transform a Technical Specification (or equivalent input) into an atomic, dependency-ordered Implementation Plan. The plan is the contract between architect and implementer: it removes ambiguity about WHAT changes, WHERE it changes, in WHAT ORDER, and HOW each step is verified. The coder agent executes the plan verbatim; ambiguous or oversized steps each produce a class of implementation defect.
This skill is stack-agnostic and project-agnostic. Concrete phase catalogs, layering rules, banned patterns, and verification commands come from the project's architecture document and agent-instruction files, not from this skill. Read those documents first; design within them; flag every deviation explicitly.
## Running scripts bundled with this skill
Script paths in this document (e.g. `scripts/`) are resolved relative to **this** SKILL.md file, not to your current working directory. If a relative command fails to resolve, prefix it with the path your platform loaded this SKILL.md from.
**Fallback.** If `python3` cannot be located, analyze the script's purpose and logic and execute its intent with available tools, but warn the user that python is not available and the logic was executed with a fallback approach that may not be perfect.
## Project context: reading order
These documents are the authority every plan must conform to. Read in this order; skip tiers the project does not ship; do not load files that do not exist.
1. **Agent-instructio