write-focused-plan-test

Writes an approved focused Plan document from retained assessment evidence and frontier corrections.

Updated Mar 24, 2026
One-click install
npx skills add https://github.com/skyrocoster/dnd-kids-resources --skill write-focused-plan-test-skyrocoster
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: write-focused-plan-test
Source: https://github.com/skyrocoster/dnd-kids-resources/tree/main/.opencode/skills/write-focused-plan-test
Command: npx skills add https://github.com/skyrocoster/dnd-kids-resources --skill write-focused-plan-test-skyrocoster

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It turns an approved planning proposal into a correctly structured Plan document without restarting repository exploration, ensuring the Plan lands at the right path, follows the Layer 1 schema, and preserves compiler-relevant facts for downstream work orders. ## Core Features & Use Cases - Guarded Plan Writing: Requires PROPOSAL APPROVED, an exact TARGET PATH, and FRONTIER CORRECTIONS before writing, and rejects flat active-Plan targets in favor of the nested docs/plans/active/<feature>/<feature>.md form. - Schema and Touches Validation: Applies the Layer 1 schema from docs/PLAN_TEMPLATE.md and validates every Touches entry as a repo-relative glob matching existing files. - Docs Contract Checks: Runs scripts/check_docs.py --write-generated and --check for real active Plans, while exempting user-authorized scratch simulations. - Use Case: After a coordinator approves a focused Plan proposal with frontier corrections, invoke this Skill to write the Plan file, validate ownership globs, record stage routing as ORDERED or QUICK-CANDIDATE, and return a structured RESULT report. ## Quick Start Ask the agent to write the approved focused Plan for the feature using the retained assessment evidence and the frontier corrections, targeting the nested active plan path.

Frequently Asked Questions about write-focused-plan-test

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

FAQPage Schema
How do I write an approved focused Plan from assessment evidence?▼

Provide the coordinator's PROPOSAL APPROVED signal, the exact TARGET PATH, and the FRONTIER CORRECTIONS. The Plan is then written from retained case context using the Layer 1 schema, without restarting broad repository exploration or implementing code.

What target path is required for an active Plan document?▼

A real active Plan must target docs/plans/active/<feature>/<feature>.md, where the feature directory exists and the filename repeats the feature name. Flat targets like docs/plans/active/<feature>.md are rejected unless the coordinator explicitly authorizes normalization.

Can a Plan be written under a scratch directory?▼

A path under scratch/ is allowed only when the user explicitly authorized that simulation path. Scratch simulations are outside the docs contract, so the check_docs.py verification commands are not run for them.

How are Touches entries validated in a Plan?▼

Each Touches entry must be a repo-relative glob that currently matches at least one existing file or directory. Placeholder production files are never created just to satisfy the documentation checker, and conditional or verification-only paths are not listed as unconditional Touches.

Why does Plan writing fail or return BLOCKED?▼

Writing is blocked when the proposal is not approved, the target path is missing or malformed, or required frontier corrections are absent. The result report returns BLOCKED or FAILED with the exact blocker described in the ISSUE field.

What verification commands run after writing a Plan?▼

For a real active Plan, scripts/check_docs.py runs first with --write-generated, the generated changes are inspected, then it runs with --check. The Skill never commits changes to version control.