Run any Skill in Manus with one click

prep-plan

Stars6

Forks0

UpdatedJune 12, 2026 at 17:33

Use when ready to build a reviewable implementation plan as a lore artifact. Input can be a spec, design, brainstorm, research, or a well-defined prompt. Triggers include "prep plan", "prepare a plan", "plan this", "make a plan", "plan the implementation", and "break this into steps".

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

rjroy

rjroy/vibe-garden

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Project Management SpecialistsBusiness and Financial Operations Occupations·SOC 13-1082

SKILL.md

readonly

name	prep-plan
description	Use when ready to build a reviewable implementation plan as a lore artifact. Input can be a spec, design, brainstorm, research, or a well-defined prompt. Triggers include "prep plan", "prepare a plan", "plan this", "make a plan", "plan the implementation", and "break this into steps".

Prep Plan

Build an implementation plan the user can review and approve before any code is written. The plan is the output. Implementation is a separate step via /implement.

Do not use EnterPlanMode. This skill authors a document, not a precursor to immediate code changes.

Process

Gather context. Invoke the lore-researcher agent via Task tool with the topic description — wait for the result. Read any relevant lore artifacts (spec, design, brainstorm, research). Explore the codebase with an Explore subagent to understand what exists and where changes will land.

Surface gaps before drafting. If the input has ambiguous requirements, contradictions, or unstated assumptions that would force guesses, list them and ask the user to resolve them first. A plan built on unreviewed assumptions fails during implementation.

Draft collaboratively. Map the goal or requirements to concrete implementation steps. Order by dependency. Flag steps that need specialized expertise. Include a final validation step that checks the implementation against the source artifact.

Save. The saved file is the review vehicle — don't present the plan in chat before saving.

Fresh-eyes review. After saving, invoke the plan-reviewer agent via Task tool on the saved plan. Present findings and offer to address issues before implementation begins.

Saving

Save to .lore/work/plans/[feature-name].md using kebab-case. Load ${CLAUDE_PLUGIN_ROOT}/shared/frontmatter-schema.md for the frontmatter fields. The document body is freeform — what matters is that steps are concrete (files, functions, changes) and the source artifact or goal is clearly referenced so validation has something to check against.

Write the body Markdown-first per the "Body Format" section of ${CLAUDE_PLUGIN_ROOT}/shared/frontmatter-schema.md. Reach for embedded inline HTML when the step flow needs it — a visual step sequence with dependency indicators, and validation gates distinguished visually from the step description.

More from this repository

same repository

resolve-drift

rjroy/vibe-garden

Use when checking whether field-guide reference pages still match current code and tests. Reads pages plus fg-evidence anchors, reports or fixes semantic drift, and can use sub-agents for parallel audit batches. Triggers include "resolve drift", "semantic drift", "check accuracy", "verify the reference against code", and "audit the wiki".

2026-06-256

update-evidence

rjroy/vibe-garden

Use after ingesting or editing field-guide pages to attach living code/test anchors. Adds or refreshes fg-evidence metadata without trying to prove prose accuracy. Triggers include "update evidence", "wire evidence", "add evidence anchors", and "connect the wiki to code".

2026-06-256

ingest

rjroy/vibe-garden

Use when extracting knowledge from .lore/ artifacts into the reference wiki. Converts work artifacts (retros, specs, plans, research, notes) into structured wiki pages grouped by knowledge type. Reads Markdown or HTML sources and writes Markdown by default. Triggers include "ingest this", "extract knowledge from", "add this to the wiki", "update the reference from", and "populate the field guide".

2026-06-256

init

rjroy/vibe-garden

Use when setting up field-guide on a project for the first time, or to refresh the scheduled lint job after it expires. Triggers include "init field-guide", "set up field-guide", "refresh field-guide lint schedule", and "bootstrap the wiki".

2026-06-256

lint

rjroy/vibe-garden

This skill is used when the project wiki needs a health check. Triggers include 'lint the wiki', 'check wiki health', 'run field-guide lint', 'are there stale wiki pages', 'find orphaned pages', 'check for contradictions in the wiki'.

2026-06-256

query

rjroy/vibe-garden

Use when asking questions about the project wiki, querying accumulated knowledge, searching project decisions or lessons. Triggers include "query the wiki", "what does the wiki say about", "search project knowledge", and natural language questions directed at the field-guide wiki.

2026-06-256

name	prep-plan
description	Use when ready to build a reviewable implementation plan as a lore artifact. Input can be a spec, design, brainstorm, research, or a well-defined prompt. Triggers include "prep plan", "prepare a plan", "plan this", "make a plan", "plan the implementation", and "break this into steps".

Prep Plan

Build an implementation plan the user can review and approve before any code is written. The plan is the output. Implementation is a separate step via /implement.

Do not use EnterPlanMode. This skill authors a document, not a precursor to immediate code changes.

Process

Save. The saved file is the review vehicle — don't present the plan in chat before saving.

Fresh-eyes review. After saving, invoke the plan-reviewer agent via Task tool on the saved plan. Present findings and offer to address issues before implementation begins.