ce-plan

Create structured implementation plans for software features and multi-step tasks.

Updated May 11, 2026
One-click install
npx skills add https://github.com/mmnavarr/harness --skill ce-plan-mmnavarr
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ce-plan
Source: https://github.com/mmnavarr/harness/tree/main/skills/ce-plan
Command: npx skills add https://github.com/mmnavarr/harness --skill ce-plan-mmnavarr

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Turning a feature idea, bug report, or requirements document into an actionable implementation plan is time-consuming and error-prone. This Skill produces durable, repo-grounded plans with clear scope, decisions, file paths, and test scenarios so implementation can start confidently. ## Core Features & Use Cases - Structured Plan Generation: Builds plans with problem frame, requirements traceability, key technical decisions, implementation units, risks, and test scenarios, saved to docs/plans/ with a conventional filename. - Research-Driven Planning: Dispatches parallel research agents covering repo patterns, institutional learnings, framework docs, and best practices before structuring the plan. - Plan Deepening: Runs a confidence-gap check on existing plans and strengthens weak sections via targeted sub-agent review with interactive accept/reject control. - Use Case: After brainstorming a new checkout feature, invoke the Skill to produce a sequenced implementation plan with per-unit test scenarios, then hand off directly to execution or create a tracked issue. ## Quick Start Ask the assistant to create a plan for your feature or task, for example: plan how we should build user authentication with OAuth support.

Frequently Asked Questions about ce-plan

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

FAQPage Schema
How do I create an implementation plan for a new feature?▼

Invoke the Skill with a feature description, requirements doc path, or rough task description. It researches the codebase and relevant patterns, confirms scope with you, then writes a structured plan file under docs/plans/ with implementation units and test scenarios.

How to deepen or strengthen an existing plan?▼

Say 'deepen the plan' or 'run a deepening pass' with a plan path. The Skill scores confidence gaps per section, dispatches targeted research agents, and lets you accept or reject each finding before updating the plan.

Does the planning skill require a requirements document first?▼

No. A prior brainstorm requirements doc is useful context but never required. The Skill can plan from any input, and runs a brief planning bootstrap to establish problem frame, scope, and success criteria when input is underspecified.

Can the plan be turned into a GitHub or Linear issue?▼

Yes. After the plan is written, the post-generation menu offers issue creation. It detects the configured tracker in AGENTS.md and runs gh issue create or the Linear CLI with the plan as the issue body.

When should I not use this planning workflow?▼

Skip it when the task is a clear bug with known root cause (use a debug workflow) or a ready-to-execute task with no architectural decisions (go straight to implementation). The Skill itself suggests these route-outs when it detects them.