---
title: "planning-skills-for-agents-and-humans"
description: "Planning workflows with evidence-gated research, fluid collaborative shaping, explicit promotion gates, breadboarding, bounded implementation handoffs, and reflection."
canonical: https://agentpluginsdirectory.com/plugins/planning-skills-for-agents-and-humans
last-updated: 2026-10-05
---

# planning-skills-for-agents-and-humans
Planning workflows with evidence-gated research, fluid collaborative shaping, explicit promotion gates, breadboarding, bounded implementation handoffs, and reflection.
- Slug: planning-skills-for-agents-and-humans
- Publisher: Matt Lane
- Repository: https://github.com/mattlane66/planning-skills-for-agents-and-humans
- Manifest: plugin.json
- Version: 1.5.1
- License: MIT
- Category (editorial): other
- Skills: 14 (breadboard-reflection, breadboarding, dumplink, executable-breadboards, feed-planning-context, framing-doc, interface-contracts, kickoff-doc, lead-user-research, planning-router, shaping, sketch-reconciliation, statechart, wayfinding)
- MCP servers: 1 (planning-skills)
- Stars: 3
- Repository created: 2026-04-17
- Repository last pushed: 2026-09-30
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/planning-skills-for-agents-and-humans
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What planning-skills-for-agents-and-humans does, in the publisher's words

Turn a fuzzy feature into a selected, testable, vertically sliced implementation packet, without letting the agent invent scope.

These skills help product and engineering teams preserve intent from raw evidence through implementation. They are most useful for strategically important feature work with a bounded appetite, usually a 2 to 6 week bet for a small launch team.

New here? Start with the 10-minute guide.

- there are several plausible ways to solve the problem
- you already have a solution idea but do not yet know which needs or constraints it truly serves
- a prototype looks promising, but you do not yet understand how it should behave
- an agent is about to modify a real codebase

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/mattlane66/planning-skills-for-agents-and-humans/HEAD/README.md

## MCP servers

- planning-skills: transport: streamable-http; url: https://planning-skills-mcp-production.up.railway.app/mcp

Read from the plugin's own mcp.json. Environment variable names only, never values.