speakmanai-cc · Skills Update

Your SDLC pipeline now starts before the architecture, and stops for a design review before the code.

By David Speakman ·

speakmanai-cc is the Claude Code skill layer for SPEAKMAN.AI: one skill per SDLC phase, each orchestrating a real multi-agent session and turning the result into something you actually keep. A document. A codebase. A mockup. A report. This update adds a phase on either end of the pipeline you already had, and gets the whole set onto Claude Desktop in a single upload.

pipeline.log — a run through this update /generate-project-brief -> brief.md, zero credits, zero MCP session /generate-sad -> Solution Architecture Document /generate-requirements -> domain model, use cases, API/DB schema /generate-ux-design -> screen inventory, flow diagrams, 4 mockups, human-approved
17
skills total, up from 14.
2
new SDLC phases. Idea intake, UX design.
1
upload gets you all 17 on Claude Desktop.
0
skills that needed sandbox-specific adaptation this round.
Phase 0 · Idea Intake

Coaching a raw idea into a brief, adapted from a workflow 50,000 contributors already trust.

/generate-project-brief runs entirely in Claude Code (no SPEAKMAN.AI session, no credits), coaching a pitch, a Slack thread, a meeting note, or a half-formed idea into a structured brief through guided discovery, in three modes: Create, Update, and Validate. Its coaching stance and audit-trail structure are adapted, not copied, from the product-brief workflow in BMAD-METHOD, an open source AI-driven development framework with a contributor community in the tens of thousands, used under BMAD-METHOD's MIT license.

The brief's own structure was built to be handed straight to Phase 1 or a sizing gate. No reformatting step, no glue code, no adapter, just a file path.

Phase 2.5 · UX Design

A design proposal before a single line of production code.

/generate-ux-design maps your architecture and requirements into a screen inventory, checks that every requirement traces to a real screen, then proposes a design direction and produces self-contained HTML mockups for the highest-priority screens. A real thing to react to, not a paragraph describing one. The mockup step runs through your own connected coding agent rather than a fixed background model, because design judgment is exactly where that choice matters most.

The review gate is a real one. The skill publishes every mockup individually and waits for your actual answer: approve, or describe exactly what to change and watch it revise in place, not start over.

Where This Sits

The full pipeline, phase by phase.

Idea Intake

/generate-project-brief New

A raw idea, coached into a structured brief. Zero credits, no MCP session.

Architecture

/generate-sad

Business description in, Solution Architecture Document out.

Requirements

/generate-requirements

Domain model, naming dictionary, use cases, API and DB schema.

UX Design

/generate-ux-design New

Screen inventory, flow diagrams, a proposed direction, and clickable mockups.

Code Generation

/generate-speakmanai-code

A working, milestone gated, git committed codebase.

Infrastructure

/generate-infrastructure

Terraform for GCP, AWS, and Azure, plus pre-pentest hardening.

Pentest & UAT

/pentest

A gated security engagement, run against the live staging build.

Run /sdlc-pipeline for a guided walkthrough that drives every phase in order and carries state between them, checkpointed so a multi-day build survives a closed laptop.

On Claude Desktop

One upload, not seventeen.

Claude Desktop's Cowork mode runs skills in Anthropic's own sandboxed VM, which can't reach a Claude Code install's asset directory. So every skill in the desktop bundle is fully self-contained rather than depending on a separate setup step. Both new skills needed zero adaptation to cross over: generate-project-brief only ever writes local files, and generate-ux-design only ever calls MCP tools and Claude's own rendering capability, so neither one touches anything sandbox-specific in the first place.

Plugin

All 17 skills, one upload, via Cowork → Settings → Plugins.

Fallback

No Cowork? Individual skills upload one at a time via Settings → Skills.

Same engine

Every skill talks to the same SPEAKMAN.AI MCP server Claude Code uses: local or hosted, your choice.

Version 1.3.0

Bumped from 14 skills to 17. See the plugin's own README for the update path.

Claude Code · Free · Open Source

Install the skills.

Clone the repo and run the install script, or grab the Claude Desktop plugin. Either way, you're running against your own SPEAKMAN.AI deployment.

The Engine Underneath

Run SPEAKMAN.AI locally, free.

These skills work against any SPEAKMAN.AI deployment. The local engine is MIT licensed, no account required.

Written by David Speakman. Speakman Consulting designs and builds this kind of system for growing organizations: agent workflows with the governance that keeps humans in the loop.