By mnfst-ai
Artful Making skills for vibe coders. 11 skills across the Shape-to-Stage flow cycle — shape your spec, brief it, stage it clean. The mirror never goes dark.
Stop and check whether the work in progress is still coherent — still pointing at the original intent, still serving the right user, still worth building in this form. Use this skill when a builder senses something is off but can't name it, feels like the work has drifted, wants to reset before continuing, asks "are we still on track," "does this still make sense," or "should we keep going." Also use at natural transition points — between chunks, after unexpected results from a coding tool, or whenever the plot feels lost mid-build. Can be run on any artifact: a prompt, a chunk, a PRD, a conversation, a set of cards. This is a lightweight gate — 2 minutes at any transition point. For the full shape/stage boundary synthesis with inline change suggestions and a staged spec, use Shape Brief instead. Part of the Stage Manager Artful Making Skill Library by Manifest AI.
Read the accumulated output from one or more shape skills (Find the Holes, Collapsed Options, Risk Sequence, Soul Check) and synthesize findings into a ranked top-three problem areas with suggested fixes — then generate inline change suggestions for the builder to accept or reject, produce a Stage_Manager_Brief.md handoff document, and write an updated spec as [original-filename]-Staged.md ready for /ce:brainstorm, /ce:work, /ce:plan, or Superpowers. Use when a builder has run one or more shape skills and wants to move forward without manually synthesizing the output themselves. Also use when a builder says "brief this," "synthesize the shape," "what are the top problems," or "I'm ready to hand off." Part of the Stage Manager Artful Making Skill Library by Manifest AI.
Analyze a PRD, MRD, architecture doc, prompt, or prototype for places where the builder has already committed to a typical solution without knowing it — especially when they are trying to push the envelope on something. Use this skill when a vibe coder asks "am I thinking too small," "are there better approaches," "what are my options before I build this," "am I moving too fast," or wants to protect a breakthrough idea from being averaged down by safe, default choices. Also use when transitioning from prototype to production. Part of the Stage Manager Artful Making Skill Library by Manifest AI.
Analyze a PRD, MRD, architecture doc, or prompt for specification gaps where coding tools will invent behavior on their own. Use this skill whenever a vibe coder or builder asks to "find the holes," "review my spec," "what will the AI fill in," "check my PRD," or wants to identify underspecified areas before handing work to Claude Code, Cursor, Replit, or any agentic coding tool. Part of the Stage Manager Artful Making Skill Library by Manifest AI.
Analyze a PRD, MRD, architecture doc, design doc, or prompt for the load-bearing assumptions — the things that, if wrong, make everything downstream irrelevant. Use this skill when a vibe coder wants to know what to build first, asks "what could go wrong," wants to sequence work to surface the riskiest assumptions early, is worried about building the wrong thing, or wants to apply lean startup or Jobs to Be Done thinking before committing to a full build. Also use before writing prompts for Claude Code, Cursor, or Replit to ensure the highest-risk work gets proven before the lower-risk work gets built. Part of the Stage Manager Artful Making Skill Library by Manifest AI.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
How you move through your work is what you build.
A free, open collection of 11 skills for vibe coders who want to stay the author while building with AI tools.
These skills help you expand options before converging, maintain coherence across a build, and keep the soul of the work intact while Claude Code, Cursor, Replit, or any agentic coding tool runs at speed.
Use this if you just want the 11 Stage Manager skills as slash commands in Claude Code.
git clone https://github.com/Mnfst-AI/Stage_Manager_Skills.git
cd Stage_Manager_Skills
bash install.sh
Use this if you want the full stack — Stage Manager skills plus the CE pipeline with Stage Manager gates woven into every phase.
Works whether or not you already have Compound Engineering installed.
git clone https://github.com/Mnfst-AI/Stage_Manager_Skills.git
cd Stage_Manager_Skills
bash install-enhanced-ce.sh
The installer will:
~/.claude/commands/ce.backup/To roll back to stock CE: cp ~/.claude/commands/ce.backup/* ~/.claude/commands/ce/
Use this if you're running Superpowers and want Stage Manager shaping skills available in the same session.
git clone https://github.com/Mnfst-AI/Stage_Manager_Skills.git
cd Stage_Manager_Skills
bash install-superpowers.sh
The installer will:
~/.claude/skills/The workflow with Superpowers: Run Stage Manager shape skills to shape and brief your spec, then hand the Stage_Manager_Brief.md and your staged spec to Superpowers for planning and execution.
Compound Engineering is a methodology and Claude Code plugin from Every, created by Kieran Klaassen and Dan Shipper. It inverts the typical accumulation of technical debt — each unit of engineering work makes the next unit easier.
CE provides five commands: /ce:brainstorm, /ce:plan, /ce:work, /ce:review, /ce:compound.
Superpowers is an open-source agentic framework by Jesse Vincent that enforces professional development workflows — TDD, parallel sub-agents, structured planning — in Claude Code. 94,000+ GitHub stars and in the official Anthropic marketplace.
Stage Manager and Superpowers are complementary: Stage Manager shapes your spec before Superpowers executes it. Shape first. Stage second.
Shape skills (any combo)
→ /sm:shape:brief
→ Inline change suggestions (accept/reject)
→ Stage_Manager_Brief.md + [Spec_Name]-Staged.md
→ CE (/ce:brainstorm, /ce:plan, /ce:work)
or Superpowers
| CE Phase | Stage Manager Gate |
|---|---|
| Brainstorm | Coherence Check at close |
| Plan | Find the Holes + Risk Sequence before work begins |
| Work | Prompt Craft before coding, Live Mirror after each session |
| Review | Decision Capture — full manifest of tool-made choices |
| Compound | Soul Check — ensures documented learning reflects original intent |
Stage Manager runs before Superpowers. The Stage_Manager_Brief.md and [Spec_Name]-Staged.md it produces become the input to Superpowers brainstorming and planning — pre-loaded with resolved spec holes, accepted fixes, open questions the builder hasn't decided, and explicit guardrails for what the agent must not decide silently.
npx claudepluginhub mnfst-ai/stage_manager_skills --plugin stage-managerArtful Making skills for vibe coders. 16 skills across the Shape-to-Stage flow cycle — shape your spec, validate your premise, brief it, stage it clean. The mirror never goes dark.
Compound Engineering workflow: PRD-driven sprints, isolated worktrees, hook-enforced safety, automated learning. Skills become /vini-workflow:plan, /vini-workflow:compound, etc.
AI-powered development tools for code review, research, design, and workflow automation.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Plan and autonomously build a software task end-to-end. Recons the codebase, applies preloaded memory, decomposes into the right number of phases, gets one confirmation, then prepares a single ready-to-paste /goal command — one paste between you and done — that drives execution to completion with built-in retry, fix-spec recovery, and per-phase memory writeback. Works on Claude Code and Codex.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.