Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+22 moreClaude CodeCursorCodex CLIMuseDots
OpenClaw
Manus
Grok
Grok Bot+18 agentsStudio OS — AI Product Development Workflow
Guide your AI agent from idea and brief to architecture, development, and verified delivery.
Free
Studio OS — AI Product Development Workflow
Example session with this skill installed
Use Studio OS to explore a product idea: a simple app for freelance designers to track client feedback and see which revisions are still unresolved. Start with the product discussion and brief before architecture or coding.
- Read your context and instructions
- Compiled the studio os
Illustrative opening interaction
This example shows the first product conversation, not a recorded end-to-end build or a claim that files have already been created.
Stage: Interview · New product
My initial understanding is that freelance designers need one place to collect client feedback, connect it to the relevant deliverable, and see which revision requests still need attention.
| Area | Initial understanding | To clarify |
|---|---|---|
| Primary user | A freelance designer managing client revisions | Solo use or collaboration with other designers? |
| Problem | Feedback is scattered and unresolved requests are easy to miss | Where does feedback arrive today? |
| Desired result | A clear view of outstanding revision requests | What would make a first version useful in a real project? |
| Product scope | Still under discussion | We have not chosen accounts, integrations, or a technology stack. |
Is this understanding correct? Describe the last project where feedback became difficult to manage: how did it arrive, and what got lost or delayed?
What follows: clarify the problem and constraints, then record an agreed brief with scope and acceptance criteria. Architecture and implementation follow the selected workflow once those decisions are sufficiently clear.
Connects securely to your tools. The creator never sees your data.
About this skill
Bring an idea. Build with a product studio.
Studio OS gives your AI coding agent a structured product workflow: understand the problem, agree on scope, design the solution, implement it, and verify the result. It works with new ideas, existing codebases, and ongoing feature work.
What you get
- Discovery and briefing: product goals, user scenarios, scope, and acceptance criteria before implementation.
- Architecture and delivery planning: decisions, contracts, task ownership, and dependencies.
- Project memory: decisions and progress stored in your project so work can continue across sessions.
- Native subagent orchestration: bounded delegation when your host provides and permits it, with a single-agent fallback.
- Validation and QA: evidence, unresolved issues, and release readiness recorded separately from implementation progress.
- The Studio OS 0.7.0 runtime, workflows, templates, and public documentation.
Start with a request
“Use Studio OS to develop my product idea. Start by understanding the problem and agreeing on the brief.”
For an existing project, tell the agent which workspace to use and what you want to change. Studio OS selects the appropriate starting stage.
Requirements and delivery
Use an agent that can read and write your project files and run the checks your project needs. For Agensi MCP delivery, the entry point reads the required runtime instructions over HTTPS from an immutable commit of the author's public GitHub repository. Your project files are not uploaded to GitHub by this adapter. Chat-only agents without workspace access cannot run the full workflow.
This Agensi adapter is an initial integration. Package structure and source retrieval are checked separately from a full marketplace-to-agent run; compatibility with every agent or model is not claimed. Subagent model choice depends on the host. Model/API usage is separate, and token savings are not guaranteed.
Open source
Studio OS is free and MIT-licensed. This is the original author's distribution of the public project: https://github.com/Aleksei2507/studio-os. The optional local admin panel requires a local Studio OS installation and Node.js; it does not run directly from streamed MCP instructions.
What's included (21 skills in this plugin)
studio-os
Guide product work from an idea or existing codebase through discovery, briefing, architecture, development, validation, and release. Use when the user asks to start, resume, or deliver a project through Studio OS. Requires an agent with project file access; remote delivery also requires HTTPS access to public GitHub files.
studio-os
Run an adaptive, model-independent product studio workflow for new ideas, existing codebases, and bounded product changes. Use when the user asks Studio OS to start, continue, research, plan, design, build, validate, release, or evolve product work. Activate before the host agent plans implementation or edits product files.
studio-os
Run Studio OS for a new product idea, existing codebase, or ongoing Studio OS project. Use whenever the user asks Studio OS to start, resume, research, plan, design, build, fix, validate, release, or continue product work. Activate before the host agent makes its own implementation plan, selects technical skills, or edits product files. Also use for explicit Studio OS skill invocation, including $studio-os or /studio-os:studio-os.
architecture
Translate an accepted Project Brief, roadmap, and existing codebase constraints into technical architecture, ADRs, and an evidence-bounded delivery estimate. Use after Planning or conditionally for a Work Item that changes accepted technical boundaries, before Interface Design or Development.
briefing
Turn accepted product understanding into product decisions, scope, scenarios, and acceptance criteria. Use after Discovery or for a Feature Work Item when product scope or expected behavior is not already clear.
brownfield
Analyze an existing codebase without Project Memory and create evidence-based onboarding artifacts, including observed standards and design-system profiles. Use when meaningful source code exists but the project has no .studio directory.
design-strategy
Define the product's user experience, interaction model, trust requirements, and visual direction before Planning, Architecture, and detailed Interface Design. Use conditionally when experience decisions materially affect product value or usability.
development
Implement one accepted roadmap increment, Feature, Bugfix, or Refactor within confirmed product scope, architecture, and interface design. Use after all selected preparation stages, including Task Decomposition, when code changes are authorized and required capabilities are available.
discovery
Turn Interview context into product understanding, risks, constraints, and success criteria. Use after Interview in a Greenfield workflow or when accepted product understanding must be revised.
evolution
Analyze explicit Studio OS project retrospectives and create evidence-based local improvement proposals. Use only when the user asks to evolve Studio OS and provides or is asked for project paths.
interface-design
Turn accepted product experience and architecture decisions into an implementation-ready interface specification and design system. Use conditionally after Architecture for new or materially changed web, mobile, or desktop interfaces before Development.
interview
Understand a new product idea and prepare a concise handoff to Discovery. Use as the first Runtime in the Greenfield workflow when the user has an idea but no existing product codebase.
planning
Turn an accepted Project Brief into a value-oriented Product Roadmap or Brownfield Development Roadmap. Use when scope and acceptance criteria are confirmed and sequencing decisions are needed.
product-outcome
Independently compare an accepted product milestone or Work Item outcome with delivered evidence. Use after QA to decide whether the target is ready for Release, requires another roadmap increment, is blocked, or needs explicit re-scoping.
qa
Evaluate a validated increment against accepted user scenarios, product scope, UX expectations, and acceptance criteria. Use after technical Validation and before Product Outcome or Release.
release
Decide release readiness, prepare release notes and operational safeguards, and execute external release actions only with explicit authorization. Use after Product Outcome PASS for lifecycle or Feature targets, or after sufficient Validation and QA evidence for workflows that do not select Product Outcome.
research
Investigate current market, competitor, domain, regulatory, monetization, or technical evidence that may change a Studio OS product decision. Use conditionally from Greenfield or Brownfield workflows, or as the execution stage of a Research Work Item.
retrospective
Capture objective observations and user feedback about a completed Studio OS project, stage, or Work Item. Use after delivery when the user chooses to review the Studio OS process.
task-decomposition
Turn accepted Architecture, Roadmap, and Acceptance Criteria into a bounded, estimable, requirement-traced task list. Use after Architecture and before Development when the accepted scope needs more than one estimable, independently completable unit.
validation
Run reproducible technical checks for a completed increment and report objective PASS, FAIL, BLOCKED, or PARTIAL evidence. Use after Development and before product QA.
work-item
Classify and initialize a bounded change in an existing Studio OS project, then select the Feature, Bugfix, Research, or Refactor workflow. Use when .studio exists and the user asks to add, fix, investigate, or restructure something.
How to use
Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scanned
Verified clean 1 day ago
- Free to download with an account
Requires
Node.js
Python
Git