Openspec Superpowers Workflow

Community

SYZ-Coder

openspec-superpowers-workflow

Use when the user explicitly wants an OpenSpec-first path that creates proposal, design, specs, and tasks before handing off to Superpowers execution, verification, and optional archive, or when a follow-up turn is confirming or editing tasks that this workflow already generated.

Overview

Publisher	SYZ-Coder
Repository	`superpowers-openspec-team-skills`
Skill name	`openspec-superpowers-workflow`
Stars	200
Forks	54
Bundled files	3
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
3 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by SYZ-Coder on GitHub. Read the source before you install it.

Installation

Install the Openspec Superpowers Workflow AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/SYZ-Coder/superpowers-openspec-team-skills/tree/main/team-skills/openspec-superpowers-workflow
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/SYZ-Coder/superpowers-openspec-team-skills/tree/main/team-skills/openspec-superpowers-workflow

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/SYZ-Coder/superpowers-openspec-team-skills.git /tmp/superpowers-openspec-team-skills
mkdir -p .claude/skills
cp -r /tmp/superpowers-openspec-team-skills/team-skills/openspec-superpowers-workflow .claude/skills/openspec-superpowers-workflow

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Openspec Superpowers Workflow in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Openspec Superpowers Workflow on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Openspec Superpowers Workflow is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

OpenSpec + Superpowers Workflow

Overview

Use this skill as the OpenSpec-first feature delivery entrypoint. It creates and validates OpenSpec change artifacts first, then hands the completed task checklist to Superpowers for implementation planning, TDD, and verification.

This is an explicit opt-in workflow. Do not use it by default. Only use it when the user explicitly asks for this workflow, names this skill, or a repository policy explicitly requires it.

If .superpowers-memory/ exists in the repository, treat it as shared project memory: read it before planning and update it before closing the workflow.

Required Order

Run $openspec-feature-workflow first. Use it to clarify the change enough to create and complete proposal, design, specs, and tasks.
Stop OpenSpec apply-style execution after tasks.md is complete.
Present the generated OpenSpec task checklist to the user.
By default, wait for explicit confirmation before implementation planning starts.
After the user confirms tasks.md, pause once more and ask whether to continue execution development. Accept either 继续开发 or continue-dev as the explicit continuation command.
Do not route the confirmed task handoff through OpenSpec apply.
If the user chooses execution development, hand off to the Superpowers track for implementation planning, worktree setup, TDD, and verification.
After execution development completes, pause again and ask whether to continue code review. Accept either 继续审查 or continue-review as the explicit continuation command.
If the project uses OpenSpec archive flow and code, specs, and verification are aligned, archive the change as the final OpenSpec step. Before that final step, you may pause and ask whether to continue archive. Accept either 继续归档 or continue-archive as the explicit continuation command, or continue to use $openspec-archive-change.
Do not claim completion until verification evidence exists.
If .superpowers-memory/ exists, update CURRENT_STATE.md and add a short journal entry for the session outcome.

When to Use

The user explicitly asks for OpenSpec + Superpowers
The user explicitly names $openspec-superpowers-workflow
The user explicitly wants OpenSpec proposal/design/spec/tasks before implementation planning
The current turn is a follow-up that confirms, revises, or continues tasks.md that this workflow generated earlier in the same request
A repository policy explicitly requires this workflow

Continuation Gate

If this workflow already produced OpenSpec artifacts for the current request and the user is now confirming, revising, or continuing the generated tasks.md, keep this workflow active even if the user does not repeat the skill name.
Treat task edits or confirmation as a continuation turn, not as a fresh routing decision.
After the user confirms the task checklist, keep this workflow active, pause for the explicit execution-development prompt, and do not fall back to OpenSpec apply.
At that handoff, accept either 继续开发 or continue-dev as the continuation command.
If the user chooses execution development, resume at the next incomplete Superpowers stage: hand off to the Superpowers track, write the implementation plan, and continue with TDD and verification.
After execution development completes, ask whether to continue code review as a separate follow-up step.
At that later handoff, accept either 继续审查 or continue-review as the continuation command.
If the project uses archive flow and the work is aligned, a later archive handoff may accept either 继续归档 or continue-archive, while $openspec-archive-change remains valid.
If the user revises tasks instead of confirming them, update the OpenSpec task summary, confirm the revised checklist state if needed, then continue the same workflow rather than falling back to generic OpenSpec apply guidance.

Deliverables

OpenSpec change artifacts in openspec/changes/<change-name>/
Implementation plan in docs/superpowers/plans/
Code, tests, and fresh verification output
Archived OpenSpec change when archive flow is part of the project workflow
Updated Superpowers memory when .superpowers-memory/ is present

Guardrails

Do not skip OpenSpec artifacts for behavior changes
Do not use OpenSpec apply as the implementation stage for this combined workflow
After OpenSpec tasks.md is complete, stop OpenSpec apply-style execution, summarize the generated tasks, and by default ask the user to confirm the OpenSpec task checklist before the post-task handoff
Do not stop after OpenSpec artifacts with a readiness message such as "run apply", "/opsx:apply", or "let me start implementation"
Do not resume through OpenSpec apply after tasks.md is confirmed; the only allowed next-step prompt is whether to continue execution development
After the user confirms tasks.md, pause and ask whether to continue execution development
At that prompt, accept either 继续开发 or continue-dev
Do not continue directly into Superpowers execution after OpenSpec artifacts until the user has explicitly confirmed the generated tasks.md and chosen execution development as the next step
After Superpowers execution and verification complete, ask whether to continue code review
At that prompt, accept either 继续审查 or continue-review
If archive is the next step, accept either 继续归档 or continue-archive, while $openspec-archive-change remains usable.
Treat OpenSpec tasks as constraints and checklist input for the Superpowers implementation plan
Do not archive the change until code, tests, and specs are aligned
Do not skip worktree, TDD, or verification when the request includes them
Keep the skill portable: use repo-local paths and avoid machine-specific assumptions

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Openspec Superpowers Workflow AI skill do?

Why use Openspec Superpowers Workflow on TypingMind?

Because you install it once and use it with any model. Openspec Superpowers Workflow is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Openspec Superpowers Workflow in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/SYZ-Coder/superpowers-openspec-team-skills/tree/main/team-skills/openspec-superpowers-workflow. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Openspec Superpowers Workflow?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Openspec Superpowers Workflow?

As many as you like. As long as a model supports skills, you can use Openspec Superpowers Workflow with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Openspec Superpowers Workflow AI skill free?

Yes. It is published on GitHub by SYZ-Coder under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Block Kit

openclaw

OrganizationPopular

Use proactively for structured or interactive Slack replies, and when asked to author or validate native Slack Block Kit JSON.

1password

Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.

Apple Reminders

List, add, edit, complete, or delete Apple Reminders and reminder lists via remindctl.

Clawhub

Search ClawHub for skills when a requested capability is not already available; install, verify, update, uninstall, publish, or sync skills.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

OpenSpec + Superpowers Workflow

Overview

Required Order

When to Use

Continuation Gate

Deliverables

Guardrails

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now