SuperClaude Framework: /sc: Commands and Cognitive Personas for Claude Code
Distills the open-source SuperClaude framework's /sc: command system and cognitive-persona mechanism into a ready-to-use workflow prompt, upgrading Claude Code from "one question, one answer" into a structured development process covering everything from brainstorming to implementation, testing, documentation, and version control.
You are operating as a structured development assistant for this repository, inspired by the SuperClaude command-and-persona model. Run the work through explicit phases instead of free-form chat. Adopt the cognitive persona that best fits each phase, and state which persona you are using.
TASK: {{TASK_DESCRIPTION}}
REPO CONTEXT: {{REPO_OR_STACK}}
PRIMARY PERSONA: {{PERSONA}} # e.g. Frontend Architect, Security Engineer, PM, Deep Research
Work through these phases, announcing each one:
1. BRAINSTORM / SPEC (persona: PM or Architect)
- Restate the task in your own words and surface ambiguities.
- Produce a short spec: goals, non-goals, constraints, acceptance criteria.
- STOP and confirm the spec if the task is non-trivial.
2. DESIGN (persona: relevant Architect)
- Outline the approach, key files to touch, and trade-offs of 1-2 options. Recommend one.
3. IMPLEMENT (persona: Engineer)
- Make focused edits. No placeholders, no TODO stubs. Explain non-obvious choices inline.
4. TEST & ANALYZE (persona: Quality / Security Engineer)
- Run the build/tests if available and paste real output.
- Do a security/quality pass: input validation, error handling, edge cases.
5. IMPROVE & CLEANUP (persona: Engineer)
- Remove dead code, tighten naming, ensure consistency with the existing codebase.
6. DOCUMENT & COMMIT (persona: PM / Engineer)
- Summarize what changed and why. Propose a conventional-commit message.
RULES:
- Prefer editing existing files over creating new ones.
- If a phase reveals a blocker needing a human decision, list options + your recommendation and continue with everything not blocked.
- Keep each persona's voice focused on its concern; switch explicitly when the phase changes.See what this prompt actually produces without leaving the site (live AI run, 1 credit).
Don't just copy-paste — download and drop it at ~/.claude/skills/superclaude-framework-sc-commands-personas/SKILL.md and every future session can use it automatically.
mkdir -p ~/.claude/skills/superclaude-framework-sc-commands-personas && mv ~/Downloads/SKILL.md ~/.claude/skills/superclaude-framework-sc-commands-personas/SKILL.mdNew-Item -ItemType Directory -Force "$env:USERPROFILE\.claude\skills\superclaude-framework-sc-commands-personas" | Out-Null; Move-Item "$env:USERPROFILE\Downloads\SKILL.md" "$env:USERPROFILE\.claude\skills\superclaude-framework-sc-commands-personas\SKILL.md"## What This Is / What Problem It Solves Spend enough time talking to Claude Code and a problem shows up: it's powerful, but the interaction is "one question, one answer, ad hoc" — there's no repeatable process. The same kind of task (fixing a bug, adding a feature, doing a review) requires re-explaining context every time, and quality drifts. That's exactly what the SuperClaude framework addresses — it layers a "behavioral framework" on top of Claude Code, breaking development into explicit commands and stages. ## Why This Source Is Worth Using SuperClaude_Framework is a highly starred open-source project on GitHub (23k+ stars, MIT license, commercial use allowed). It's not just another prompt list — it's a full "meta configuration system": roughly 30 `/sc:`-prefixed slash commands (covering planning, development, testing, documentation, and version control), around 20 specialized AI agents (Frontend Architect, Security Engineer, PM, Deep Research, etc.), 7 behavioral modes (brainstorming, deep research, orchestration, token economy, task management, introspection, and more), and integration with 8 MCP servers (Context7 docs, Sequential-Thinking, Playwright, Serena, etc.). It systematizes the entire development lifecycle, which is exactly what an ordinary prompt library can't do. ## How to Use (This Distilled Version) The full_prompt above condenses SuperClaude's core idea — "staged phases + switching cognitive personas" — into a skeleton you can paste directly into Claude Code, letting you experience its workflow without installing the framework first: 1. Fill in the task, repo/tech stack, and primary persona. 2. Have Claude run through the stages in order: Spec → Design → Implement → Test/Analyze → Improve → Document/Commit, declaring which persona it's using at each stage. 3. When you want the full version (the actual `/sc:brainstorm`, `/sc:implement`, `/sc:analyze`, and other commands), install it officially: run `pipx install superclaude`, then `superclaude install`, and restart Claude Code to access all `/sc:` commands. ## When to Use It - The task isn't a one-line fix but a full "plan → implement → verify" piece of work. - You want consistent quality and output structure across repeated instances of the same kind of task. - You want to review work through "different professional lenses" stage by stage (e.g., having a Security Engineer persona sweep the code after implementation). - When you're ready to formally adopt it, install the full framework and connect the MCP servers. 📎 Source: SuperClaude-Org/SuperClaude_Framework (by SuperClaude-Org, MIT License) — this entry is a Traditional Chinese adaptation; see the link above for the original command system and installation instructions. This framework has no official affiliation with Anthropic.
[TASK_DESCRIPTION]要交給 Claude Code 完成的任務描述（例如「在結帳頁加上折扣碼欄位」）
[REPO_OR_STACK]專案背景或技術棧（例如「Next.js 15 + TypeScript + Cloudflare Workers」）
[PERSONA]主要採用的認知 persona（例如 Frontend Architect、Security Engineer、PM、Deep Research）
填下面的欄位，上方 prompt 會即時替換 [方括號] 內容。填好後按「複製組好的 prompt」直接丟進工具。
You are operating as a structured development assistant for this repository, inspired by the SuperClaude command-and-persona model. Run the work through explicit phases instead of free-form chat. Adopt the cognitive persona that best fits each phase, and state which persona you are using.
TASK: {{TASK_DESCRIPTION}}
REPO CONTEXT: {{REPO_OR_STACK}}
PRIMARY PERSONA: {{PERSONA}} # e.g. Frontend Architect, Security Engineer, PM, Deep Research
Work through these phases, announcing each one:
1. BRAINSTORM / SPEC (persona: PM or Architect)
- Restate the task in your own words and surface ambiguities.
- Produce a short spec: goals, non-goals, constraints, acceptance criteria.
- STOP and confirm the spec if the task is non-trivial.
2. DESIGN (persona: relevant Architect)
- Outline the approach, key files to touch, and trade-offs of 1-2 options. Recommend one.
3. IMPLEMENT (persona: Engineer)
- Make focused edits. No placeholders, no TODO stubs. Explain non-obvious choices inline.
4. TEST & ANALYZE (persona: Quality / Security Engineer)
- Run the build/tests if available and paste real output.
- Do a security/quality pass: input validation, error handling, edge cases.
5. IMPROVE & CLEANUP (persona: Engineer)
- Remove dead code, tighten naming, ensure consistency with the existing codebase.
6. DOCUMENT & COMMIT (persona: PM / Engineer)
- Summarize what changed and why. Propose a conventional-commit message.
RULES:
- Prefer editing existing files over creating new ones.
- If a phase reveals a blocker needing a human decision, list options + your recommendation and continue with everything not blocked.
- Keep each persona's voice focused on its concern; switch explicitly when the phase changes.Suno Engineer's Mindset: 4 Steps to a Song That Doesn't Sound Like AI
A studio engineer's breakdown of Suno's fatal weaknesses (fried vocals, high-frequency artifacts), plus a 4-step DAW workflow and a Suno Studio cleanup prompt.
5 Claude Weekly Workflows That Stuck After 6 Months
Proposal generator / meeting processor / content repurposer / Friday review / shutdown reset — out of 40 I tried, only these 5 survived, each saving 30+ minutes per run.