Using Superpowers
farm-fe/farm
A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Generate targeted clarifying questions (2-3 max) that challenge vague requirements and extract missing context.
Install Clarification Protocol
$ npx skills add alirezarezvani/claude-cto-team --skill clarification-protocol -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install alirezarezvani/claude-cto-team clarification-protocol --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/alirezarezvani/claude-cto-team.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/clarification-protocol .claude/skills/clarification-protocol && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "clarification-protocol" agent skill from https://github.com/alirezarezvani/claude-cto-team/tree/main/skills/clarification-protocol into .claude/skills/clarification-protocol/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clarification-protocol", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/alirezarezvani/claude-cto-team/tree/main/skills/clarification-protocolType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add alirezarezvani/claude-cto-team --skill clarification-protocol -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install alirezarezvani/claude-cto-team clarification-protocol --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alirezarezvani/claude-cto-team.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/clarification-protocol .agents/skills/clarification-protocol && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "clarification-protocol" agent skill from https://github.com/alirezarezvani/claude-cto-team/tree/main/skills/clarification-protocol into .agents/skills/clarification-protocol/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clarification-protocol", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add alirezarezvani/claude-cto-team --skill clarification-protocol -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install alirezarezvani/claude-cto-team clarification-protocol --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alirezarezvani/claude-cto-team.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/clarification-protocol .cursor/skills/clarification-protocol && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "clarification-protocol" agent skill from https://github.com/alirezarezvani/claude-cto-team/tree/main/skills/clarification-protocol into .cursor/skills/clarification-protocol/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clarification-protocol", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/alirezarezvani/claude-cto-team.git --path skills/clarification-protocol--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add alirezarezvani/claude-cto-team --skill clarification-protocol -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install alirezarezvani/claude-cto-team clarification-protocol --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alirezarezvani/claude-cto-team.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/clarification-protocol .gemini/skills/clarification-protocol && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "clarification-protocol" agent skill from https://github.com/alirezarezvani/claude-cto-team/tree/main/skills/clarification-protocol into .gemini/skills/clarification-protocol/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clarification-protocol", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install alirezarezvani/claude-cto-team clarification-protocolInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add alirezarezvani/claude-cto-team --skill clarification-protocol -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/alirezarezvani/claude-cto-team.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/clarification-protocol .github/skills/clarification-protocol && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "clarification-protocol" agent skill from https://github.com/alirezarezvani/claude-cto-team/tree/main/skills/clarification-protocol into .github/skills/clarification-protocol/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clarification-protocol", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add alirezarezvani/claude-cto-team --skill clarification-protocol -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install alirezarezvani/claude-cto-team clarification-protocol --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alirezarezvani/claude-cto-team.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/clarification-protocol .opencode/skills/clarification-protocol && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "clarification-protocol" agent skill from https://github.com/alirezarezvani/claude-cto-team/tree/main/skills/clarification-protocol into .opencode/skills/clarification-protocol/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clarification-protocol", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
clarification-protocol- GitHub stars
- 117
- Token cost
- ~1.9k tokens
- SKILL.md length
- 555 words
- Files
- 3
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- MIT
At a glance
Generate targeted clarifying questions (2-3 max) that challenge vague requirements and extract missing context.
- Works in 10 steps: Maximum 2-3 Questions Per Round → Challenge Mode, Not Interview Mode → Provide Example Answers → …
- Tasks that involve Requirements gathering
- SKILL.md covers When to Use, Core Principles, Question Generation Framework and Output Format, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Clarification Protocol is an agent skill from alirezarezvani/claude-cto-team. Generate targeted clarifying questions (2-3 max) that challenge vague requirements and extract missing context. Use after request-analyzer identifies clarification needs, before routing to specialist agents. Helps cto-orchestrator avoid delegating unclear requirements.
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `challenge-patterns.md` and `question-templates.md`).
It sits in Agent Workflows, covering Requirements gathering. The repository describes itself as: Your personal CTO Team for Claude Code . These Subagents will help you challenging yourself while you plan and execute. The licence is MIT.
When your agent uses it
- Tasks that involve Requirements gathering
Example prompts
- “/clarification-protocol”
Workflow steps
10 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit a5bbb78. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Clarification Protocol loads about 1.9k tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 555 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from alirezarezvani/claude-cto-team at commit a5bbb78, republished under its MIT licence (© alirezarezvani). 555 words, ~1,864 tokens.
Download SKILL.mdSave it as
.claude/skills/clarification-protocol/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- clarification-protocol
- description
- Generate targeted clarifying questions (2-3 max) that challenge vague requirements and extract missing context. Use after request-analyzer identifies clarification needs, before routing to specialist agents. Helps cto-orchestrator avoid delegating unclear requirements.
Clarification Protocol
Generates focused, challenging questions to extract missing context and clarify vague requirements before routing to specialist agents.
When to Use
- After request-analyzer identifies vague terms or missing context
- When requirements are ambiguous and could lead to wrong solutions
- Before delegating to cto-architect or strategic-cto-mentor
- When buzzwords need to be translated into specific requirements
Core Principles
1. Maximum 2-3 Questions Per Round
Users lose patience with long questionnaires. Prioritize ruthlessly:
- Ask only what's blocking progress
- Combine related questions
- Defer nice-to-have information
2. Challenge Mode, Not Interview Mode
Don't just ask—challenge assumptions:
- Bad: "What scale do you need?"
- Good: "You mentioned 'scalable'—are we designing for 10K users or 10M? That changes the architecture significantly."
3. Provide Example Answers
Help users understand what you're looking for:
- Bad: "What's your timeline?"
- Good: "What's your timeline? For context, a robust MVP typically takes 8-12 weeks with a team of 4."
Question Generation Framework
Step 1: Prioritize Missing Information
Rank by impact on routing and design:
| Priority | Category | Examples |
|---|---|---|
| P0 | Blocking | Can't proceed without this (e.g., "What problem does AI solve here?") |
| P1 | High Impact | Significantly changes approach (e.g., "1K or 100K users?") |
| P2 | Medium Impact | Affects details but not direction (e.g., "Budget range?") |
| P3 | Nice to Have | Can be discovered later (e.g., "Preferred cloud provider?") |
Ask P0 first, then P1. Defer P2/P3.
Step 2: Select Question Type
| Type | When to Use | Template |
|---|---|---|
| Scope | Vague feature description | "When you say [X], do you mean [A] or [B]?" |
| Scale | Missing numbers | "What scale are we designing for? [X] users? [Y] requests/second?" |
| Timeline | Vague deadlines | "What's the actual deadline? Is there flexibility if scope changes?" |
| Constraint | Unknown limitations | "Are there constraints I should know about? Budget, team size, existing systems?" |
| Success | Unclear goals | "How will we know this succeeded? What metrics matter?" |
Show full SKILL.md (259 more words)Show less
Step 3: Frame as Challenge
Transform neutral questions into challenging ones:
| Neutral (Weak) | Challenge (Strong) |
|---|---|
| "What do you mean by AI-powered?" | "'AI-powered' can mean many things—are you trying to classify data, generate content, or make predictions? What specific problem are you solving?" |
| "What's your budget?" | "Knowing budget helps me avoid over-engineering. Are we optimizing for < $5K/month or is $50K/month acceptable for the right solution?" |
| "How many users?" | "You mentioned 'scale'—I want to avoid designing for problems you don't have. How many users today, and what's realistic in 12 months?" |
Output Format
## Clarification Needed
Before I route this to the appropriate specialist, I need to understand a few things:
### Challenge 1: [Vague Term/Concept]
[Direct challenge statement]
**Question**: [Specific question]
**Why this matters**: [Impact on design/routing]
**Example answers**:
- Option A: [example] → leads to [approach]
- Option B: [example] → leads to [different approach]
### Challenge 2: [Missing Context]
[...]
---
Once you clarify these points, I'll route to [suggested agent] with a clear brief.Question Templates by Category
See question-templates.md for comprehensive templates.
See challenge-patterns.md for examples of turning neutral questions into challenges.
Examples
Example 1: AI Feature Request
User Request: "We want to add AI capabilities to improve customer experience"
Clarification Output:
## Clarification Needed
Before I route this to cto-architect, I need to understand what "AI capabilities" means for your use case:
### Challenge 1: Vague AI Requirement
"AI capabilities" could mean anything from a chatbot to predictive analytics. I don't want to design the wrong solution.
**Question**: What specific customer problem are you trying to solve with AI?
**Why this matters**: A recommendation engine has completely different architecture than a support chatbot.
**Example answers**:
- "Customers can't find products" → Recommendation engine / search improvement
- "Support tickets are overwhelming" → AI-assisted ticket routing or chatbot
- "Churn is high" → Predictive analytics for at-risk customers
### Challenge 2: Missing Scale
**Question**: How many customers are we talking about? And how many interactions per day would this AI feature handle?
**Why this matters**: 1,000 daily interactions vs 1,000,000 changes whether we use a simple API call or need dedicated ML infrastructure.
---
Once you clarify these points, I'll route to cto-architect with a clear brief for the appropriate AI architecture.Example 2: Scaling Concerns
User Request: "Our app needs to scale better"
Clarification Output:
## Clarification Needed
"Scale better" is a symptom—I need to understand the disease before prescribing treatment.
### Challenge 1: What's Actually Broken?
**Question**: What specific scaling issue are you experiencing? Slow page loads? Database timeouts? High infrastructure costs? All of the above?
**Why this matters**: Scaling a slow database is different from scaling a CPU-bound API.
**Example answers**:
- "Page loads take 5+ seconds at peak" → Likely caching/CDN solution
- "Database queries timing out" → Database scaling or query optimization
- "AWS bill doubled last month" → Cost optimization vs actual scaling
### Challenge 2: Current vs Target Scale
**Question**: What's your current traffic, and what do you need to support? Be specific: requests per second, concurrent users, data volume.
**Why this matters**: "Scale" at 10K users looks very different from "scale" at 10M users. I don't want to over-engineer.
---
Once I understand the specific bottleneck, I'll route to the appropriate specialist.Anti-Patterns to Avoid
1. The Interrogation
Bad: Asking 10 questions at once Good: Max 2-3 targeted questions
2. The Open-Ended Trap
Bad: "Tell me more about your requirements" Good: "Is this for internal users (hundreds) or external customers (thousands+)?"
3. The Assumption Question
Bad: "What microservices architecture do you want?" (assumes microservices) Good: "What's your current architecture, and what's driving the need to change?"
4. The Jargon Barrier
Bad: "What's your CAP theorem preference for the distributed system?" Good: "If the system goes offline briefly, should it prioritize consistency (everyone sees the same data) or availability (the system stays up)?"
References
- Question Templates - Ready-to-use question templates by category
- Challenge Patterns - Examples of effective challenge framing
© alirezarezvani, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files in skills/clarification-protocol of alirezarezvani/claude-cto-team.
- SKILL.md
- challenge-patterns.md
- question-templates.md
Open the folder on GitHubat commit a5bbb78
Compare with similar skills
Clarification Protocol next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Clarification Protocol this skillalirezarezvani/claude-cto-team | 117 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Using Superpowersfarm-fe/farm | 5.6k | 35 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Interview Meaddyosmani/agent-skills | 103k | 6 repos | ~3.8k | Automated safety check: Pass | MIT | |
| Grillingpietheinstrengholt/rssmonster | 564 | 32 repos | ~510 | Automated safety check: Pass | MIT | |
| Agentic Workflow Designerdotnet/Open-XML-SDK | 4.6k | 2 repos | ~3.5k | Automated safety check: Pass | MIT | |
| Ask User QuestionMemTensor/MemOS | 12k | — | ~1k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Interview Me
addyosmani/agent-skills
Asks one question at a time, each with a best guess attached, until the agent is about 95 percent sure what you really want, before any plan, spec or code.
Grilling
pietheinstrengholt/rssmonster
Grill the user relentlessly about a plan, decision, or idea.
- Official
Agentic Workflow Designer
dotnet/Open-XML-SDK
Interviews you one question at a time about goal, trigger, permissions and data needs, then drafts a single agentic workflow markdown file.
Ask User Question
MemTensor/MemOS
Shows a question as a modal in the interface to clarify a task, collect a preference or get approval, since the user cannot see terminal output.
Brainstorming Before Building
jnMetaCode/superpowers-zh
Turns a rough idea into an approved design before any code is written, sorting the request into spike, bounded or architectural and enforcing an approval gate.
More from alirezarezvani/claude-cto-team
All 12 skills in this repoAntipattern Detector
alirezarezvani/claude-cto-team
Detect common technical and organizational anti-patterns in proposals, architectures, and plans.
Architecture Pattern Selector
alirezarezvani/claude-cto-team
Recommend architecture patterns (monolith, microservices, serverless, modular monolith) based on scale, team size, and constraints.
Assumption Challenger
alirezarezvani/claude-cto-team
Identify and challenge implicit assumptions in plans, proposals, and technical decisions.
Cost Estimator
alirezarezvani/claude-cto-team
Infrastructure and development cost estimation for technical projects.
ML Cv Specialist
alirezarezvani/claude-cto-team
Deep expertise in ML/CV model selection, training pipelines, and inference architecture.
Request Analyzer
alirezarezvani/claude-cto-team
Analyze incoming user requests to detect intent, request type (design/validate/debug/document), complexity level, and identify vague requirements or buzzwords that need clarification.
Related
Categories
Questions about Clarification Protocol
What does Clarification Protocol do?
Generate targeted clarifying questions (2-3 max) that challenge vague requirements and extract missing context. Clarification Protocol is an agent skill from alirezarezvani/claude-cto-team. Generate targeted clarifying questions (2-3 max) that challenge vague requirements and extract missing context.
When should I use Clarification Protocol?
Clarification Protocol fits situations like: tasks that involve Requirements gathering.
How do I install Clarification Protocol in Claude Code?
Run `npx skills add alirezarezvani/claude-cto-team --skill clarification-protocol -a claude-code`. Or copy the skill folder (skills/clarification-protocol in alirezarezvani/claude-cto-team) into .claude/skills/clarification-protocol in your project. Claude Code loads it when a task matches its description.
How do I install Clarification Protocol in Codex?
Run `npx skills add alirezarezvani/claude-cto-team --skill clarification-protocol -a codex`. Or copy the skill folder (skills/clarification-protocol in alirezarezvani/claude-cto-team) into .agents/skills/clarification-protocol in your project. Codex loads it when a task matches its description.
Can I use Clarification Protocol in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add alirezarezvani/claude-cto-team --skill clarification-protocol -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/clarification-protocol, .gemini/skills/clarification-protocol, .github/skills/clarification-protocol and .opencode/skills/clarification-protocol in your project.
What does Clarification Protocol need to run?
SKILL.md names no scripts, command-line tools or credentials: Clarification Protocol is instructions for the agent only.
Does Clarification Protocol access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Clarification Protocol safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Clarification Protocol use?
Clarification Protocol is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Clarification Protocol use?
About 1.9k tokens (SKILL.md is roughly 7.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Clarification Protocol?
Skills that share tags, products or a category with Clarification Protocol: Using Superpowers (farm-fe/farm, 5.6k stars), Interview Me (addyosmani/agent-skills, 103k stars), Grilling (pietheinstrengholt/rssmonster, 564 stars) and Agentic Workflow Designer (dotnet/Open-XML-SDK, 4.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Clarification Protocol?
alirezarezvani (a GitHub user) maintains it in alirezarezvani/claude-cto-team, which has 117 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on December 18, 2025.
Source: alirezarezvani/claude-cto-team on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.