Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Request Analyzer

ASecurity

Analyze incoming user requests to detect intent, request type (design/validate/debug/document), complexity level, and identify vague requirements or buzzwords that need clarification. Use when cto-orchestrator receives new requests that need classification before routing to specialist agents.

112 stars
0 votes
0 copies
22 views
Added 12/19/2025
ai-agentsgosqlnodedebuggingcode-reviewdatabasebackenddocumentation

Security Analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned 2/12/2026

$npx -y skills add alirezarezvani/claude-cto-team --skill request-analyzer --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Request Analyzer?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Request Analyzer
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/alirezarezvani-request-analyzer/badge)](https://www.skillsdirectory.com/skills/alirezarezvani-request-analyzer)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: request-analyzer
description: Analyze incoming user requests to detect intent, request type (design/validate/debug/document), complexity level, and identify vague requirements or buzzwords that need clarification. Use when cto-orchestrator receives new requests that need classification before routing to specialist agents.
---

# Request Analyzer

Classifies incoming requests to enable intelligent routing and identify clarification needs before delegating to specialist agents.

## When to Use

- When receiving a new user request that needs classification
- When determining which specialist agent should handle a request
- When identifying if requirements are too vague to proceed
- When detecting buzzwords that need to be challenged

## Analysis Framework

### Step 1: Detect Intent

Classify the primary intent:

| Intent | Indicators | Route |
|--------|------------|-------|
| **Strategic** | "roadmap", "strategy", "plan", "prioritize", "decide" | May need validation |
| **Implementation** | "build", "create", "implement", "design", "architect" | Design work |
| **Debugging** | "fix", "broken", "error", "slow", "not working" | Debug/investigate |
| **Documentation** | "document", "explain", "describe", "write docs" | Documentation |

### Step 2: Classify Request Type

| Type | Key Phrases | Primary Agent |
|------|-------------|---------------|
| **Design** | "How should I build...", "What architecture...", "Design a system..." | cto-architect |
| **Validate** | "Is this plan solid?", "Thoughts on...", "Review my roadmap..." | strategic-cto-mentor |
| **Debug** | "Why is X slow?", "Fix this error...", "Troubleshoot..." | debug-helper |
| **Document** | "Write documentation for...", "Explain how..." | docs-writer |
| **Review** | "Review this code...", "Check for issues..." | code-reviewer |

### Step 3: Assess Complexity

| Complexity | Characteristics | Execution Pattern |
|------------|-----------------|-------------------|
| **Single** | Clear scope, one domain, obvious routing | Direct to one agent |
| **Sequential** | Multiple phases, depends on previous output | Agent chain |
| **Parallel** | Independent domains, can run simultaneously | Multiple agents in parallel |

### Step 4: Identify Vague Terms

Scan for buzzwords that require clarification. See [buzzword-dictionary.md](buzzword-dictionary.md) for the complete list.

**Common red flags:**
- "AI-powered" - What specific AI capability?
- "scale" - What numbers? From what to what?
- "fast" / "soon" - What timeline exactly?
- "simple" - Simple for whom? What constraints?
- "modern" - What specific technologies?

### Step 5: Detect Missing Context

Check for required context based on request type:

**For Design Requests:**
- [ ] Expected user/traffic scale
- [ ] Budget constraints
- [ ] Timeline requirements
- [ ] Team size and expertise
- [ ] Existing infrastructure

**For Validation Requests:**
- [ ] Current state or existing plan
- [ ] Business goals and constraints
- [ ] Timeline and resources
- [ ] Success criteria

## Output Format

Provide analysis in this structure:

```
## Request Analysis

**Intent**: [strategic | implementation | debugging | documentation]
**Type**: [design | validate | debug | document | review]
**Complexity**: [single | sequential | parallel]

### Vague Terms Detected
- "[term]" - needs clarification: [what to ask]

### Missing Context
- [missing information item]

### Suggested Routing
**Primary Agent**: [agent name]
**Rationale**: [why this agent]

### Clarification Needed
[yes/no] - [brief explanation]

### Recommended Next Step
[what to do next - clarify or delegate]
```

## Examples

### Example 1: Vague Request

**User**: "I want to add AI capabilities to my app"

**Analysis**:
- **Intent**: Implementation
- **Type**: Design
- **Complexity**: Unknown (needs clarification)
- **Vague Terms**: "AI capabilities" - What specific problem are we solving?
- **Missing Context**: Scale, budget, timeline, team, existing stack
- **Clarification Needed**: Yes
- **Next Step**: Use clarification-protocol before routing

### Example 2: Clear Design Request

**User**: "Design a real-time notification system for 100K users, using our existing PostgreSQL database and Node.js backend"

**Analysis**:
- **Intent**: Implementation
- **Type**: Design
- **Complexity**: Single
- **Vague Terms**: None
- **Missing Context**: Timeline, budget (nice to have but not blocking)
- **Suggested Routing**: cto-architect
- **Clarification Needed**: No (can proceed with optional clarification)

### Example 3: Validation Request

**User**: "Here's my Q2 roadmap - migrate to microservices, add real-time features, and launch mobile app. Thoughts?"

**Analysis**:
- **Intent**: Strategic
- **Type**: Validate
- **Complexity**: Single
- **Vague Terms**: None
- **Missing Context**: Team size, current architecture state
- **Suggested Routing**: strategic-cto-mentor
- **Clarification Needed**: Mild (some context helpful but not blocking)

## References

- [Classification Criteria](classification-criteria.md) - Detailed routing logic
- [Buzzword Dictionary](buzzword-dictionary.md) - Common vague terms to challenge

Attribution

alirezarezvanialirezarezvani
View sourceSee grades on GitHubMore from alirezarezvani →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →