supabase
Handles the full Supabase workflow from schema changes to deployment, with built-in security guardrails that catch common traps like RLS...
disambiguate-requirements
Break vague requirements into precise business rules (BR-*), constraints (C-*), and formulas (F-*) for code generation. Orchestrates extraction of BR-*, C-*, F-* from REQ-*. Use after requirement-extraction to enable autogeneration.
Full skill instructions
Skill Type: Orchestrator (Requirements Refinement) Purpose: Transform vague requirements into precise BR-, C-, F-* specifications Prerequisites: REQ-* requirement exists but lacks detailed BR-, C-, F-*
You are disambiguating requirements to enable code autogeneration.
Your goal is to transform vague requirements into precise specifications:
This enables code autogeneration - precise specs → auto-generated code.
Example:
## <REQ-ID>: User Login
**Description**: Users can log in with email and password
**Acceptance Criteria**:
1. User enters credentials
2. System validates credentials
3. User gains access or sees error
Problem: Too vague for code generation!
Invoke: extract-business-rules skill
Questions to ask:
*Generated BR- for <REQ-ID>**:
Business Rules:
- BR-001: Email validation
- Format: regex ^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$
- Error: "Invalid email format"
- BR-002: Password requirements
- Minimum length: 12 characters
- Must contain: 1 uppercase, 1 lowercase, 1 number, 1 special char
- Error: "Password must be at least 12 characters with mixed case, number, and special char"
- BR-003: Failed attempt handling
- Max attempts: 3 per 15 minutes
- Lockout duration: 15 minutes
- Error: "Account locked. Try again in {remaining} minutes"
- BR-004: Email case sensitivity
- Emails are case-insensitive
- Store as lowercase
- Compare as lowercase
- BR-005: Password case sensitivity
- Passwords are case-sensitive
- No transformation on storage or comparison
Invoke: extract-constraints skill
Questions to ask:
*Generated C- for <REQ-ID>**:
Constraints:
- C-001: Database query timeout
- Max query time: 100ms
- Fallback: Return "Service temporarily unavailable"
- C-002: Session management
- Session timeout: 30 minutes of inactivity
- Token: JWT format
- Storage: Redis cache
- C-003: Password hashing
- Algorithm: bcrypt
- Cost factor: 12
- Library: bcrypt.js or bcrypt (Python)
- C-004: HTTPS required
- All login requests must be HTTPS
- Reject HTTP requests
- Redirect HTTP → HTTPS
- C-005: Rate limiting
- Max login attempts: 10 per minute per IP
- Behavior: Return 429 (Too Many Requests)
Invoke: extract-formulas skill
Questions to ask:
*Generated F- for <REQ-ID>**:
Formulas:
- F-001: Lockout expiry time
- Formula: lockout_expiry = last_attempt_time + (15 * 60) seconds
- Inputs: last_attempt_time (datetime)
- Output: lockout_expiry (datetime)
- F-002: Remaining lockout time
- Formula: remaining = max(0, (lockout_expiry - current_time) / 60) minutes
- Inputs: lockout_expiry (datetime), current_time (datetime)
- Output: remaining (int, minutes)
- F-003: Password strength score
- Formula: score = length_score + complexity_score + uniqueness_score
- Range: 0-100
- Thresholds: <50 weak, 50-75 medium, >75 strong
Add BR-, C-, F- to requirement*:
## <REQ-ID>: User Login with Email and Password
[Previous content...]
---
### Business Rules (BR-*)
**BR-001: Email validation**
- Format: regex `^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$`
- Case insensitive (store and compare as lowercase)
- Error message: "Invalid email format"
- Autogenerate: Yes (code generation from regex)
**BR-002: Password requirements**
- Minimum length: 12 characters
- Must contain: 1 uppercase, 1 lowercase, 1 number, 1 special char
- Case sensitive
- Error message: "Password must be at least 12 characters with mixed case, number, and special char"
- Autogenerate: Yes (validation function)
**BR-003: Failed attempt handling**
- Max attempts: 3 per 15 minutes
- Lockout duration: 15 minutes
- Reset on successful login
- Error message: "Account locked. Try again in {remaining} minutes"
- Autogenerate: Yes (lockout tracker class)
**BR-004: Email case sensitivity**
- Normalization: Convert to lowercase before storage/comparison
- Autogenerate: Yes (email normalizer function)
**BR-005: Password case sensitivity**
- Storage: Hash as-is (no transformation)
- Comparison: Case-sensitive hash comparison
- Autogenerate: No (standard hashing library)
---
### Constraints (C-*)
**C-001: Database query timeout**
- Max time: 100ms
- Fallback: "Service temporarily unavailable"
- Monitoring: Alert if >80ms (warning threshold)
**C-002: Session management**
- Session timeout: 30 minutes inactivity
- Token format: JWT (HS256)
- Storage: Redis cache with TTL
**C-003: Password hashing**
- Algorithm: bcrypt
- Cost factor: 12 (secure but performant)
- Library: bcrypt (acknowledge E(t) - existing library)
**C-004: HTTPS required**
- Protocol: All requests must be HTTPS
- Reject: HTTP requests not allowed
- Redirect: Optional HTTP → HTTPS redirect
**C-005: Rate limiting**
- Max requests: 10 login attempts per minute per IP
- Response: HTTP 429 (Too Many Requests)
- Reset: 1 minute window
---
### Formulas (F-*)
**F-001: Lockout expiry time**
lockout_expiry = last_attempt_time + (15 * 60) seconds
- Inputs: last_attempt_time (datetime)
- Output: lockout_expiry (datetime)
- Autogenerate: Yes (datetime calculation)
**F-002: Remaining lockout time**
remaining = max(0, (lockout_expiry - current_time) / 60) minutes
- Inputs: lockout_expiry (datetime), current_time (datetime)
- Output: remaining (int, rounded to nearest minute)
- Autogenerate: Yes (timedelta calculation)
**F-003: Password strength score**
score = length_score + complexity_score + uniqueness_score where: length_score = min(50, length * 2) complexity_score = (has_upper * 10) + (has_lower * 10) + (has_number * 10) + (has_special * 20) uniqueness_score = 0 (check against common passwords)
- Range: 0-100
- Thresholds: <50 weak, 50-75 medium, >75 strong
- Autogenerate: Yes (password scorer function)
---
### Discovery Log
**Added during disambiguation**:
- BR-004: Email case sensitivity (discovered while discussing validation)
- BR-005: Password case sensitivity (discovered while discussing hashing)
- C-005: Rate limiting (discovered as security concern)
- F-003: Password strength scoring (discovered as UX enhancement)
**Source**: Product team discussion during disambiguation
**Date**: 2025-11-20
When disambiguation complete:
[DISAMBIGUATION - <REQ-ID>]
Original Requirement:
"Users can log in with email and password"
Disambiguated Into:
Business Rules (5):
✓ BR-001: Email validation (regex, case handling)
✓ BR-002: Password requirements (length, complexity)
✓ BR-003: Failed attempt handling (lockout logic)
✓ BR-004: Email case sensitivity (normalization)
✓ BR-005: Password case sensitivity (hashing)
Constraints (5):
✓ C-001: Database query timeout (100ms)
✓ C-002: Session management (JWT, Redis, 30min)
✓ C-003: Password hashing (bcrypt, cost 12)
✓ C-004: HTTPS required (protocol enforcement)
✓ C-005: Rate limiting (10/min per IP)
Formulas (3):
✓ F-001: Lockout expiry time calculation
✓ F-002: Remaining lockout time calculation
✓ F-003: Password strength scoring
Total: 13 specifications (5 BR + 5 C + 3 F)
Autogeneration Ready:
✓ BR-001 → validate_email() + tests
✓ BR-002 → validate_password() + tests
✓ BR-003 → LockoutTracker class + tests
✓ F-001 → calculate_lockout_expiry() + tests
✓ F-002 → calculate_remaining_time() + tests
✓ F-003 → calculate_password_strength() + tests
Updated: docs/requirements/authentication.md
✅ Disambiguation Complete!
Requirement now precise enough for code generation
This orchestrator invokes:
extract-business-rules - Extract BR-* specificationsextract-constraints - Extract C-* specificationsextract-formulas - Extract F-* specificationsBefore invoking:
If prerequisites not met:
requirement-extraction firstWhy disambiguation?
Disambiguation vs Traditional Requirements:
Traditional: "Email must be valid"
→ Vague, developers guess regex pattern
Disambiguated: "BR-001: Email validation"
→ Regex: ^[a-zA-Z0-9._%+-]+@...
→ Error: "Invalid email format"
→ Autogenerate validate_email() function
→ Clear, testable, auto-generatable
Homeostasis Goal:
desired_state:
all_requirements_disambiguated: true
autogeneration_ready: true
vague_requirements: 0
"Excellence or nothing" 🔥
Handles the full Supabase workflow from schema changes to deployment, with built-in security guardrails that catch common traps like RLS...
Comprehensive guides and best practices for Neon Serverless Postgres, covering setup, connection methods, authentication, and platform APIs.
Guide for setting up and using Firebase Authentication. Use this skill when the user's app requires user sign-in, user management, or secure data access using auth rules.
A skill to evaluate how secure Firestore security rules are. Use this when Firestore security rules are updated to ensure that the generated rules are extremely secure and robust.
Official skill for integrating Firebase AI Logic (Gemini API) into web applications. Covers setup, multimodal inference, structured output, and security.
Complete Better Auth server and client setup with database adapters, session management, plugins, and security configuration.
Deploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login — e.g. "deploy to vercel", "set up vercel", "add environment variables to vercel".
Complete Cloudflare platform integration with decision trees for compute, storage, AI, networking, security, and infrastructure-as-code.
Run Azure compliance and security audits with azqr plus Key Vault expiration checks. Covers best-practice assessment, resource review, policy/compliance validation, and security posture checks. WHEN: compliance scan, security audit, BEFORE running azqr (compliance cli tool), Azure best practices, Key Vault expiration check, expired certificates, expiring secrets, orphaned resources, compliance assessment.
Send, read, and manage Gmail messages, drafts, labels, and account settings.
Comprehensive website auditing across 230+ rules in 21 categories including SEO, performance, security, and accessibility.
Shared authentication, CLI syntax, and output formatting patterns for gws Google Workspace commands.
Discover your celebrity doppelgänger with StarByFace!
GeoSpy: Pricing, Features, FAQs, and Alternatives for AI Teams
Detect AI-generated voices to protect against audio fraud.
Ensure Your Content's Originality with AI Plagiarism Checker
Upscale images by 400% without quality loss
Protect your social media from copyright disputes
Accurately Detect AI-Generated Content with TheChecker.AI
Chrome extension that detects and flags AI-generated content