Credance
Update this file after every meaningful implementation change. - Unit 09: Frontend Integration & Real-Time Sync — COMPLETE
Install / Use
npx skills add codewithemmax/CredanceInstalls into whichever agent you are using.
Amazon Q Rules
Amazon Q Developer rules
Quality Score
Category
Development & EngineeringSupported Platforms
Tags
Our assessment of Credance
Credance scores 59/100 on our quality scale, 4144th of 4,646 Development & Engineering skills we index.
Its Amazon Q Rules is 5.8 KB long, well organised into 10 sections and no code examples: a solid amount of guidance for an agent.
It has no GitHub stars yet, so there is no community track record; judge it on its content.
Maintenance, license and trust
- We could not determine when the repository was last updated.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 68/100, with 3 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Credance compared with similar skills
All 4 of these similar skills score higher than Credance; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| Credance (this skill)by codewithemmax | 59 | 0 | — | Amazon Q Rules |
| taste-skillby Leonxlnx | 100 | 104.0k | today | CLAUDE.md |
| ai-job-searchby ai-job-search-dev | 100 | 67.0k | 1d ago | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 45.7k | 1d ago | CLAUDE.md |
| algorithmic-artby anthropics | 100 | 177.9k | 36d ago | SKILL.md |
Frequently asked questions
- How do I install Credance?
- Run
npx skills add codewithemmax/Credance. The install tabs above show the steps for each supported agent. - Which AI agents does Credance work with?
- It is written for Amazon Q, as a Amazon Q Rules file. Other agents that read the same format can often use it too.
- Is Credance safe to use?
- It declares no license and scores 68/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is Credance still maintained?
- We could not determine when the repository was last updated.
Skill content
View source on GitHubProgress Tracker
Update this file after every meaningful implementation change.
Current Phase
- Unit 09: Frontend Integration & Real-Time Sync — COMPLETE
Current Goal
- All core units implemented successfully
Completed
- Defined
project-overview.md,architecture.md,code-standards.md,ai-workflow-rules.md. - ✅ Unit 01 — COMPLETE:
package.json,tsconfig.json(strict mode),prisma/schema.prisma(all 7 models + enums),src/config/env.ts(typed env validation),src/routes/health.route.ts,src/server.ts. Prisma client generated.npm run buildpasses with zero TypeScript errors. Pushed tomainon GitHub. - ✅ Unit 02 — COMPLETE:
src/middlewares/auth.middleware.ts(Supabase JWT),src/utils/crypto.util.ts(AES-256-GCM BVN encryption),src/services/squad.service.ts(virtual account creation),src/controllers/trader.controller.ts,src/routes/trader.route.ts.POST /api/v1/traders/onboardmounted. Zero TypeScript errors. Pushed tofeat/02-identity-onboardingon GitHub. - ✅ Unit 03 — COMPLETE:
src/middlewares/webhook.middleware.ts(HMAC SHA-512 correct format with JSON.stringify(body)),src/controllers/webhook.controller.ts(idempotency + async handoff),src/routes/webhook.route.ts.POST /api/v1/webhooks/squadmounted. Successfully tested with Squad webhook format. Zero TypeScript errors. - ✅ Unit 04 — COMPLETE:
src/engine/vouch.engine.ts(full VouchEngine with Variables A-D, tier evaluation, safety brakes, B2B fast-track),src/services/transaction.service.ts(buildUserData aggregation + VouchEngine integration),prisma/schema.prisma(added activeTier as Int, previousTier, creditLimit, outstandingBalance to Trader model). Zero TypeScript errors. All mathematical boundaries and edge cases implemented according to specification. Successfully tested with real Squad webhooks. - ✅ Unit 05 — COMPLETE:
src/engine/fraud.detector.ts(Recursive CTE 4-hop cycle detection, -150 penalty),src/services/ajo.service.ts(recurring.completed +40 / recurring.failed -60), webhook controller extended, fraud check wired into transaction service. Zero TypeScript errors. Integrated with Unit 04 scoring pipeline. - ✅ Unit 06 — COMPLETE: Tier evaluation post-score hook and Squad Transfer API disbursement.
evaluateTierUnlock()function triggers ₦50,000 loan disbursement when score crosses 400 (Tier 2 threshold).disburseLoan()function calls Squad Transfer API. Successfully tested with webhook simulation. - ✅ Unit 07 — COMPLETE:
src/middlewares/api-key.middleware.ts(Partner API key validation),src/controllers/lender.controller.ts,src/routes/lender.route.ts.GET /api/v1/lenders/score/:virtualAccountmounted. Secure B2B API endpoint for external partners to query trader scores. Zero TypeScript errors. - ✅ Unit 08 — COMPLETE:
src/controllers/debug.controller.ts,src/routes/debug/debug.route.ts.POST /api/v1/debug/simulate-paymentsmounted. God Mode simulation endpoint that generates fake transactions and feeds them directly into the scoring engine. Environment-restricted to development/demo only. Zero TypeScript errors. - ✅ Unit 09 — COMPLETE:
src/controllers/trader.controller.ts(getTraderScore, getTraderTransactions, streamTraderScore with user isolation via supabaseUserId),src/controllers/loan.controller.ts(acceptLoan with user isolation),src/routes/loan.route.ts.GET /api/v1/traders/score,GET /api/v1/traders/transactions,GET /api/v1/traders/score/stream(SSE),POST /api/v1/loans/acceptmounted. Complete frontend integration API with real-time sync and proper user isolation. AddedsupabaseUserIdfield to Trader model for one-to-one user-trader relationship. Zero TypeScript errors.
In Progress
- None - All units complete
Next Up
- Unit 08: Demo Trigger & Simulation Environment
Open Questions
- What specific metrics (e.g., exact weighting of transaction consistency vs. Ajo defaults) will the AI Scoring Engine use, or should that be stubbed initially?
- Does the user have the Squad Sandbox API keys ready for local
.envconfiguration?
Architecture Decisions
- Strict Idempotency: Implemented via the
WebhookEventtable to prevent duplicate transaction processing from Squad API retries. - Synchronous Handoff: Webhook routes will immediately return a
200 OKto Squad and process score updates asynchronously to prevent timeout errors. - Data Source Authority: The scoring engine is mathematically restricted to using only verified Squad webhook data; self-reported income is strictly prohibited.
Session Notes
- The architecture requires a strict Controller-Service pattern. Controllers handle routing and extraction, while Services handle external APIs and Prisma mutations.
- UI development is explicitly out of scope. The deliverable is a functional API backend.
Unit 04 Implementation Details
- VouchEngine Class: Implements deterministic scoring with Variables A-D as specified
- Variable A (Age & Activity): +12 points per active month, capped at 150 points, requires >= 10 unique transactions to activate
- Variable B (Consistency): Based on daily consistency points, capped at 300 points
- Variable C (Network Retention): Repeat senders * 13 + New senders * 7, capped at 250 points
- Variable D (Volume Scaling): Tier 1 gets 0 volume points, others based on actual vs target volume ratio
- Safety Brakes: Utilization penalty (-50 points * (1 + months_in_default)) when debt > 80% of limit
- Soft Landing: Sets "Repayment-Only" state when tier drop leaves debt > new limit
- B2B Fast-Track: 70% volume match threshold for instant tier unlock on Day 31
- Database Integration: buildUserData() aggregates transaction history for engine input
- Score Updates: Atomic transactions update trader score, tier, and ledger simultaneously
Related Skills
taste-skill
104.0kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
ai-job-search
67.0kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
45.7kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
