Works with the AI tools you already use
spark
A role-based architecture board that interrogates, hardens, and scaffolds resolved implementation plans.
$5
spark
Example session with this skill installed
I have a raw idea for a HIPAA-compliant patient intake system for small clinics. Start Build Mode.
- Read your context and instructions
- Compiled the spark
- Generated the UI component
I have initiated
Build Mode for the HIPAA-compliant patient intake system. The current maturity stage is
IDEA. I have performed the initial intake and identified the core system primitives: patient identity management, encrypted form submission, and clinical dashboarding.
Build Mode: Discovery & Silence Audit
| Role | Status | Dependency |
|---|---|---|
| System Architect | MENTIONED | REQUIRED_NOW |
| Security Architect | PARTIALLY | REQUIRED_NOW |
| Compliance / Privacy | ABSENT | BLOCKER |
| Data Architect | ABSENT | REQUIRED_NOW |
| FinOps | ABSENT | NOT_REQUIRED |
Initial Interrogation (P0 Questions)
- Compliance: How will we handle Business Associate Agreements (BAAs) with third-party cloud providers?
- Security: Will the decryption keys for patient data reside on the client-side or in a managed HSM?
- Data: Does the requirement for HIPAA compliance necessitate a physical data residency within a specific region?
Decision Log Preview
| ID | Decision | Status | Impact |
|---|---|---|---|
| DEC-001 | Cloud Provider | PROPOSED | High (Security/Compliance) |
| DEC-002 | Encryption Layer | OPEN | Critical (Security) |
Next steps
- Resolve the Compliance BLOCKER by defining the regulatory scope (e.g., HIPAA vs. HITECH).
- Answer the P0 Interrogation questions to move from IDEA to ARCHITECTURAL_DISCOVERY.
- Confirm if the clinical dashboard requires an
OWNED_UIclassification to activate Frontend roles.
spark.tsx
TSX · React component
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
What you get
About this skill
The problem
Founders often rush from a raw idea to implementation, leaving critical architectural gaps and security risks unaddressed. Traditional AI prompting results in generic code snippets rather than a hardened, internally consistent system design.
What it does
- Executes a role-based interrogation using 15 specialized architectural lenses, including Security, Data, FinOps, and GTM.
- Runs mandatory gates for claim coverage, 28-pair consistency checks, and security hardening before finalizing any design.
- Generates a complete implementation-ready document set, including PRDs, architecture specs, security models, and phased execution plans.
- Produces a full repository scaffold of directories and empty files to ensure structural integrity without injecting premature code.
Why this beats prompting it yourself
Standard prompts generate what you ask for, even if it is a bad idea. This skill actively challenges your assumptions, identifies silent omissions across 15 technical domains, and refuses to sign off on a design until it survives a simulated adversarial review.
Use cases
- Transforming a rough "back of the napkin" startup concept into a verified technical specification.
- Auditing existing architecture documents to find security vulnerabilities and scaling bottlenecks.
- Validating that a product's GTM strategy is technically supported by its backend infrastructure.
- Standardizing repository structures for new projects to prevent architectural drift from day one.
Known limitations
Does not write implementation code, stubs, or boilerplate. Requires explicit founder sign-off at high-consequence decision points.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean today
- Passed all security checks, Safe to install