Works with the AI tools you already use
FPGA Reset Strategy
FPGA reset architecture as an area decision: why one wrong reset turns 4 BRAMs into 73,728 flip-flops, and the hybrid reset pattern that is always safe.
$30
/moSubscription · cancel anytime
Secure checkout via Stripe
- Always the latest version
- Delivered live to your agent via MCP
- Cancel anytime, access ends at period end
See it in action
You say
Generate a signed 16-bit Radix-4 Booth multiplier in Verilog with the corresponding Python golden model verification steps.
Your agent does
The skill provides a parameterized booth_mult_16.v featuring a 9-row recoding logic. It includes the exact 0xAAAA8000 correction vector and a testbench. Running python3 booth_golden.py --width 16 confirms the algorithm against 65k+ directed and random vectors.
What you get
About this skill
Resets are not free. This skill treats FPGA reset architecture as the area and timing decision it really is.
What you get:
- The resource-cost mechanics: a reset on a RAM blocks block-RAM inference (computed: 18,432x area per displaced BRAM — 73,728 discrete flip-flop bits for one 4096x18 buffer), a reset on a delay line blocks shift-register primitives (16x), and async styles block register packing into DSP and dedicated resources.
- The policy that follows: control-path registers get resets, datapath pipeline registers deliberately do not — with the reasoning you can defend in review.
- Correctness rules: fully-async reset hazards (recovery/removal timing, release near the clock edge), fully-sync limitations, and the standard hybrid — asynchronous assertion with synchronized deassertion — as compile-checked Verilog-2001, plus multi-clock-domain reset ordering and internally-generated-reset pitfalls.
- The synthesis interaction most guides skip: reset nets block register balancing and retiming, and the inversion workaround that unblocks them.
- A pure-stdlib reset-policy auditor: describe your registers, RAMs and delay lines as JSON, get every violation flagged with its computed cost delta and a concrete remediation.
Run python3 scripts/reset_cost_audit.py after install: five built-in cases self-test in seconds and exit 0. Every claim is backed by that runnable evidence.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.
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
Free forever
No account required to browse
Creator
4 skills on Agensi
We sell high-quality skills only – not the standard knowledge any language model already has. Every skill is tested and reviewed by us before it's listed. Our goal: using our skills should let you build your own business and actually make money. Wir verkaufen ausschließlich hochwertige Skills – keine Standard-Antworten, die ohnehin jedes Sprachmodell liefert. Jeder Skill wird von uns getestet und geprüft, bevor er hier gelistet wird. Unser Anspruch: Mit unseren Skills sollst du dein eigenes Geschäft aufbauen und wirklich Geld verdienen können.
Frequently Asked Questions
Popular in AI Agents & LLM Ops
agentic-workflow
A risk-aware, evidence-based engineering lifecycle protocol for robust agentic task execution and safety.
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.

prompt-engineer
Professional prompt engineering patterns for building robust, secure, and production-ready LLM applications.
codex-grade-coding
Turn your AI agent into a senior engineer with strict task classification and verification-driven coding protocols.