More screenshots
Works with the AI Agents you already use
FPGA Booth Recoding Multiplier
Radix-4 Booth multiplier design with verified RTL and an exhaustive golden model — halve your partial products without sign-extension bugs.
$30
FPGA Booth Recoding Multiplier
Example session with this skill installed
Generate a 16-bit signed Radix-4 Booth multiplier in Verilog with the corresponding Python golden model for verification.
- Read your context and instructions
- Compiled the fpga booth recoding
RTL generated: booth_mult_16x16.v (parameterized).
Logic: Radix-4 recoding, 8 partial products, MSB inversion for sign-prevention.
Correction Vector C: 0xAAAA8000.
Run python3 scripts/booth_golden.py --width 16 to verify against hardware-accurate partial products.
Connects securely to your tools. The creator never sees your data.
About this skill
Build radix-4 (modified Booth) multipliers that actually work on the first synthesis.
What you get:
- The complete radix-4 recoding tables and encoder equations, with the sign-extension-prevention correction vector derived in closed form — the part most implementations get wrong.
- One's-complement negative partial products with separate correction bits, signed AND unsigned operand handling (including the extra top digit unsigned operands need).
- Parameterized Verilog-2001: digit encoder, partial-product generator, and a full generate-loop multiplier — compiled and simulated with 1,515 checks, 0 errors, including the INT_MIN x INT_MIN corner.
- A pure-stdlib Python golden model that reproduces the hardware algorithm bit-exactly (rows + neg bits + correction vector, not a shortcut a*b) — verified exhaustively on all 65,536 signed 8x8 pairs plus random 32x32, with a debug CLI that prints the recoded digits for any operand pair.
- An honest FPGA-vs-ASIC section: when Booth pays off on LUT fabrics and when a plain AND-array partial-product multiplier is the better choice.
Run python3 scripts/booth_golden.py after install: it self-tests in seconds and exits 0. Every claim in this skill is backed by that runnable evidence.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
Does not support DSP-block tiling, truncated multipliers, or squarers. Unsigned operands require one additional recoded digit. Radix-8 requires manual latency trade-off for the 3A hard multiple.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 3 months ago
Permissions
No special permissions declared or detected