Agent skill

Vivado Constraints

by Shinei-Nouzen-Arch in Shinei-Nouzen-Arch/FPGA-Agent

A skill your agent uses when the user needs help writing XDC/SDC timing or physical constraints for Vivado FPGA designs.

GPL-2.0Auto-check passedDevelopment

Install Vivado Constraints

skills CLI
$ npx skills add Shinei-Nouzen-Arch/FPGA-Agent --skill vivado-constraints -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Shinei-Nouzen-Arch/FPGA-Agent vivado-constraints --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Shinei-Nouzen-Arch/FPGA-Agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/vivado-constraints .claude/skills/vivado-constraints && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
vivado-constraints
GitHub stars
180
Token cost
~3.4k tokens
SKILL.md length
550 words
Files
3
Skills in repo
10
Repo updated
First seen
Licence
GPL-2.0

At a glance

A skill your agent uses when the user needs help writing XDC/SDC timing or physical constraints for Vivado FPGA designs.

  • Works in 4 steps: set_clock_groups — cannot be overridden → set_false_path → set_max_delay / set_min_delay → …
  • The user needs help writing XDC/SDC timing
  • SKILL.md covers XDC File Management, Clock Definition Guide, Clock Latency, Jitter,… and I/O Delay Templates, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Vivado Constraints is an agent skill from Shinei-Nouzen-Arch/FPGA-Agent. Use this skill when the user needs help writing XDC/SDC timing or physical constraints for Vivado FPGA designs. This includes clock definitions (createclock, creategeneratedclock, virtual clocks), I/O delay constraints (setinputdelay, setoutputdelay, DDR timing), timing exceptions (setfalsepath, setmulticyclepath, setmaxdelay, setmindelay), clock domain crossing (CDC) constraints (setclockgroups, setbusskew), clock uncertainty/jitter/latency, physical constraints (IOSTANDARD, PACKAGEPIN, LOC, Pblock, placement…

Its SKILL.md is about 3.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `REFERENCE.md` and `agents/openai.yaml`).

It sits in Development. The licence is GPL-2.0.

When your agent uses it

  • The user needs help writing XDC/SDC timing
  • Physical constraints for Vivado FPGA designs
  • The user mentions XDC
  • Timing constraints

Example prompts

  • “/vivado-constraints”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. set_clock_groups — cannot be overridden
  2. set_false_path
  3. set_max_delay / set_min_delay
  4. set_multicycle_path

What it can do on your machine

Read from SKILL.md and the folder at commit b60a52e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are tcl).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Vivado Constraints loads about 3.4k tokens when it runs. Until then it costs about 243 tokens; SKILL.md has 550 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~243
When it runs · the whole SKILL.md, loaded when a task matches
~3.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Shinei-Nouzen-Arch/FPGA-Agent at commit b60a52e, republished under its GPL-2.0 licence (© Shinei-Nouzen-Arch). 550 words, ~3,440 tokens.

Download SKILL.mdSave it as .claude/skills/vivado-constraints/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
vivado-constraints
description
Use this skill when the user needs help writing XDC/SDC timing or physical constraints for Vivado FPGA designs. This includes clock definitions (create_clock, create_generated_clock, virtual clocks), I/O delay constraints (set_input_delay, set_output_delay, DDR timing), timing exceptions (set_false_path, set_multicycle_path, set_max_delay, set_min_delay), clock domain crossing (CDC) constraints (set_clock_groups, set_bus_skew), clock uncertainty/jitter/latency, physical constraints (IOSTANDARD, PACKAGE_PIN, LOC, Pblock, placement, routing), XDC precedence rules, constraint scoping (SCOPED_TO_REF), constraint ordering optimization, or constraint debugging (check_timing, report_exceptions, report_clock_interaction). Trigger when the user mentions XDC, SDC, timing constraints, clock constraints, IO delay, false path, multicycle path, clock groups, or physical pin assignment. For timing report interpretation and analysis use vivado-analysis.

Vivado XDC Constraints Decision Guide

Based on UG903 (v2025.2). For complete syntax examples, see REFERENCE.md.

XDC File Management

Synthesis vs Implementation Constraints
tcl
# Project Mode: set on XDC file objects
set_property USED_IN_SYNTHESIS TRUE [get_files timing.xdc]
set_property USED_IN_IMPLEMENTATION TRUE [get_files timing.xdc]
set_property USED_IN_SYNTHESIS FALSE [get_files physical.xdc]  ;# impl only

# Non-Project Mode: just read in appropriate order
read_xdc timing.xdc        ;# both synth and impl
read_xdc physical.xdc      ;# read after synth only
Constraint Scoping (for IP / sub-modules)
tcl
# Project Mode
set_property SCOPED_TO_REF uart_tx_ctl [get_files uart_tx_ctl.xdc]
set_property SCOPED_TO_CELLS uart_tx_i0/uart_tx_ctl_i0 [get_files uart_tx_ctl.xdc]

# Non-Project Mode
read_xdc -ref uart_tx_ctl uart_tx_ctl.xdc
read_xdc -cells uart_tx_i0/uart_tx_ctl_i0 uart_tx_ctl.xdc
Object Naming Rules
  • Single-bit register myReg → instance name: myReg_reg
  • Multi-bit register myBus[2:0] → myBus_reg[0], myBus_reg[1], myBus_reg[2]
  • Query multi-bit: get_cells myBus_reg[*] (NOT myBus_reg[2:0])
  • Hierarchical names: use explicit / separator, NOT wildcards with -hierarchical
  • Recommended: Use get_cells inst_A/inst_B/*_reg without -hierarchical

Clock Definition Guide

Primary Clocks
tcl
# Board clock on input port (RECOMMENDED)
create_clock -period 10 [get_ports sysclk]

# Named clock with custom waveform (25% duty cycle, 90° phase shift)
create_clock -name devclk -period 10 -waveform {2.5 5} [get_ports ClkIn]

# Differential clock — define on POSITIVE pin ONLY
create_clock -name sysclk -period 3.33 [get_ports SYS_CLK_clk_p]

# GT recovered clock
create_clock -name rxclk -period 3.33 [get_pins gt0/RXOUTCLK]

# Virtual clock (no netlist object — for I/O delay reference)
create_clock -name clk_virt -period 10

Rules:

  • Define primary clocks on input ports, NOT on BUFG outputs
  • Primary clocks must be defined first — other constraints reference them
  • Virtual clocks must be defined before set_input_delay/set_output_delay that use them
Generated Clocks
tcl
# MMCM/PLL outputs → AUTO-DERIVED, no manual constraint needed
# User logic divider → must define manually:
create_generated_clock -name clkdiv2 -source [get_ports clkin] -divide_by 2 [get_pins REGA/Q]

# Using -edges (edge indices of master clock)
create_generated_clock -name clkdiv2 -source [get_pins REGA/C] -edges {1 3 5} [get_pins REGA/Q]

# Duty cycle change + phase shift via -edges and -edge_shift
create_generated_clock -name clkshift -source [get_pins mmcm0/CLKIN] \
    -edges {1 2 3} -edge_shift {2.5 0 2.5} [get_pins mmcm0/CLKOUT]

# Multiply + divide (for MMCM manual definition)
create_generated_clock -name clk43 -source [get_pins mmcm0/CLKIN] \
    -multiply_by 4 -divide_by 3 [get_pins mmcm0/CLKOUT]

# Combinational path only (MUX output)
create_generated_clock -name clkout -source [get_pins mmcm0/CLKIN] \
    -combinational [get_pins MUX/O]

# Rename auto-derived clock (name + source_object only)
create_generated_clock -name clk_rx [get_pins clk_gen_i0/clk_core_i0/inst/mmcm_adv_inst/CLKOUT0]

Rules:

  • -source accepts pin/port ONLY, not clock objects
  • MMCM/PLL outputs are auto-derived — only define manually if you need custom settings
  • Auto-derived clocks can only be renamed at CMB output pins
  • Use get_clocks -of_objects [get_pins <pin>] to query auto-derived clock names
Clock Groups
tcl
# Asynchronous clocks (most common — separate oscillators)
set_clock_groups -name async_clk0_clk1 -asynchronous \
    -group {clk0 usrclk itfclk} -group {clk1 gtclkrx gtclktx}

# With -include_generated_clocks (auto-include derived clocks)
set_clock_groups -name async_grp -asynchronous \
    -group [get_clocks -include_generated_clocks clk0] \
    -group [get_clocks -include_generated_clocks clk1]

# Exclusive clocks (BUFGMUX — only one active at a time)
set_clock_groups -name exclusive_clk0_clk1 -physically_exclusive \
    -group clk0 -group clk1

Rules:

  • set_clock_groups has HIGHEST priority among timing exceptions
  • Cannot be overridden by -reset_path
  • Prefer set_clock_groups over two set_false_path for async CDC
  • -logically_exclusive and -physically_exclusive are equivalent for AMD FPGAs

Clock Latency, Jitter, Uncertainty

tcl
# Source latency (board-level delay, outside FPGA)
set_clock_latency -source -early 0.2 [get_clocks sysClk]
set_clock_latency -source -late 0.5 [get_clocks sysClk]

# Input jitter (primary clocks only, per-clock)
set_input_jitter [get_clocks -of_objects [get_ports clkin]] 0.1

# System jitter (global, all clocks)
set_system_jitter 0.05

# Additional clock uncertainty (extra timing margin)
set_clock_uncertainty 0.5 [get_clocks clk1]

# Inter-clock uncertainty (MUST define BOTH directions)
set_clock_uncertainty 2.0 -from [get_clocks clk1] -to [get_clocks clk2]
set_clock_uncertainty 2.0 -from [get_clocks clk2] -to [get_clocks clk1]

I/O Delay Templates

SDR Input
tcl
# Basic (both min and max)
set_input_delay -clock sysClk 2 [get_ports DIN]

# Separate min/max
set_input_delay -clock sysClk -max 4 [get_ports DIN]
set_input_delay -clock sysClk -min 1 [get_ports DIN]

# Relative to virtual clock
create_clock -name clk_port_virt -period 10
set_input_delay -clock clk_port_virt 2 [get_ports DIN]
DDR Input
tcl
create_clock -name clk_ddr -period 6 [get_ports DDR_CLK_IN]
set_input_delay -clock clk_ddr -max 2.1 [get_ports DDR_IN]
set_input_delay -clock clk_ddr -max 1.9 [get_ports DDR_IN] -clock_fall -add_delay
set_input_delay -clock clk_ddr -min 0.9 [get_ports DDR_IN]
set_input_delay -clock clk_ddr -min 1.1 [get_ports DDR_IN] -clock_fall -add_delay
SDR Output
tcl
set_output_delay -clock sysClk 6 [get_ports DOUT]

# Separate min/max
set_output_delay -clock sysClk -max 6 [get_ports DOUT]
set_output_delay -clock sysClk -min 1 [get_ports DOUT]
DDR Output
tcl
create_clock -name clk_ddr -period 6 [get_ports DDR_CLK_IN]
set_output_delay -clock clk_ddr -max 2.1 [get_ports DDR_OUT]
set_output_delay -clock clk_ddr -max 1.9 [get_ports DDR_OUT] -clock_fall -add_delay
set_output_delay -clock clk_ddr -min 0.9 [get_ports DDR_OUT]
set_output_delay -clock clk_ddr -min 1.1 [get_ports DDR_OUT] -clock_fall -add_delay
Combinational Path (in-to-out)
tcl
create_clock -name sysClk -period 10
set_input_delay -clock sysClk 4 [get_ports DIN]
set_output_delay -clock sysClk 1 [get_ports DOUT]
# Effective budget: 10 - 4 - 1 = 5 ns

Key rules:

  • -clock is REQUIRED in Vivado (optional in SDC standard)
  • -clock_fall refers to the CLOCK edge, not data edge
  • -add_delay needed for second constraint on same port (DDR)
  • Use virtual clock to model different jitter/source latency scenarios

Timing Exceptions

Multicycle Path — Decision Table
ScenarioConstraints
Same clock / same-freq same-phaseset_multicycle_path N -setup -from CLK1 -to CLK2
set_multicycle_path N-1 -hold -from CLK1 -to CLK2
SLOW → FASTset_multicycle_path N -setup -from CLK1 -to CLK2
set_multicycle_path N-1 -hold -end -from CLK1 -to CLK2
FAST → SLOWset_multicycle_path N -setup -start -from CLK1 -to CLK2
set_multicycle_path N-1 -hold -from CLK1 -to CLK2

Key rules:

  • -setup default: moves destination (capture) clock edge → use -start to move source instead
  • -hold default: moves source (launch) clock edge → use -end to move destination instead
  • -start and -end have no effect within same clock domain
  • Always pair setup + hold multicycle constraints
Show full SKILL.md (218 more words)Show less
False Path
tcl
# Between async clock domains (prefer set_clock_groups instead)
set_false_path -from [get_clocks CLKA] -to [get_clocks CLKB]
set_false_path -from [get_clocks CLKB] -to [get_clocks CLKA]

# Reset signal
set_false_path -from [get_ports reset] -to [all_registers]

# Through specific path (ORDER of -through matters!)
set_false_path -through [get_pins MUX1/a0] -through [get_pins MUX2/a1]

# Setup-only or hold-only
set_false_path -setup -from [get_clocks CLKA] -to [get_clocks CLKB]

CAUTION: -through without -from or -to removes ALL paths through that pin/net.

Max/Min Delay
tcl
# Override setup requirement
set_max_delay 5 -from [get_pins FD1/C] -to [get_pins FD2/D]

# Override hold requirement
set_min_delay 1 -from [get_pins FD1/C] -to [get_pins FD2/D]

# CDC path with -datapath_only (no clock skew, hold auto false-pathed)
set_max_delay -datapath_only -from [get_cells src_reg*] -to [get_cells dst_reg*] 10.0

-datapath_only differences:

set_max_delayset_max_delay -datapath_only
Clock skewIncludedNever included
Hold requirementUntouchedAuto false-pathed
-fromOptionalMandatory
Case Analysis
tcl
set_case_analysis <value> <pins_or_ports>
# Values: 0, 1, zero, one, rise, rising, fall, falling
# rise/rising/fall/falling → only specified transition analyzed

# Example: select clk_2 through BUFGMUX
set_case_analysis 1 [get_pins clock_sel/S]
Disable Timing
tcl
# Disable cell timing arcs
set_disable_timing -from WCLK -to O [get_cells inst_fifo_gen/gdm.dm/gprl.dout_i_reg[*]]

# Check all disabled arcs
report_disable_timing -file disabled_arcs.rpt

XDC Precedence Rules

Exception Priority (highest → lowest)
  1. set_clock_groups — cannot be overridden
  2. set_false_path
  3. set_max_delay / set_min_delay
  4. set_multicycle_path
Object Specificity (highest → lowest)
  1. Ports, pins, cells (cells resolved to pins)
  2. Clocks
Filter Specificity (highest → lowest)
  1. -from -through -to
  2. -from -to
  3. -from -through
  4. -from
  5. -through -to
  6. -to
  7. -through

-reset_path can override false_path/max_delay/multicycle priority, but NOT clock_groups.

Last constraint wins for equivalent constraints (same type, same specificity).


CDC Constraints

Asynchronous CDC
tcl
# Option 1: set_clock_groups (RECOMMENDED — covers both directions)
set_clock_groups -asynchronous -group [get_clocks clkA] -group [get_clocks clkB]

# Option 2: set_false_path (need BOTH directions)
set_false_path -from [get_clocks clkA] -to [get_clocks clkB]
set_false_path -from [get_clocks clkB] -to [get_clocks clkA]
CDC with max delay constraint
tcl
# Limit path delay for CDC (when using synchronizer + set_false_path)
set_max_delay -datapath_only -from [get_cells src_reg*] -to [get_cells dst_sync_reg*] 10.0
Multi-bit CDC with bus skew
tcl
# CE-controlled CDC (handshake): skew = N_sync_stages * dst_period
set_bus_skew -from [get_cells src_hsdata_ff_reg*] -to [get_cells dest_hsdata_ff_reg*] 10.000

# Gray-coded FIFO: skew = dst_period
set_bus_skew -from [get_cells src_gray_ff_reg*] -to [get_cells {dest_graysync_ff_reg[0]*}] 2.500

# set_bus_skew requires: -from AND -to, at least 2 startpoints + 2 endpoints
# Value should be > 0.5 * min(src_period, dst_period)

Constraint Ordering for Performance

Write XDC sections in this order for minimum runtime impact:

OrderCommandsReason
1set_disable_timing, set_case_analysisPrune timing graph first
2create_clock, create_generated_clock, set_clock_senseDefine clocks before referencing
3set_clock_latency, set_propagated_clock, set_clock_uncertainty, set_input_jitter, set_system_jitterClock properties
4set_input_delay, set_output_delayI/O timing
5set_clock_groups, set_false_path, set_min_delay, set_max_delay, set_multicycle_path, set_bus_skewTiming exceptions
6set_max_time_borrow, set_external_delayRarely used

Performance tips:

  • Use get_cells instead of get_pins for large queries
  • Cache repeated queries in Tcl variables
  • Avoid all_fanin/all_fanout combined with set_disable_timing
  • Replace all_registers -clock clk1 with get_clocks clk1 where possible

Constraint Validation Commands

tcl
# Check for unconstrained paths
check_timing -file check_timing.rpt

# Review timing exception coverage, conflicts, ignored constraints
report_exceptions -coverage -file exceptions_coverage.rpt
report_exceptions -ignored -file exceptions_ignored.rpt
report_exceptions -scope_override -file exceptions_scope.rpt
report_exceptions -ignored_objects -file exceptions_ignored_obj.rpt

# Clock domain interaction matrix
report_clock_interaction -file clock_interaction.rpt

# Methodology checks (XDCV-1, XDCV-2 for large constraint collections)
report_methodology -file methodology.rpt

© Shinei-Nouzen-Arch, GPL-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files in vivado-constraints of Shinei-Nouzen-Arch/FPGA-Agent.

  • SKILL.md
  • REFERENCE.md
  • agents/openai.yaml

Open the folder on GitHubat commit b60a52e

Compare with similar skills

Vivado Constraints next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Vivado Constraints compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vivado Constraints this skillShinei-Nouzen-Arch/FPGA-Agent180—~3.4kAutomated safety check: PassGPL-2.0
Vercel Composition Patternssupabase/supabase111k58 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k4 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 58 repos~726 tokens
    DevelopmentAuto-check passed
  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed
  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 4 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

More from Shinei-Nouzen-Arch/FPGA-Agent

All 10 skills in this repo
  • Vivado Debug

    Shinei-Nouzen-Arch/FPGA-Agent

    A skill your agent uses when the user needs help with Vivado in-system debugging, hardware programming, or debug core configuration.

    180 GitHub stars~4.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Vivado Analysis

    Shinei-Nouzen-Arch/FPGA-Agent

    A skill your agent uses when the user needs Vivado design analysis, timing report interpretation, or timing-closure diagnosis.

    180 GitHub stars~3.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Vivado Impl

    Shinei-Nouzen-Arch/FPGA-Agent

    A skill your agent uses when the user needs Vivado implementation strategy selection or optimization.

    180 GitHub stars~3.7k tokensUpdated 1 mo ago
    Auto-check passed
  • Vivado Sim

    Shinei-Nouzen-Arch/FPGA-Agent

    A skill your agent uses when the user needs help with Vivado simulation strategy, flow selection, and debugging.

    180 GitHub stars~2.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Vivado Synth

    Shinei-Nouzen-Arch/FPGA-Agent

    A skill your agent uses when the user needs help with Vivado synthesis strategy selection, synthesis attribute configuration, synthdesign option tuning, resource inference control…

    180 GitHub stars~3.6k tokensUpdated 1 mo ago
    Auto-check passed
  • Vivado Tcl

    Shinei-Nouzen-Arch/FPGA-Agent

    Generate, review, explain, and execute Vivado/Vitis TCL scripts for FPGA design flows, and verify their execution results.

    180 GitHub stars~2.5k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Vivado Constraints

What does Vivado Constraints do?

A skill your agent uses when the user needs help writing XDC/SDC timing or physical constraints for Vivado FPGA designs. Vivado Constraints is an agent skill from Shinei-Nouzen-Arch/FPGA-Agent. Use this skill when the user needs help writing XDC/SDC timing or physical constraints for Vivado FPGA designs.

When should I use Vivado Constraints?

Vivado Constraints fits situations like: the user needs help writing XDC/SDC timing; physical constraints for Vivado FPGA designs; the user mentions XDC; timing constraints.

How do I install Vivado Constraints in Claude Code?

Run `npx skills add Shinei-Nouzen-Arch/FPGA-Agent --skill vivado-constraints -a claude-code`. Or copy the skill folder (vivado-constraints in Shinei-Nouzen-Arch/FPGA-Agent) into .claude/skills/vivado-constraints in your project. Claude Code loads it when a task matches its description.

How do I install Vivado Constraints in Codex?

Run `npx skills add Shinei-Nouzen-Arch/FPGA-Agent --skill vivado-constraints -a codex`. Or copy the skill folder (vivado-constraints in Shinei-Nouzen-Arch/FPGA-Agent) into .agents/skills/vivado-constraints in your project. Codex loads it when a task matches its description.

Can I use Vivado Constraints in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Shinei-Nouzen-Arch/FPGA-Agent --skill vivado-constraints -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vivado-constraints, .gemini/skills/vivado-constraints, .github/skills/vivado-constraints and .opencode/skills/vivado-constraints in your project.

What does Vivado Constraints need to run?

SKILL.md names no scripts, command-line tools or credentials: Vivado Constraints is instructions for the agent only.

Does Vivado Constraints access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Vivado Constraints safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Vivado Constraints use?

Vivado Constraints is published under the GPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Vivado Constraints use?

About 3.4k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Vivado Constraints?

Skills that share tags, products or a category with Vivado Constraints: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vivado Constraints?

Shinei-Nouzen-Arch (a GitHub user) maintains it in Shinei-Nouzen-Arch/FPGA-Agent, which has 180 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on September 5, 2026.

Source: Shinei-Nouzen-Arch/FPGA-Agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.