Trellis Session Insight
mindfold-ai/Trellis
Reach into past AI conversation history through the trellis mem CLI.
A skill your agent uses when the user needs help with Vivado in-system debugging, hardware programming, or debug core configuration.
$ npx skills add Shinei-Nouzen-Arch/FPGA-Agent --skill vivado-debug -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Shinei-Nouzen-Arch/FPGA-Agent vivado-debug --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Shinei-Nouzen-Arch/FPGA-Agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/vivado-debug .claude/skills/vivado-debug && rm -rf skills-srcUse ~/.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/
Install the "vivado-debug" agent skill from https://github.com/Shinei-Nouzen-Arch/FPGA-Agent/tree/main/vivado-debug into .claude/skills/vivado-debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vivado-debug", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Shinei-Nouzen-Arch/FPGA-Agent/tree/main/vivado-debugType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Shinei-Nouzen-Arch/FPGA-Agent --skill vivado-debug -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Shinei-Nouzen-Arch/FPGA-Agent vivado-debug --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Shinei-Nouzen-Arch/FPGA-Agent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/vivado-debug .agents/skills/vivado-debug && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "vivado-debug" agent skill from https://github.com/Shinei-Nouzen-Arch/FPGA-Agent/tree/main/vivado-debug into .agents/skills/vivado-debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vivado-debug", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Shinei-Nouzen-Arch/FPGA-Agent --skill vivado-debug -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Shinei-Nouzen-Arch/FPGA-Agent vivado-debug --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Shinei-Nouzen-Arch/FPGA-Agent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/vivado-debug .cursor/skills/vivado-debug && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "vivado-debug" agent skill from https://github.com/Shinei-Nouzen-Arch/FPGA-Agent/tree/main/vivado-debug into .cursor/skills/vivado-debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vivado-debug", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Shinei-Nouzen-Arch/FPGA-Agent.git --path vivado-debug--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Shinei-Nouzen-Arch/FPGA-Agent --skill vivado-debug -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Shinei-Nouzen-Arch/FPGA-Agent vivado-debug --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Shinei-Nouzen-Arch/FPGA-Agent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/vivado-debug .gemini/skills/vivado-debug && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "vivado-debug" agent skill from https://github.com/Shinei-Nouzen-Arch/FPGA-Agent/tree/main/vivado-debug into .gemini/skills/vivado-debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vivado-debug", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Shinei-Nouzen-Arch/FPGA-Agent vivado-debugInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Shinei-Nouzen-Arch/FPGA-Agent --skill vivado-debug -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Shinei-Nouzen-Arch/FPGA-Agent.git skills-src && mkdir -p .github/skills && cp -r skills-src/vivado-debug .github/skills/vivado-debug && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "vivado-debug" agent skill from https://github.com/Shinei-Nouzen-Arch/FPGA-Agent/tree/main/vivado-debug into .github/skills/vivado-debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vivado-debug", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Shinei-Nouzen-Arch/FPGA-Agent --skill vivado-debug -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Shinei-Nouzen-Arch/FPGA-Agent vivado-debug --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Shinei-Nouzen-Arch/FPGA-Agent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/vivado-debug .opencode/skills/vivado-debug && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "vivado-debug" agent skill from https://github.com/Shinei-Nouzen-Arch/FPGA-Agent/tree/main/vivado-debug into .opencode/skills/vivado-debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vivado-debug", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
vivado-debugA skill your agent uses when the user needs help with Vivado in-system debugging, hardware programming, or debug core configuration.
Vivado Debug is an agent skill from Shinei-Nouzen-Arch/FPGA-Agent. Use this skill when the user needs help with Vivado in-system debugging, hardware programming, or debug core configuration. This includes ILA (Integrated Logic Analyzer) configuration and trigger strategies, VIO (Virtual I/O) usage for signal monitoring and control, JTAG-to-AXI Master for AXI transaction generation, markdebug attribute and debug probing flows (Netlist Insertion, HDL Instantiation), Set Up Debug Wizard, ILA cross-trigger architecture, debug core timing impact and mitigation, Vivado Hardware…
Its SKILL.md is about 4.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `REFERENCE.md`, `agents/openai.yaml` and `references/debug-troubleshooting.md`).
It sits in Development, covering Debugging. The licence is GPL-2.0.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit b60a52e. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md (its code samples are tcl, verilog and vhdl).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Vivado Debug loads about 4.8k tokens when it runs, and up to ~6.1k if it reads all its reference files. Until then it costs about 232 tokens; SKILL.md has 1,897 words of instructions outside code blocks.
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.
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.
The full file from Shinei-Nouzen-Arch/FPGA-Agent at commit b60a52e, republished under its GPL-2.0 licence (© Shinei-Nouzen-Arch). 1,897 words, ~4,821 tokens.
.claude/skills/vivado-debug/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.Based on UG908 (v2025.2). This skill helps choose debug strategies, configure debug cores, and troubleshoot hardware debugging. For complete command syntax, see REFERENCE.md. For TCL execution, use vivado-tcl.
Choose debug cores based on what you need to observe or control:
| Debug Core | Version | Purpose | Key Capability |
|---|---|---|---|
| ILA (Integrated Logic Analyzer) | v6.2 | Trigger on events and capture data at system speeds | Waveform capture, advanced triggers, storage qualification |
| VIO (Virtual Input/Output) | v3.0 | Monitor or control signals at JTAG scan rates | Real-time signal read/write, no waveform capture |
| JTAG-to-AXI Master | v1.2 | Generate AXI transactions to interact with AXI slave cores | Read/write AXI Full and AXI Lite interfaces |
| ILA Cross-Trigger | (ILA feature) | Synchronize triggers between ILA cores or between ILA and processor | Cross-clock-domain trigger coordination |
Decision guide:
Need to capture signal waveforms at full speed?
YES --> ILA
NO --> Need to read/write signals in real-time?
YES --> VIO (low bandwidth, JTAG rate)
NO --> Need to read/write AXI slave registers?
YES --> JTAG-to-AXI Master
NO --> Need to coordinate triggers across clock domains?
YES --> ILA with Cross-Trigger enabledFour approaches to add debug cores, each with different trade-offs:
| Scenario | Flow | How It Works | Best For |
|---|---|---|---|
| Tag signals in HDL, use wizard later | mark_debug + Netlist Insertion | Add mark_debug attribute in VHDL/Verilog. After synthesis, use Set Up Debug wizard to insert ILA cores. | Flexibility to enable/disable debug without HDL changes |
| Mark signals in synthesized netlist GUI | GUI Mark Debug | Right-click nets in Netlist/Schematic views and select Mark Debug. Use Set Up Debug wizard. | Quick signal selection without modifying source code |
| Automated scripted flow | TCL Automation | Use set_property to set mark_debug, then create_debug_core / connect_debug_port TCL commands. | Repeatable, version-controlled debug insertion |
| Full control in HDL source | HDL Instantiation | Manually instantiate ILA/VIO/JTAG-to-AXI Master IP in HDL and connect to signals. | Per-probe comparator control, cross-trigger ports, VIO cores |
Verilog:
(* mark_debug = "true" *) wire [7:0] char_fifo_dout;VHDL:
attribute mark_debug : string;
attribute mark_debug of char_fifo_dout: signal is "true";Valid values: "TRUE" or "FALSE" (the "SOFT" value is not supported by Vivado synthesis).
Control MARK_DEBUG behavior post-synthesis without modifying source files:
| Mode | Synthesis Behavior | Implementation Behavior | Use When |
|---|---|---|---|
enable (default) | Do not optimize MARK_DEBUG nets | Do not optimize MARK_DEBUG nets | Active debugging, need nets preserved |
disable | Freely optimize | Freely optimize | Production build, remove all debug overhead |
synthesis_only | Do not optimize (nets available at start of impl) | Freely optimize during impl | Want debug net availability but allow impl optimization |
Hollow green icon = MARK_DEBUG set, NOT connected to any ILA core
Full green icon = MARK_DEBUG set, connected to an ILA core
Yellow icon = No MARK_DEBUG on net, but connected to an ILA coreThe C_DATA_DEPTH property controls how many samples the ILA stores. Larger depth consumes more Block RAM:
| C_DATA_DEPTH | Samples | BRAM Impact | Recommended Use |
|---|---|---|---|
| 1024 (default) | 1K | Low | Initial debug, quick trigger verification |
| 2048 | 2K | Low-Medium | Short protocol sequences |
| 4096 | 4K | Medium | Typical protocol debug |
| 8192 | 8K | Medium-High | Longer event sequences |
| 16384 | 16K | High | Multi-phase protocol analysis |
| 32768 | 32K | High | Rare event capture with large pre/post-trigger window |
| 65536 | 64K | Very High | Extended capture, ensure BRAM budget allows |
| 131072 | 128K | Very High | Maximum capture depth, significant resource cost |
Rule of thumb: Start with 1024. Increase only when you need more pre/post-trigger context. Each doubling roughly doubles BRAM usage per probe bit.
| Property | Default | Set to TRUE When | Impact |
|---|---|---|---|
| C_ADV_TRIGGER | false | Need state-machine-based triggers, counter triggers, or range triggers | Adds trigger logic resources |
| C_EN_STRG_QUAL | false | Need basic capture control (filter which samples are stored) | Uses 1 comparator for capture control |
| C_INPUT_PIPE_STAGES | 0 | Timing violations on ILA probe inputs; increase to 1-6 | Adds FF pipeline stages, improves timing at cost of sample latency |
| C_TRIGIN_EN | false | Need cross-trigger input (from another ILA or processor) | Adds TRIG_IN/TRIG_IN_ACK ports |
| C_TRIGOUT_EN | false | Need cross-trigger output (to another ILA or processor) | Adds TRIG_OUT/TRIG_OUT_ACK ports |
| C_MEMORY_TYPE (Versal only) | 0 (BRAM) | High BRAM utilization, want to use UltraRAM instead | 0=BRAM, 1=URAM; URAM can ease BRAM timing |
Each probe port can be configured independently:
| Probe Type | Captures Data | Participates in Trigger | BRAM Usage | Use When |
|---|---|---|---|---|
| Data and Trigger | Yes | Yes | Full | Need to both see and trigger on signal (most common) |
| Data Only | Yes | No | Full | Only need to see signal values, not trigger on them |
| Trigger Only | No | Yes | Reduced | Only need to trigger on signal, do not need waveform display |
Tip: Configuring wide buses as "Trigger Only" when you do not need their waveform significantly reduces BRAM consumption.
Important: In the netlist insertion flow, all probes share the same number of comparators. Use HDL instantiation flow to set different comparator counts per probe.
Cross-triggering enables trigger coordination between ILA cores in different clock domains, or between an ILA core and a processor (e.g., Zynq-7000 SoC).
+------------------+ +------------------+
| ILA 1 | | ILA 2 |
| | | |
| trig_in <-----+------------------+-- trig_out |
| trig_in_ack ---+------------------+-> trig_out_ack |
| | | |
| trig_out ------+------------------+-> trig_in |
| trig_out_ack <-+------------------+-- trig_in_ack |
+------------------+ +------------------+Requirements:
trig_in must be synchronous to the ILA clock| Signal | Latency | Notes |
|---|---|---|
| trig_in --> trig_in_ack | 1 clock cycle | ACK asserted 1 clk after trig_in asserts |
| trig_in (or trigger condition) --> trig_out | 9 clock cycles | TRIG_OUT asserted 9 clks after trigger condition met |
| trig_in_ack / trig_out_ack de-assert | When trigger de-asserts | ACK signals go low only when trigger signals are de-asserted |
Behavior: TRIG_OUT remains HIGH until TRIG_OUT_ACK is received. If TRIG_OUT_ACK is tied to LOW, TRIG_OUT remains HIGH until the user re-arms the ILA. Only TRIG_OUT goes LOW if TRIG_OUT_ACK is tied to LOW.
The VIO (Virtual Input/Output) core monitors and controls signals at JTAG scan rates (not system speed).
| Port Direction | Hardware Perspective | Use In Vivado | Typical Use |
|---|---|---|---|
| Input ports | Directly connected to design signals to monitor | Read values in VIO Dashboard (periodically refreshed) | Status indicators, counter values, state machine states |
| Output ports | Drive signals into the design for control | Write values from VIO Dashboard or TCL | Reset control, MUX select, enable signals, load values |
VIO operates on set/commit and refresh/get model:
Write flow: set_property OUTPUT_VALUE <val> [get_hw_probes <probe>]
commit_hw_vio [get_hw_probes {<probe>}]
Read flow: refresh_hw_vio [get_hw_vios {hw_vio_1}]
get_property INPUT_VALUE [get_hw_probes <probe>]Recommended refresh rate: 500 ms or longer (very small values make Vivado sluggish).
1. reset_hw_axi [get_hw_axis hw_axi_1]
2. create_hw_axi_txn read_txn [get_hw_axis hw_axi_1] \
-type READ -address 00000000 -len 4
3. run_hw_axi [get_hw_axi_txns read_txn]
4. report_hw_axi_txn [get_hw_axi_txns read_txn]Important: If you reprogram the device, all existing jtag_axi transactions are deleted and must be recreated.
Versal adaptive SoC uses a different debug infrastructure than 7 series/UltraScale/UltraScale+.
Every Versal design with debug cores requires a Control, Interface, and Processing System (CIPS) IP instance in a block design:
opt_design, AXI4 Debug Hub is auto-inserted and connectedThe AXI4 Debug Hub replaces the BSCAN-based debug hub used in previous architectures. It connects the CIPS AXI4 interface to debug cores via AXI4-Stream.
Supported debug cores on Versal:
| Method | Auto-Insertion | Debug Core Connection | When to Use |
|---|---|---|---|
| Automatic AXI4 Debug Hub insertion and connection | Yes, during opt_design | Automatic | Most designs (recommended). Cannot be used with DFX. |
| Manual AXI4 Debug Hub instantiation, automatic debug core connection | User instantiates Debug Hub | Automatic during opt_design | Need manual address assignment or using DFX. Vivado replaces user's Debug Hub with correctly configured one. |
| Manual AXI4 Debug Hub instantiation, manual debug core connection | User instantiates Debug Hub | User connects each core's AXI4-Stream master/slave | Full manual control. Required for DFX. Must set exact Number of Debug Cores. |
Recommended AXI connection: Use PMC NoC interface for the AXI4 Debug Hub. FPD/LPD interfaces are also possible, but extended address ranges 0x004_0000_0000 (8G) and 0x400_0000_0000 (1T) are not supported.
When AXI-based interfaces from the PS/PMC cannot be used (e.g., AXI timeout), BSCAN Fallback provides an alternative communication path.
| Connectivity Option | Description | Suggested Use |
|---|---|---|
| AXI4 | Only AXI4 path enabled | Most hardware debug use cases |
| AXI4, BSCAN Fallback | Both paths available, AXI4 default | System-wide AXI timeout debugging |
| AXI4, BSCAN Fallback (BSCAN default) | Both paths available, BSCAN default | AXI path not accessible at boot |
| AXI4 (Unconnected), BSCAN (Default) | Only BSCAN pathway | Exclusive BSCAN connectivity to Debug Hub |
Steps to enable BSCAN Fallback:
The ILA core can impact design timing. Follow this decision tree when timing violations appear after adding debug cores:
Timing violation after adding debug cores?
|
+-- Violation path is in ILA or AXIS-ILA core probe inputs?
| |
| YES --> Increase C_INPUT_PIPE_STAGES (try 1, then up to 6)
| Still failing? --> Try URAM storage (Versal: C_MEMORY_TYPE=1)
| Still failing? --> Try impl strategy:
| Performance_Explore or
| Performance_ExtraTimingOpt
|
+-- Violation path is in debug_hub (dbg_hub) core?
| |
| YES --> 1. Set C_CLK_INPUT_FREQ_HZ to actual clock frequency
| 2. Set C_ENABLE_CLK_DIVIDER to true
| 3. Re-implement design
| (This adds MMCM clock divider to achieve ~100 MHz internally)
|
+-- Violation path is elsewhere but worsened by debug?
|
YES --> 1. Close timing BEFORE adding debug cores
2. Choose narrower probe widths
3. Reduce C_DATA_DEPTH
4. Use Performance_Explore impl strategy
5. For Versal: use 100-250 MHz clock for AXI4-Debug HubAdditional timing guidelines:
The steps to debug your design in hardware using an ILA debug core:
1. Connect to hardware target and program FPGA/SoC
--> open_hw_manager
--> connect_hw_server -url localhost:3121
--> program_hw_devices [lindex [get_hw_devices] 0]
2. Set up the ILA: configure trigger and capture controls
--> Add probes in Trigger Setup window
--> Set compare values, operators, radix
--> Choose trigger mode: BASIC_ONLY or ADVANCED (state machine)
--> Configure capture mode: ALWAYS or conditional
3. Arm the ILA trigger
--> run_hw_ila hw_ila_1
4. View captured data in Waveform window
--> wait_on_hw_ila hw_ila_1
--> display_hw_ila_data [upload_hw_ila_data hw_ila_1]
5. Use VIO core to drive control signals and view status
--> Add probes in VIO Dashboard
--> Set OUTPUT_VALUE and commit_hw_vio
--> Read INPUT_VALUE after refresh_hw_vio
6. Use JTAG-to-AXI Master to run AXI transactions
--> reset_hw_axi, create_hw_axi_txn, run_hw_axiFor non-Versal architectures (7 series, UltraScale, UltraScale+):
| Debugging Phase | JTAG Clock | Debug Hub Clock | Debug Core Clock |
|---|---|---|---|
| Connect to Target | Stable | N/A | N/A |
| Programming | Stable | N/A | N/A |
| Debug Core Discovery | Stable | Stable | N/A |
| Debug Core Measurement | Stable | Stable | Stable |
Notes:
get or set of properties on the debug coreFor non-Versal architectures: If your design contains debug cores, ensure that the JTAG clock is 2.5x times slower than the debug hub clock.
JTAG_clock_frequency < Debug_Hub_clock_frequency / 2.5Example: If Debug Hub clock is 100 MHz, JTAG must be < 40 MHz.
To lower JTAG frequency:
set_property PARAM.FREQUENCY 250000 [get_hw_targets \
*/xilinx_tcf/Digilent/210203327962A]AMD recommends Debug Hub clock frequency around 100 MHz. You can change the Debug Hub clock:
connect_debug_port dbg_hub/clk [get_nets <clock net name>]Versal debug cores use AXI-based connectivity and are not subject to the BSCAN clocking guidelines. For Versal, if a timing failure is observed after adding debug cores, use a clock between 100 MHz and 250 MHz for the AXI4-Debug Hub.
For detailed error triage, SVF programming flow, report_debug_core, and post-implementation debug verification commands, read references/debug-troubleshooting.md.
Quick checks:
report_debug_core and inspect debug-core utilization before programming hardware.© 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
SKILL.md and 3 other files (references) in vivado-debug of Shinei-Nouzen-Arch/FPGA-Agent.
Open the folder on GitHubat commit b60a52e
Vivado Debug 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Vivado Debug this skillShinei-Nouzen-Arch/FPGA-Agent | 180 | — | ~4.8k | Automated safety check: Pass | GPL-2.0 | |
| Trellis Session Insightmindfold-ai/Trellis | 15k | 4 repos | ~1.7k | Automated safety check: Pass | AGPL-3.0 | |
| Native Data FetchingCherryHQ/cherry-studio-app | 4k | 6 repos | ~2.9k | Automated safety check: Notes | MIT | |
| Debugging Executionsn8n-io/n8n | 207k | — | ~2.6k | Automated safety check: Pass | Custom licence | |
| Aoti Debugpytorch/pytorch | 104k | 1 repos | ~1.7k | Automated safety check: Pass | Custom licence | |
| Herdr Throwaway Reproductionherdrdev/herdr | 43k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 |
mindfold-ai/Trellis
Reach into past AI conversation history through the trellis mem CLI.
CherryHQ/cherry-studio-app
A skill your agent uses when implementing or debugging ANY network request, API call, or data fetching.
n8n-io/n8n
Debug failed or wrong-output workflow executions using executions tools.
pytorch/pytorch
Debug AOTInductor (AOTI) errors and crashes. An agent skill from pytorch/pytorch.
herdrdev/herdr
Runs a disposable, uniquely named Herdr session inside an existing one so runtime, pane, terminal or API bugs can be reproduced without touching the main session.
ultralisp/ultralisp
A skill your agent uses when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Shinei-Nouzen-Arch/FPGA-Agent
A skill your agent uses when the user needs Vivado design analysis, timing report interpretation, or timing-closure diagnosis.
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.
Shinei-Nouzen-Arch/FPGA-Agent
A skill your agent uses when the user needs Vivado implementation strategy selection or optimization.
Shinei-Nouzen-Arch/FPGA-Agent
A skill your agent uses when the user needs help with Vivado simulation strategy, flow selection, and debugging.
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…
Shinei-Nouzen-Arch/FPGA-Agent
Generate, review, explain, and execute Vivado/Vitis TCL scripts for FPGA design flows, and verify their execution results.
Categories
A skill your agent uses when the user needs help with Vivado in-system debugging, hardware programming, or debug core configuration. Vivado Debug is an agent skill from Shinei-Nouzen-Arch/FPGA-Agent. Use this skill when the user needs help with Vivado in-system debugging, hardware programming, or debug core configuration.
Vivado Debug fits situations like: the user needs help with Vivado in-system debugging; hardware programming; debug core configuration; VIO (Virtual I/O) usage for signal monitoring and control.
Run `npx skills add Shinei-Nouzen-Arch/FPGA-Agent --skill vivado-debug -a claude-code`. Or copy the skill folder (vivado-debug in Shinei-Nouzen-Arch/FPGA-Agent) into .claude/skills/vivado-debug in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Shinei-Nouzen-Arch/FPGA-Agent --skill vivado-debug -a codex`. Or copy the skill folder (vivado-debug in Shinei-Nouzen-Arch/FPGA-Agent) into .agents/skills/vivado-debug in your project. Codex loads it when a task matches its description.
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-debug -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-debug, .gemini/skills/vivado-debug, .github/skills/vivado-debug and .opencode/skills/vivado-debug in your project.
SKILL.md names no scripts, command-line tools or credentials: Vivado Debug is instructions for the agent only.
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.
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.
Vivado Debug 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.
About 4.8k tokens (SKILL.md is roughly 19k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.3k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Vivado Debug: Trellis Session Insight (mindfold-ai/Trellis, 15k stars), Native Data Fetching (CherryHQ/cherry-studio-app, 4k stars), Debugging Executions (n8n-io/n8n, 207k stars) and Aoti Debug (pytorch/pytorch, 104k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
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.