Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mapleleavessssssss-wq/vivado-mcp --skill vivado-timing-closuregit clone --depth 1 https://github.com/mapleleavessssssss-wq/vivado-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mapleleavessssssss-wq/vivado-mcp/vivado-timing-closure)<a href="https://agentmods.dev/skills/mapleleavessssssss-wq/vivado-mcp/vivado-timing-closure"><img src="https://agentmods.dev/badge/skills/mapleleavessssssss-wq/vivado-mcp/vivado-timing-closure/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mapleleavessssssss-wq/vivado-mcp/vivado-timing-closure"><img src="https://agentmods.dev/badge/skills/mapleleavessssssss-wq/vivado-mcp/vivado-timing-closure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00056 | $0.01022 |
| Opus 5.5 | $0.00022 | $0.00409 |
| Sonnet 5.5 | $0.00011 | $0.00204 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade A, and why
vivado-timing-closure scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vivado 时序收敛
可用入口:get_project_info、get_timing_report、get_utilization_report、get_critical_warnings、get_cdc_report、run_tcl、safe_tcl。
只分析时不启动构建;用户要求优化时继续完成已授权的 RTL/XDC/策略修复。保持接口、目标频率和功能语义;改变这些条件需要对应授权。此流程不包含硬件编程。
记录可比较的基线
现场用 get_project_info 确认工程、器件与 run;报告必须对应当前 source/XDC。离线输入不需要 Vivado 会话,但结论只覆盖所给文件。
get_timing_report(session_id="design", output_format="json")
get_timing_report(output_format="json", report_file="/work/reports/before.rpt")
记录 provenance、stage、context、parse_status、metrics 和 verdict。setup、hold、pulse_width 的缺失值是 null,不能当作零。met_observed_checks 只说明已观察指标满足;verdict.signoff 为 false,不等于完整签核。
需要比较时,用宿主文件工具把返回的完整 JSON 正文原样保存为新基线文件,包含 schema、来源和上下文;不要只存 metrics,也不要把原始 Tcl 文本传给 baseline_file。MCP 不会自动写入报告。
分类后修复
- 先核对时钟与约束覆盖,再解释最差路径。有现场会话时用
run_tcl获取report_clock_interaction -return_string、report_methodology -return_string;离线缺少旁证时列为未验证。CDC 嫌疑需要结构与协议证据。 - 用返回路径与可用资源/告警报告区分逻辑深度、扇出/布线、拥塞、I/O 约束和时钟问题;现场可调用
get_utilization_report、get_critical_warnings。布局策略不能修复逻辑协议错误。 - 一次只验证一个根因假设。保留 baseline 和最佳候选,记录具体 RTL/XDC/策略变更。用户输入的路径/对象通过
safe_tcl,不要拼入原始 Tcl。 set_false_path和 multicycle 不是性能优化手段;它们与 waiver 只能依据真实功能关系,不能用于消除真实违例。没有协议证据时报告不确定性,继续不依赖该例外的分析。- CDC 嫌疑通过
get_cdc_report与实际同步结构核对。set_clock_groups会覆盖重叠路径的set_max_delay -datapath_only;用report_exceptions核实生效范围。set_bus_skew需用独立report_bus_skew检查,不能从 WNS 推断。
同条件复测
重跑受影响阶段后读取新报告,或对新保存的原始报告进行离线比较:
get_timing_report(session_id="design", output_format="json", baseline_file="/work/reports/baseline.json")
get_timing_report(output_format="json", report_file="/work/reports/after.rpt", baseline_file="/work/reports/baseline.json")
先读 comparison.status 与 reasons,再解释 deltas。不同/未知设计或阶段不能比较;即使 design/device/stage 相同,约束身份未知时差值仅为观察,不证明优化效果。该接口的比较 authoritative 为 false,须用独立的输入、约束和路径覆盖记录说明可比性。
收敛验收需同一当前 post-route 设计的 setup/hold/pulse-width、完整约束覆盖、route、DRC/methodology 和适用 CDC 检查。仅 WNS 改善或摘要非负不够。达到目标后交付证据;连续两轮无实质改善时保留最佳结果并重新归因,受总预算限制停止,不把停滞称成功。报告数值变化、可比性、变更、剩余违例和未验证检查。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 23d ago First seen · 45 lines · 56 tokens per session scan A 71932f8f62bb
vivado-timing-closure is a skill published in the GitHub repository mapleleavessssssss-wq/vivado-mcp (157 stars, last pushed 24d ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,022 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-23.
Other skills, from other repositories
readable-verilog-generator
Use when creating, writing, reviewing, annotating, repairing, refactoring, or validating readable Verilog RTL, including synthesizable Verilog-2001 .v files, existing-RTL analysis, semantic comment annotation, testbench scaffold planning, ASIC-quality review, local or remote Vivado/xsim validation, evidence-backed…
drc-fix
Diagnose and fix Design Rule Check (DRC) violations in a layout or GDS. Use when the user says "fix DRC", "DRC clean", "resolve spacing errors", "my layout fails DRC", or shares a DRC report from Calibre, Klayout, or Magic.
hw-debug-loop
Closed-loop hardware debug methodology for half-duplex protocol ICs when BFM passes but real-silicon connecttest FAILs (Category B/C from the A/B/C extraction-gap analysis). Use after spec-to-rtl + flowcompliancecheck have all PASSed, the SOF has been burned to FPGA, and the host-side acceptance test (e.g.…
lvs-triage
Triage Layout-vs-Schematic (LVS) mismatches — missing connections, short/open nets, device parameter mismatches, unmatched instances. Use when the user says "LVS", "layout vs schematic", "LVS mismatch", "netlist compare", "Calibre LVS", "Netgen".
synth-doctor
Automatically diagnose and fix EDA tool failures. Parses Yosys synthesis and OpenROAD P&R logs, classifies errors into known patterns, and provides actionable fix commands. Triggers when: synthesis fails, P&R fails, 'why did synth fail', 'fix synthesis error', 'DRC violation', or any EDA tool error during Phase 2.…
fpga-led-probe-allocation
Codify FPGA LED probe allocation patterns (instantaneous / pulse-stretched / sticky / byte-display) and produce an FPGA-top template with comment-table mapping (LED → signal → expected behaviour per test stage). Use when a fresh agent has to verify a chip on a DE10-Lite-class board with no scope and only the on-board…