Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/vibeic/vibe-icnpx agentmods add skills/vibeic/vibe-ic/hls-c2rtlWrote 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/vibeic/vibe-ic/hls-c2rtl)<a href="https://agentmods.dev/skills/vibeic/vibe-ic/hls-c2rtl"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/hls-c2rtl/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/vibeic/vibe-ic/hls-c2rtl"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/hls-c2rtl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00079 | $0.01050 |
| Opus 5 | $0.00039 | $0.00525 |
| Sonnet 5 | $0.00016 | $0.00210 |
| Haiku 4.5 | $0.00008 | $0.00105 |
Grade A, and why
hls-c2rtl 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 11d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HLS (C/C++ → RTL)
Doctrine (v0.1.50): 把修法寫進工具，而非寫進 prompt. The HLS tool is the source of RTL; AI is the backstop on pragma narrative.
High-Level Synthesis is the entry point for DSP / AI accelerator /
image-processing blocks where the algorithm is already written in
C/C++. This skill guides the lowering from algorithm to RTL with
pragmas / directives and hands off to /rtl-review.
Mandatory Deterministic Preflight
# 1. After HLS emits RTL, the standard plugin gates apply IMMEDIATELY:
python3 plugins/vibe-ic/programs/rtl_review_aggregate.py \
--rtl-dir <hls-output-dir> # see skills/rtl-review for backing
python3 plugins/vibe-ic/programs/rtl_hygiene_lint.py \
<hls-output-dir>/*.v
python3 plugins/vibe-ic/programs/reset_discipline_check.py \
--rtl-dir <hls-output-dir>
HLS-emitted RTL is NOT exempt from plugin gates — many HLS tools emit RTL with subtle latch / reset-discipline issues that downstream synthesis catches only after wasted hours. Refuse to claim "HLS RTL is correct" without running the same gates a hand-authored RTL would face.
When to use
- Algorithmic block (filter, matrix multiply, feature extractor) exists in C/C++/SystemC
- Dataflow-heavy pipeline where manual RTL would be error-prone
- Design-space exploration across latency vs throughput vs area
- Target flow: Vitis HLS, Catapult HLS, Stratus HLS, XLS (open source, Google)
Inputs
- Source file(s) — C/C++/SystemC
- Test vectors (golden I/O pairs)
- Target: FPGA (bitstream) vs ASIC (Verilog netlist)
- Constraints: target clock period, latency budget, throughput, resource limits
- Tool choice
Workflow
- Clean the source: remove pointer chasing, dynamic allocation, recursion — HLS only digests statically-bounded C
- Interface synthesis: decide on AXI-Stream, AXI-Lite, memory-mapped BRAM, or wire handshake for each argument
- Apply pragmas / directives:
#pragma HLS PIPELINE II=1for loops#pragma HLS UNROLL factor=N#pragma HLS DATAFLOWfor stream pipelines#pragma HLS ARRAY_PARTITIONfor memory banks
- Co-simulate C vs generated RTL using the test vectors
- Emit RTL and hand off to
/rtl-reviewand/testbench-gen - Report PPA — estimated from HLS tool's synthesis report
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 100 lines · 79 tokens per session scan A 06c0494e484d
hls-c2rtl is a skill published in the GitHub repository vibeic/vibe-ic (23 stars, last pushed today), licensed Apache-2.0. It adds 79 tokens to every session and 1,050 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
doca-argp
Use this skill for hands-on DOCA Arg Parser CLI work on a shipped sample or new DOCA-using app — adding / removing / renaming flags; wiring docaargpinit → register params → docaargpstart → docaargpdestroy in order; picking a parameter type from the full public enum (DOCAARGPTYPESTRING, INT, BOOLEAN, DEVICE, DEVICEREP…
embedded-stm32
Best practices for embedded C/C++ development on STM32 microcontrollers using the HAL, covering peripherals, DMA, interrupts, memory constraints, and hardware-focused testing. Use when writing STM32 HAL code, configuring peripherals generated by STM32CubeMX, working with interrupts or DMA, debugging with SWD/JTAG…
hip-kernel-optimization
This skill should be used when writing or tuning HIP kernels on AMD/NVIDIA GPUs, covering memory coalescing, shared-memory tiling, bank conflict avoidance, warp primitives, occupancy, vectorization, async ops, loop unrolling, and profiling.
cuda
Use when writing CUDA kernels, managing the thread, block, and grid hierarchy, tiling shared memory, using streams, setting nvcc flags, or using Thrust. Not for kernel debugging: use cuda-debugging.
acad-arx-wizard
Agentic ObjectARX project scaffolding for AutoCAD 2027 / Visual Studio 2026. Replaces the broken .vsz VsWizardEngine wizard with a PowerShell script that generates identical C++ project files. Works for new ARX/DBX/CRX projects and add-on class wizards (Jig, Reactors, Custom Object, MFC, .NET Wrapper, COM Wrapper…
cuda
CUDA C/C++ skill for NVIDIA GPU kernel programming. Use when writing CUDA kernels, managing thread/block/grid hierarchy, optimizing memory access patterns, using streams and async copies, configuring nvcc flags, or integrating Thrust. Activates on queries about CUDA kernels, nvcc, shared memory, warp divergence…