Qt C++ Code Review
x-tools-author/x-tools
Read-only review of Qt6 C++ code that combines a deterministic lint script with six parallel analysis agents and reports only high-confidence issues.
Integrate and publish your own accelerator or ASIC design, DMA, and DTCM/SRAM with the Edge RV64 scalar core and command path.
Install Integrate Your Design
$ npx skills add exeex/edge-cores --skill integrate-your-design -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install exeex/edge-cores integrate-your-design --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/exeex/edge-cores.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/integrate-your-design .claude/skills/integrate-your-design && 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 "integrate-your-design" agent skill from https://github.com/exeex/edge-cores/tree/main/.codex/skills/integrate-your-design into .claude/skills/integrate-your-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "integrate-your-design", 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/exeex/edge-cores/tree/main/.codex/skills/integrate-your-designType 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 exeex/edge-cores --skill integrate-your-design -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install exeex/edge-cores integrate-your-design --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/exeex/edge-cores.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.codex/skills/integrate-your-design .agents/skills/integrate-your-design && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "integrate-your-design" agent skill from https://github.com/exeex/edge-cores/tree/main/.codex/skills/integrate-your-design into .agents/skills/integrate-your-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "integrate-your-design", 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 exeex/edge-cores --skill integrate-your-design -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install exeex/edge-cores integrate-your-design --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/exeex/edge-cores.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.codex/skills/integrate-your-design .cursor/skills/integrate-your-design && 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 "integrate-your-design" agent skill from https://github.com/exeex/edge-cores/tree/main/.codex/skills/integrate-your-design into .cursor/skills/integrate-your-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "integrate-your-design", 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/exeex/edge-cores.git --path .codex/skills/integrate-your-design--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 exeex/edge-cores --skill integrate-your-design -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install exeex/edge-cores integrate-your-design --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/exeex/edge-cores.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.codex/skills/integrate-your-design .gemini/skills/integrate-your-design && 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 "integrate-your-design" agent skill from https://github.com/exeex/edge-cores/tree/main/.codex/skills/integrate-your-design into .gemini/skills/integrate-your-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "integrate-your-design", 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 exeex/edge-cores integrate-your-designInstalls 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 exeex/edge-cores --skill integrate-your-design -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/exeex/edge-cores.git skills-src && mkdir -p .github/skills && cp -r skills-src/.codex/skills/integrate-your-design .github/skills/integrate-your-design && 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 "integrate-your-design" agent skill from https://github.com/exeex/edge-cores/tree/main/.codex/skills/integrate-your-design into .github/skills/integrate-your-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "integrate-your-design", 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 exeex/edge-cores --skill integrate-your-design -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install exeex/edge-cores integrate-your-design --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/exeex/edge-cores.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.codex/skills/integrate-your-design .opencode/skills/integrate-your-design && 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 "integrate-your-design" agent skill from https://github.com/exeex/edge-cores/tree/main/.codex/skills/integrate-your-design into .opencode/skills/integrate-your-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "integrate-your-design", 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.
Facts
- Skill name
integrate-your-design- GitHub stars
- 110
- Token cost
- ~1.4k tokens
- SKILL.md length
- 643 words
- Files
- 9 (incl. references)
- Skills in repo
- 9
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Integrate and publish your own accelerator or ASIC design, DMA, and DTCM/SRAM with the Edge RV64 scalar core and command path.
- Works in 7 steps: Fork edge-cores, clone the fork, and… → Add the ASIC design below src/ as a Git… → Connect the command interface → …
- Forking edge-cores
- SKILL.md covers Integration workflow, Load only the needed reference and Preserve these invariants
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Integrate Your Design is an agent skill from exeex/edge-cores. Integrate and publish your own accelerator or ASIC design, DMA, and DTCM/SRAM with the Edge RV64 scalar core and command path. Use when forking edge-cores, adding a design as a src Git submodule, defining opcode8 and setcsr/start/sync instructions, carrying imm8/GPR snapshot parameters, connecting DMA/SRAM/LSU debug access, using low-precision FPU instructions for bring-up, writing RTL/C++ tests, preparing research artifacts, protecting RTL, or citing the shared framework.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including reference files (for example `agents/openai.yaml`, `references/execution-model.md` and `references/instruction-interface.md`).
It sits in Development. It works with C++ and Git. The repository describes itself as: The shortest path from PyTorch to custom ASICs. The licence is Apache-2.0.
When your agent uses it
- Forking edge-cores
- Adding a design as a src Git submodule
- Defining opcode8 and setcsr/start/sync instructions
- Carrying imm8/GPR snapshot parameters
Example prompts
- “/integrate-your-design”
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Fork edge-cores, clone the fork, and initialize its submodules. Keep the
- Add the ASIC design below src/ as a Git submodule. Create a new repository
- Connect the command interface
- Design a DMA when the ASIC owns independent SRAM. Define each memory's role,
- Add LSU read/write access when RISC-V software must initialize or inspect
- Use the optional FPU during early software development to generate inputs,
- Run focused command, snapshot, DMA, SRAM, and LSU RTL tests before the public
What it can do on your machine
Read from SKILL.md and the folder at commit 68dc8aa. 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.
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
Integrate Your Design loads about 1.4k tokens when it runs, and up to ~6.5k if it reads all its reference files. Until then it costs about 125 tokens; SKILL.md has 643 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.
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 exeex/edge-cores at commit 68dc8aa, republished under its Apache-2.0 licence (© exeex). 643 words, ~1,419 tokens.
Download SKILL.mdSave it as
.claude/skills/integrate-your-design/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.- name
- integrate-your-design
- description
- Integrate and publish your own accelerator or ASIC design, DMA, and DTCM/SRAM with the Edge RV64 scalar core and command path. Use when forking edge-cores, adding a design as a src Git submodule, defining opcode8 and setcsr/start/sync instructions, carrying imm8/GPR snapshot parameters, connecting DMA/SRAM/LSU debug access, using low-precision FPU instructions for bring-up, writing RTL/C++ tests, preparing research artifacts, protecting RTL, or citing the shared framework.
Integrate Your Own Design
Welcome an independently designed accelerator, DMA, DTCM/SRAM, or complete ASIC set into the shared Edge RV platform without breaking command ordering, snapshot semantics, or memory visibility. Treat the user's design as the main contribution and Edge RV as the integration framework.
Integration workflow
- Fork
edge-cores, clone the fork, and initialize its submodules. Keep the shared monorepo structure so the design can use the maintained build, simulation, synthesis, software, and contribution workflows. - Add the ASIC design below
src/as a Git submodule. Create a new repository for a new design or attach an existing repository. Keep the ASIC's history, license, and ownership separate; record its path and revision in.gitmodulesand the parent repository. - Connect the command interface:
- allocate an unused
opcode8value and register its instruction class in the IFU/predecoder; - provide accelerator-specific
setcsr/set_*, asynchronousstart, andsyncoperations, using ACTU as the reference interface; - carry
imm8and the captured GPR parameter to the ASIC; - when using
edge-rv, consume the resolved snapshot value rather than a later live register value; and - update the intrinsic encoder, compact command queue, accel-pipe decode, readiness/backpressure, ports, and exact-encoding tests together.
- allocate an unused
- Design a DMA when the ASIC owns independent SRAM. Define each memory's role, ports, address map, width, latency, and ownership policy. A TPU-style systolic array normally needs at least an I/O SRAM and weight buffer, with DMA paths between system memory and both ASIC-visible stores.
- Add LSU read/write access when RISC-V software must initialize or inspect
I/O SRAM, weight SRAM, or another private memory during bring-up. Inspect
the
edge-rvLSU boundary and the read-only integration boundary exposed byedge-e3enc; use an explicit arbiter or multi-port contract and preserve byte strobes, response latency, backpressure, and memory visibility. Treatsrc/edge-e3enc/edge_e3enc.vas a generated reference artifact, never as editable design source. - Use the optional FPU during early software development to generate inputs,
implement reference/fallback kernels, and compare ASIC outputs. The shared
software/RTL supports NVFP4, FP8 E4M3/E5M2, BF16, and FP16 memory-format
instructions; read
src/edge-rv-lite/README.mdfor encodings, conversion behavior, and the area tradeoff. Disable the FPU later if the finished ASIC and software no longer require it. - Run focused command, snapshot, DMA, SRAM, and LSU RTL tests before the public software harness. Report the exact submodule revisions and any boundary that remains unverified.
Show full SKILL.md (259 more words)Show less
Load only the needed reference
- Read references/instruction-interface.md
when allocating opcodes or adding C++
set_*,start, orsyncwrappers. - Read references/execution-model.md when working on snapshots, queue depth, self-serializing starts, redirect/kill, or IFU/predecoder sync joins.
- Read references/memory-integration.md
when connecting DMA, SRAM, LSU, arbitration, address conversion, or
lsu_store_block/mem_store_block. - Read references/rtl-patterns.md only when implementing RTL for snapshot issue, sync join, pending start, or SRAM request blocking.
- Read references/verification.md before testing or reviewing an implementation.
- Read references/paper-evaluation.md when defining paper contributions, claims, baselines, or PPA results.
- Read references/paper-release.md only for a paper, artifact package, protected RTL release, or citation task.
Preserve these invariants
- Consume a snapshotted GPR value, never a later live register-file value.
- Match reusable snapshot slots with full sequence and epoch ownership.
- Keep setup and start commands ordered; never lose commands under backpressure or redirect.
- Make
startasynchronous and consecutive starts self-serializing without a mandatorysyncbetween them. - Make
syncawait all earlier work through the scalar join path. - If the optional scalar-store interlock is implemented, prevent both new and already-running ASIC/DMA SRAM effects while it is asserted.
- Use DMA for performance data movement; reserve scalar SRAM access for debug and bring-up.
- Preserve behavior when command, pending-start, or snapshot depth changes.
- Cite edge-cores and record the exact revision in a paper artifact.
- Attribute the Edge RV execution/snapshot framework to edge-cores; claim only the user's new ASIC and integration work as the paper's contribution.
- Never publish private source, symbol mappings, private paths, or unlicensed RTL in a protected release.
Report the files changed, exact tests run, and any integration surface that remains unverified.
© exeex, Apache-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 8 other files (references) in .codex/skills/integrate-your-design of exeex/edge-cores.
- SKILL.md
- agents/openai.yaml
- references/execution-model.md
- references/instruction-interface.md
- references/memory-integration.md
- references/paper-evaluation.md
- references/paper-release.md
- references/rtl-patterns.md
- references/verification.md
Open the folder on GitHubat commit 68dc8aa
Compare with similar skills
Integrate Your Design 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 |
|---|---|---|---|---|---|---|
| Integrate Your Design this skillexeex/edge-cores | 110 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Qt C++ Code Reviewx-tools-author/x-tools | 1.1k | 2 repos | ~4.3k | Automated safety check: Pass | BSD-3-Clause | |
| pybind11 Release Preparationpybind/pybind11 | 18k | — | ~1.7k | Automated safety check: Pass | Custom licence | |
| Qt Cpp ReviewSerial-Studio/Serial-Studio | 7.2k | — | ~4.3k | Automated safety check: Pass | Custom licence | |
| pybind11 Release Publicationpybind/pybind11 | 18k | — | ~2.5k | Automated safety check: Pass | Custom licence | |
| ExecuTorch Binary Size Reductionpytorch/executorch | 5.1k | — | ~793 | Automated safety check: Pass | Custom licence |
Similar skills
pybind11 Release Preparation
pybind/pybind11
Opens the pybind11 release-preparation pull request: picking the release base, bumping the version in common.h and integrating the changelog, following docs/release.rst.
Qt Cpp Review
Serial-Studio/Serial-Studio
Qt6/C++ deep code review for Serial Studio. An agent skill from Serial-Studio/Serial-Studio.
pybind11 Release Publication
pybind/pybind11
Walks a maintainer through publishing a pybind11 release after the preparation PR merges, with preflight checks, confirmations before each push and a GitHub release.
ExecuTorch Binary Size Reduction
pytorch/executorch
Measures and shrinks the ExecuTorch runtime binary by building a size test, analyzing it with bloaty and landing each reduction as its own pull request.
OBS Plugin Dependency Upgrade
sorayuki/obs-multi-rtmp
Updates the obs-multi-rtmp plugin repo to the latest upstream plugin template and OBS Studio version, including dependency metadata, then rebuilds it with CMake.
More from exeex/edge-cores
All 9 skills in this repoEdge Bringup
exeex/edge-cores
Prepare a macOS or Ubuntu machine for edge-e3 development, diagnose missing Verilator/LLVM/Python dependencies, initialize the public repository, and answer or act on the example prompts in the root…
Edge Contribution
exeex/edge-cores
Prepare, validate, submit, triage, and review open-source contributions to the shared Edge RV framework in edge-cores.
Rtl Release Packager
exeex/edge-cores
Generate, compare, validate, and prepare mixed public/private RTL release packages with symbol-obfuscated proprietary RTL and unchanged public RTL dependencies.
Edge Synth Report
exeex/edge-cores
Run and diagnose the repository-local Yosys synthesis profiles for edge-e3 encrypted product RTL, edge-rv, and edge-rv-lite, then summarize FPGA resource reports.
Llama Nnc
exeex/edge-cores
Develop and profile the edge-e3 PyTorch-to-NNC flow, including nnc/compiler.py lowering and generated ABI, example/llama smoke models, cpp/libnn runtime operators, BF16 correctness checks, and…
Software Harness
exeex/edge-cores
Run, extend, debug, or review the public edge-e3 bare-metal software harness, including encrypted Verilator builds, hello and tensor examples, all example/llama/model smoke cases, PyTorch BF16…
Related
Categories
Questions about Integrate Your Design
What does Integrate Your Design do?
Integrate and publish your own accelerator or ASIC design, DMA, and DTCM/SRAM with the Edge RV64 scalar core and command path. Integrate Your Design is an agent skill from exeex/edge-cores. Integrate and publish your own accelerator or ASIC design, DMA, and DTCM/SRAM with the Edge RV64 scalar core and command path.
When should I use Integrate Your Design?
Integrate Your Design fits situations like: forking edge-cores; adding a design as a src Git submodule; defining opcode8 and setcsr/start/sync instructions; carrying imm8/GPR snapshot parameters.
How do I install Integrate Your Design in Claude Code?
Run `npx skills add exeex/edge-cores --skill integrate-your-design -a claude-code`. Or copy the skill folder (.codex/skills/integrate-your-design in exeex/edge-cores) into .claude/skills/integrate-your-design in your project. Claude Code loads it when a task matches its description.
How do I install Integrate Your Design in Codex?
Run `npx skills add exeex/edge-cores --skill integrate-your-design -a codex`. Or copy the skill folder (.codex/skills/integrate-your-design in exeex/edge-cores) into .agents/skills/integrate-your-design in your project. Codex loads it when a task matches its description.
Can I use Integrate Your Design 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 exeex/edge-cores --skill integrate-your-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/integrate-your-design, .gemini/skills/integrate-your-design, .github/skills/integrate-your-design and .opencode/skills/integrate-your-design in your project.
What does Integrate Your Design need to run?
SKILL.md names no scripts, command-line tools or credentials: Integrate Your Design is instructions for the agent only.
Does Integrate Your Design 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 Integrate Your Design 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 Integrate Your Design use?
Integrate Your Design is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Integrate Your Design use?
About 1.4k tokens (SKILL.md is roughly 5.7k 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 5k tokens, read only when the agent opens those files.
What are the alternatives to Integrate Your Design?
Skills that share tags, products or a category with Integrate Your Design: Qt C++ Code Review (x-tools-author/x-tools, 1.1k stars), pybind11 Release Preparation (pybind/pybind11, 18k stars), Qt Cpp Review (Serial-Studio/Serial-Studio, 7.2k stars) and pybind11 Release Publication (pybind/pybind11, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Integrate Your Design?
exeex (a GitHub user) maintains it in exeex/edge-cores, which has 110 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on September 26, 2026.
Source: exeex/edge-cores on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.