New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Edge Contribution

by exeex in exeex/edge-cores

Prepare, validate, submit, triage, and review open-source contributions to the shared Edge RV framework in edge-cores.

Apache-2.0Auto-check passedDevelopment

Install Edge Contribution

skills CLI
$ npx skills add exeex/edge-cores --skill edge-contribution -a claude-code

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

GitHub CLI
$ gh skill install exeex/edge-cores edge-contribution --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/exeex/edge-cores.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/edge-contribution .claude/skills/edge-contribution && 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
edge-contribution
GitHub stars
110
Token cost
~1.2k tokens
SKILL.md length
582 words
Files
5 (incl. references)
Skills in repo
9
Repo updated
First seen
Licence
Apache-2.0

At a glance

Prepare, validate, submit, triage, and review open-source contributions to the shared Edge RV framework in edge-cores.

  • Works in 6 steps: Fork https://github.com/exeex/edge-cores… → Clone the fork and add the canonical… → Create a focused branch from current… → …
  • Contributors need to file a centralized edge-cores issue
  • SKILL.md covers Work through a fork, File every issue in edge-cores, Make a reviewable change and Validate before submission, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Edge Contribution is an agent skill from exeex/edge-cores. Prepare, validate, submit, triage, and review open-source contributions to the shared Edge RV framework in edge-cores. Use when contributors need to file a centralized edge-cores issue, fork the repository, modify public edge-rv RTL or related software, choose regression tests, write a structured GitHub pull request, respond to review, or provide evidence suitable for human and agent-assisted issue and PR review.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `agents/openai.yaml`, `references/issue-triage.md` and `references/review-guide.md`).

It sits in Development, covering Pull requests. It works with GitHub. The repository describes itself as: The shortest path from PyTorch to custom ASICs. The licence is Apache-2.0.

When your agent uses it

  • Contributors need to file a centralized edge-cores issue
  • Fork the repository
  • Modify public edge-rv RTL
  • Related software

Example prompts

  • “/edge-contribution”

Workflow steps

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

  1. Fork https://github.com/exeex/edge-cores into the contributor's GitHub
  2. Clone the fork and add the canonical repository as upstream.
  3. Create a focused branch from current upstream/main.
  4. Keep unrelated changes out of the branch. Never commit build products,
  5. Modify public source and tests. Preserve existing public/private boundaries;
  6. Rebase or merge current upstream/main, rerun affected tests, push the

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 (its code samples are bash).

    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

Edge Contribution loads about 1.2k tokens when it runs, and up to ~2.8k if it reads all its reference files. Until then it costs about 109 tokens; SKILL.md has 582 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~109
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.8k

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). 582 words, ~1,232 tokens.

Download SKILL.mdSave it as .claude/skills/edge-contribution/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
edge-contribution
description
Prepare, validate, submit, triage, and review open-source contributions to the shared Edge RV framework in edge-cores. Use when contributors need to file a centralized edge-cores issue, fork the repository, modify public edge-rv RTL or related software, choose regression tests, write a structured GitHub pull request, respond to review, or provide evidence suitable for human and agent-assisted issue and PR review.

Contribute to Edge RV

Help the community evolve the shared public Edge RV framework through small, tested, reviewable pull requests.

Work through a fork

  1. Fork https://github.com/exeex/edge-cores into the contributor's GitHub account.
  2. Clone the fork and add the canonical repository as upstream.
  3. Create a focused branch from current upstream/main.
  4. Keep unrelated changes out of the branch. Never commit build products, private RTL, credentials, or generated reports.
  5. Modify public source and tests. Preserve existing public/private boundaries; do not edit generated src/edge-e3enc/edge_e3enc.v as design source.
  6. Rebase or merge current upstream/main, rerun affected tests, push the branch, and open a pull request against exeex/edge-cores:main.

Do not create a fork, push, or open a PR unless the user explicitly authorizes that external action. Local branches, edits, and tests remain normal implementation steps when requested.

File every issue in edge-cores

Open all project issues at https://github.com/exeex/edge-cores/issues, even when the affected code lives in src/edge-rv, src/edge-e3enc, another submodule, an example, or the software stack. Do not split community discussion across submodule issue trackers.

Follow .github/ISSUE_TEMPLATE/edge_issue.md and include the affected area, revision, reproduction steps, observed/expected behavior, environment, and available logs. Search existing edge-cores issues first and add evidence to an existing issue when it covers the same problem.

Read references/issue-triage.md when preparing an issue for periodic agent review or when reviewing and replying to the issue queue. Do not create, comment on, label, or close a GitHub issue unless the user has authorized that external action.

Make a reviewable change

  • Read CONTRIBUTING.md and LICENSING.md before editing. Contributions to files maintained directly by edge-cores use Apache-2.0; contributions to a submodule use that submodule's license, including CERN-OHL-P-2.0 for src/edge-rv.
  • State the problem and why it belongs in the shared Edge RV framework.
  • Prefer one architectural idea or bug fix per PR.
  • Add or update a focused test that fails without the change when practical.
  • Preserve instruction encodings, module ports, parameter defaults, and software ABI unless the PR explicitly proposes a migration.
  • Document correctness, performance, area, or complexity tradeoffs instead of presenting an optimization as universally better.
  • Treat existing user changes as owned work; do not rewrite unrelated files.
Show full SKILL.md (228 more words)Show less

Validate before submission

Read references/test-matrix.md, select tests from the changed surfaces, and run the smallest relevant test first. A ready PR must report exact commands and outcomes. Use a Draft PR when important tests remain unavailable or failing, and explain why.

For changes to public src/edge-rv RTL, run at least:

sh
./scripts/build-verilator.sh
./example/hello/run.sh
./example/tensor/run.sh
./example/actu/run.sh

Add compiler/runtime and Llama regressions when those surfaces are affected. Do not write “all tests pass” unless the listed commands actually completed successfully. Do not initialize private RTL to make a public regression pass.

Write the pull request

Follow .github/pull_request_template.md. Keep the PR body self-contained so a maintainer or review agent can understand the change without reconstructing the implementation from chat history. Include:

  • problem, motivation, and scope;
  • architectural, encoding, ABI, or compatibility impact;
  • exact validation commands and PASS/FAIL results;
  • untested cases, known limitations, and risk;
  • generated artifacts or benchmark assumptions, when relevant; and
  • specific areas where review attention is requested.

Read references/review-guide.md when reviewing a PR or preparing it for agent-assisted review.

Iterate after review

Answer review comments with code or evidence. Keep follow-up commits scoped, rerun tests affected by each revision, and update the PR validation table. Never hide a regression by loosening a golden result, tolerance, timeout, or skip list without explaining and justifying that semantic change.

Before handoff, report the branch, changed files, tests run, remaining risks, and whether the PR is draft or ready.

© 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 4 other files (references) in .codex/skills/edge-contribution of exeex/edge-cores.

  • SKILL.md
  • agents/openai.yaml
  • references/issue-triage.md
  • references/review-guide.md
  • references/test-matrix.md

Open the folder on GitHubat commit 68dc8aa

Compare with similar skills

Edge Contribution 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.

Edge Contribution compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Edge Contribution this skillexeex/edge-cores110—~1.2kAutomated safety check: PassApache-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Check PRonyx-dot-app/onyx32k2 repos~2.3kAutomated safety check: PassMIT
Contributor-First PR MergeHKUDS/OpenHarness16k1 repos~847Automated safety check: PassMIT
Create Pull Requestcline/cline70k1 repos~1.6kAutomated safety check: PassApache-2.0
Pull Request Title and Body Writeropeninterpreter/openinterpreter69k2 repos~1.1kAutomated safety check: PassApache-2.0

Similar skills

  • 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

  • Check PR

    onyx-dot-app/onyx

    Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions.

    32k GitHub starsUsed in 2 repos~2.3k tokens
    DevelopmentAuto-check passed

  • Contributor-First PR Merge

    HKUDS/OpenHarness

    Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.

    16k GitHub starsUsed in 1 repo~847 tokens
    DevelopmentAuto-check passed

  • Create Pull Request

    cline/cline

    Opens a GitHub pull request from your current branch with the gh CLI, after reviewing the commits and diff and gathering the details the PR needs.

    70k GitHub starsUsed in 1 repo~1.6k tokens
    DevelopmentAuto-check passed

  • Pull Request Title and Body Writer

    openinterpreter/openinterpreter

    Rewrites the title and body of one or more pull requests with gh, leading with why the change was made, then what changed, and describing only the net result.

    69k GitHub starsUsed in 2 repos~1.1k tokens
    DevelopmentAuto-check passed

  • GitHub Review Iteration

    prisma/orm

    Official

    Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.

    48k GitHub stars~2.2k tokensUpdated today
    DevelopmentAuto-check passed

More from exeex/edge-cores

All 9 skills in this repo

  • Edge 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…

    110 GitHub stars~1.7k tokensUpdated 12 days ago
    Auto-check: notes

  • 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.

    110 GitHub stars~892 tokensUpdated 12 days ago
    Auto-check passed

  • Integrate Your Design

    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.

    110 GitHub stars~1.4k tokensUpdated 12 days ago
    Auto-check passed

  • 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.

    110 GitHub stars~516 tokensUpdated 12 days ago
    Auto-check passed

  • 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…

    110 GitHub stars~1.1k tokensUpdated 12 days ago
    Auto-check passed

  • 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…

    110 GitHub stars~1k tokensUpdated 12 days ago
    Auto-check passed

Works with

Categories

Questions about Edge Contribution

What does Edge Contribution do?

Prepare, validate, submit, triage, and review open-source contributions to the shared Edge RV framework in edge-cores. Edge Contribution is an agent skill from exeex/edge-cores. Prepare, validate, submit, triage, and review open-source contributions to the shared Edge RV framework in edge-cores.

When should I use Edge Contribution?

Edge Contribution fits situations like: contributors need to file a centralized edge-cores issue; fork the repository; modify public edge-rv RTL; related software.

How do I install Edge Contribution in Claude Code?

Run `npx skills add exeex/edge-cores --skill edge-contribution -a claude-code`. Or copy the skill folder (.codex/skills/edge-contribution in exeex/edge-cores) into .claude/skills/edge-contribution in your project. Claude Code loads it when a task matches its description.

How do I install Edge Contribution in Codex?

Run `npx skills add exeex/edge-cores --skill edge-contribution -a codex`. Or copy the skill folder (.codex/skills/edge-contribution in exeex/edge-cores) into .agents/skills/edge-contribution in your project. Codex loads it when a task matches its description.

Can I use Edge Contribution 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 edge-contribution -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/edge-contribution, .gemini/skills/edge-contribution, .github/skills/edge-contribution and .opencode/skills/edge-contribution in your project.

What does Edge Contribution need to run?

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

Does Edge Contribution 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 Edge Contribution 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 Edge Contribution use?

Edge Contribution 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 Edge Contribution use?

About 1.2k tokens (SKILL.md is roughly 4.9k 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 1.5k tokens, read only when the agent opens those files.

What are the alternatives to Edge Contribution?

Skills that share tags, products or a category with Edge Contribution: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Check PR (onyx-dot-app/onyx, 32k stars), Contributor-First PR Merge (HKUDS/OpenHarness, 16k stars) and Create Pull Request (cline/cline, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Edge Contribution?

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.