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

Wally Release

by RunanywhereAI in RunanywhereAI/wally

Cut an Wally product release (independent of SDK version) — version bump, release:patch label, merge, auto-tag, bottles.

MITAuto-check passed

Install Wally Release

skills CLI
$ npx skills add RunanywhereAI/wally --skill wally-release -a claude-code

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

GitHub CLI
$ gh skill install RunanywhereAI/wally wally-release --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/RunanywhereAI/wally.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/wally-release .claude/skills/wally-release && 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
wally-release
GitHub stars
1.6k
Token cost
~1.3k tokens
SKILL.md length
563 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Cut an Wally product release (independent of SDK version) — version bump, release:patch label, merge, auto-tag, bottles.

  • Works in 7 steps: Facts → Pin the SDK kit first → Product version + label → …
  • Shipping wally after a published SDK kit
  • SKILL.md covers 0. Facts, 1. Pin the SDK kit first, 2. Product version + label and 3. CI bar before merge, plus 4 more sections
  • Calls gh; needs GITHUB_TOKEN

What it does

Wally Release is an agent skill from RunanywhereAI/wally. Cut an Wally product release (independent of SDK version) — version bump, release:patch label, merge, auto-tag, bottles. Use when shipping wally after a published SDK kit, or when Homebrew / notarization / private overlays must not leak into public bottles.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with Homebrew, GitHub, macOS and C++. The repository describes itself as: Get up and running with GLM-5.3-flash, DeepSeek, Gemma and other open source frontier models. The licence is MIT.

When your agent uses it

  • Shipping wally after a published SDK kit
  • Homebrew / notarization / private overlays must not leak into public bottles

Example prompts

  • “/wally-release”

Requirements

  • A credential in GITHUB_TOKEN

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Facts
  2. Pin the SDK kit first
  3. Product version + label
  4. CI bar before merge
  5. Merge triggers the release
  6. Verify the GitHub Release
  7. Overlays after the public cut

What it can do on your machine

Read from SKILL.md and the folder at commit 4687fde. 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

    Shell commands in SKILL.md call:

    • gh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • GITHUB_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Wally Release loads about 1.3k tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 563 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~68
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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 RunanywhereAI/wally at commit 4687fde, republished under its MIT licence (© RunanywhereAI). 563 words, ~1,280 tokens.

Download SKILL.mdSave it as .claude/skills/wally-release/SKILL.md (or your agent's skills folder).
name
wally-release
description
Cut an Wally product release (independent of SDK version) — version bump, release:patch label, merge, auto-tag, bottles. Use when shipping wally after a published SDK kit, or when Homebrew / notarization / private overlays must not leak into public bottles.

Wally release

Repo: RunanywhereAI/wally. Product version is [product] version in versions.toml — CMake's project(wally VERSION …) reads it directly; Cargo.toml's version and Formula/wally.rb's version stamp must match it (scripts/ci/check-versions.py, and build.rs asserts the Cargo.toml / versions.toml pair at build time). Independent of the SDK kit pin.

Do this after the SDK GitHub Release this pin targets is published (not draft). Companion: wally-kit-pin, then this skill.

0. Facts

  • Label form is release:patch / release:minor / release:major (colon). .github/workflows/auto-tag.yml matches that spelling only.
  • Merge to main with that label → auto-tag pushes v<CMakeLists VERSION> and dispatches release.yml. Tag pushes with GITHUB_TOKEN do not trigger other workflows; the dispatch is required.
  • Checkout in auto-tag uses persist-credentials: true so the tag push works.
  • release.yml jobs: macos (macos-arm64 bottle), windows-arm64 and windows (windows-x86_64 zip), linux (linux-x86_64 bottle), then publish assembles the GitHub Release. macos runner must be macos-26 (Xcode 26 / Swift 6.2). macos-15 is Swift 6.1 and cannot resolve the SDK package; macos-14 is Swift 5.10.
  • Public bottle / zip is OSS only. NeuRT / QHexRT overlays are workflow artifacts or WALLY_PRIVATE_OVERLAY, never public release assets, never Homebrew bottles.
  • Linux bottles are not a v1 merge blocker.

1. Pin the SDK kit first

If this train needs new engines (sherpa routable, windows-arm64 kit, NeuRT image gen): bump cmake/sdk-pin.cmake + CI ref: v$SDK in the same PR (wally-kit-pin). CI must be green on that pin before you bump the product version.

2. Product version + label

Next patch after 0.7.0 is 0.7.1. Bump versions.toml [product] version, Cargo.toml's version, and any Formula version stamp in the same commit (scripts/ci/check-versions.py fails the PR if they drift). Open/update the PR and apply exactly one release:patch (or minor/major).

gh pr create --label release:patch is not atomic with the opened event — verify the label landed (gh pr view --json labels).

3. CI bar before merge

Required: macOS product e2e (scripts/test/e2e.sh ./build/wally) and Windows e2e against the pinned kit. agents-sync.yml must pass (scripts/ci/check-agents-sync.sh).

Re-check immediately before merge (a rollup of SUCCESS can hide checks that have not started):

bash
gh pr checks <pr> --repo RunanywhereAI/wally --json name,state,bucket \
  --jq '[.[] | select(.state == null or .state == "")] | length'   # must be 0

Do not merge on a partial matrix. Confirm bypass eligibility the same way as the SDK (bypass_pull_request_allowances) before --admin.

Show full SKILL.md (218 more words)Show less

4. Merge triggers the release

bash
gh pr merge <pr> --repo RunanywhereAI/wally --squash --admin   # only if allow-listed

auto-tag.yml tags v$PRODUCT and dispatches release.yml. Unlike the SDK train, there is typically no pre-merge candidate to reuse — let this release.yml run. Watch it; do not cancel macos for being "slow" (MLX host link + e2e).

5. Verify the GitHub Release

bash
gh release view v$PRODUCT --repo RunanywhereAI/wally --json isDraft,assets \
  --jq '{isDraft, names: [.assets[].name]}'

Expect wally-$PRODUCT-macos-arm64.tar.gz, wally-$PRODUCT-windows-x86_64.zip, wally-$PRODUCT-windows-arm64.zip, and wally-$PRODUCT-linux-x86_64.tar.gz (each + .sha256). Must be empty for *neurt*, *qhexrt*, *private*.

If release.yml still creates a non-draft release, that is the live product cut — confirm asset names before anyone bottles from it. Stamp Formula from the macOS sidecar (scripts/release/stamp-formula.py) when that path is wired.

6. Overlays after the public cut

Private packs stay off the public release. For a machine that should load NeuRT / QHexRT:

bash
export WALLY_PRIVATE_OVERLAY=/path/to/RunAnywhere-cpp-desktop-macos-arm64-neurt-private-v$SDK.tar.gz
# or windows-arm64-qhexrt

WALLY_REQUIRE_PRIVATE=1 fails closed when the overlay is missing. Default CI must pass without it.

Device proof is not CI: rebuild overlay wally on a Mac (NeuRT image gen) and on Snapdragon ARM64 Windows (QHexRT). Match QAIRT to the device Hexagon skel (ADSP_LIBRARY_PATH); see wally-e2e. Public v0.5.1 bottles are OSS — NeuRT/QHexRT will never appear in wally backends on those artifacts.

Do not

  • Attach wally-* assets onto an SDK GitHub Release.
  • Pin fetch-kit.sh at a draft SDK tag.
  • Ship NeuRT / QHexRT inside the public bottle "just this once".
  • Use macos-14 or macos-15 for the Apple job (need macos-26 / Swift 6.2).
  • Weaken assert-backends.sh when HAS_SHERPA/HAS_ONNX is TRUE.

© RunanywhereAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/wally-release of RunanywhereAI/wally.

Open the folder on GitHubat commit 4687fde

Compare with similar skills

Wally Release 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.

Wally Release compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Wally Release this skillRunanywhereAI/wally1.6k—~1.3kAutomated safety check: PassMIT
Ccapwysaid/CameraCapture191—~1.4kAutomated safety check: PassMIT
Subspace Buildsdallison/subspace104—~990Automated safety check: PassApache-2.0
Mole CLI Release Flowtw93/Mole70k—~2.6kAutomated safety check: PassGPL-3.0
Apple Container Test RunnerRustPython/RustPython22k—~467Automated safety check: PassMIT
OrcaSlicer G-code Slicingearthtojake/text-to-cad19k—~989Automated safety check: PassMIT

Similar skills

  • Ccap

    wysaid/CameraCapture

    Install or use the ccap CLI for camera capture, webcam inspection, device listing, frame capture, and video metadata.

    191 GitHub stars~1.4k tokensUpdated 3 mo ago
    MobileAuto-check passed

  • Subspace Builds

    dallison/subspace

    Build and test Subspace across supported platforms and build systems.

    104 GitHub stars~990 tokensUpdated today
    Backend & APIsAuto-check passed

  • Mole CLI Release Flow

    tw93/Mole

    Runbook for assessing and executing a Mole CLI release: distribution channels, pre-flight checks, capital-V tags, build artifacts and the handoff to curated release notes.

    70k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed

  • Apple Container Test Runner

    RustPython/RustPython

    Runs RustPython tests inside a Linux container built with Apple's container CLI, so macOS users can compare Linux results with their local ones.

    22k GitHub stars~467 tokensUpdated today
    Testing & QAAuto-check passed

  • OrcaSlicer G-code Slicing

    earthtojake/text-to-cad

    Slices STL, 3MF or OBJ models into printer-ready G-code with OrcaSlicer, either headless from the command line or by opening the model in the app.

    19k GitHub stars~989 tokensUpdated today
    Media & CreativeAuto-check passed

  • JS Cpp Protocol

    notepadqq/notepadqq

    Reference for the communication protocol between the JavaScript editor (CodeMirror or Monaco) and the C++/Qt UI layer via QWebChannel.

    2.3k GitHub stars~3.2k tokensUpdated 4 days ago
    DevelopmentAuto-check passed

More from RunanywhereAI/wally

  • Wally Architecture

    RunanywhereAI/wally

    Where Wally logic belongs — command layering, proto as SOT, kit vs CLI ownership, Apple MLX host vs wally-cxx.

    1.6k GitHub stars~992 tokensUpdated today
    Auto-check passed

  • Wally Device E2E

    RunanywhereAI/wally

    Run wally's LLM e2e on Apple Neural Engine (NeuRT) and Snapdragon Hexagon NPU (QHexRT) devices.

    1.6k GitHub stars~845 tokensUpdated today
    Auto-check passed

  • Wally E2E

    RunanywhereAI/wally

    Verify a built wally binary against a pinned C++ desktop kit on macOS and Windows.

    1.6k GitHub stars~3.8k tokensUpdated today
    Auto-check passed

  • Wally Kit Pin

    RunanywhereAI/wally

    Bump cmake/sdk-pin.cmake to a new published SDK C++ desktop kit (version + SHA-256 + IDL lock).

    1.6k GitHub stars~1k tokensUpdated today
    Auto-check passed

Works with

Questions about Wally Release

What does Wally Release do?

Cut an Wally product release (independent of SDK version) — version bump, release:patch label, merge, auto-tag, bottles. Wally Release is an agent skill from RunanywhereAI/wally. Cut an Wally product release (independent of SDK version) — version bump, release:patch label, merge, auto-tag, bottles.

When should I use Wally Release?

Wally Release fits situations like: shipping wally after a published SDK kit; homebrew / notarization / private overlays must not leak into public bottles.

How do I install Wally Release in Claude Code?

Run `npx skills add RunanywhereAI/wally --skill wally-release -a claude-code`. Or copy the skill folder (.agents/skills/wally-release in RunanywhereAI/wally) into .claude/skills/wally-release in your project. Claude Code loads it when a task matches its description.

How do I install Wally Release in Codex?

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

Can I use Wally Release 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 RunanywhereAI/wally --skill wally-release -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/wally-release, .gemini/skills/wally-release, .github/skills/wally-release and .opencode/skills/wally-release in your project.

What does Wally Release need to run?

Going by SKILL.md and its folder, Wally Release needs the command-line tools its instructions call (gh) and credentials named GITHUB_TOKEN. Our summary lists: A credential in GITHUB_TOKEN.

Does Wally Release access the network?

SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Wally Release 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 Wally Release use?

Wally Release is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Wally Release use?

About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Wally Release?

Skills that share tags, products or a category with Wally Release: Ccap (wysaid/CameraCapture, 191 stars), Subspace Builds (dallison/subspace, 104 stars), Mole CLI Release Flow (tw93/Mole, 70k stars) and Apple Container Test Runner (RustPython/RustPython, 22k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Wally Release?

RunanywhereAI (a GitHub organization) maintains it in RunanywhereAI/wally, which has 1,562 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 10, 2026.

Source: RunanywhereAI/wally on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.