ClawRouter Release Checklist
BlockRunAI/ClawRouter
Walks the agent through every ClawRouter release step in order, from the version bump and changelog entry to build, tests, npm publish, git tag and GitHub release.
Manually review changed open-compute behavior for drift across maintained user, operator, API, SDK, configuration, deployment, capability, CLI, Dashboard, and release surfaces.
Install Product Surface Check
$ npx skills add elliothux/open-compute --skill product-surface-check -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install elliothux/open-compute product-surface-check --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/elliothux/open-compute.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/product-surface-check .claude/skills/product-surface-check && 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 "product-surface-check" agent skill from https://github.com/elliothux/open-compute/tree/main/.agents/skills/product-surface-check into .claude/skills/product-surface-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-surface-check", 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/elliothux/open-compute/tree/main/.agents/skills/product-surface-checkType 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 elliothux/open-compute --skill product-surface-check -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install elliothux/open-compute product-surface-check --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/elliothux/open-compute.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/product-surface-check .agents/skills/product-surface-check && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "product-surface-check" agent skill from https://github.com/elliothux/open-compute/tree/main/.agents/skills/product-surface-check into .agents/skills/product-surface-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-surface-check", 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 elliothux/open-compute --skill product-surface-check -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install elliothux/open-compute product-surface-check --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/elliothux/open-compute.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/product-surface-check .cursor/skills/product-surface-check && 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 "product-surface-check" agent skill from https://github.com/elliothux/open-compute/tree/main/.agents/skills/product-surface-check into .cursor/skills/product-surface-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-surface-check", 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/elliothux/open-compute.git --path .agents/skills/product-surface-check--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 elliothux/open-compute --skill product-surface-check -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install elliothux/open-compute product-surface-check --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/elliothux/open-compute.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/product-surface-check .gemini/skills/product-surface-check && 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 "product-surface-check" agent skill from https://github.com/elliothux/open-compute/tree/main/.agents/skills/product-surface-check into .gemini/skills/product-surface-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-surface-check", 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 elliothux/open-compute product-surface-checkInstalls 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 elliothux/open-compute --skill product-surface-check -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/elliothux/open-compute.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/product-surface-check .github/skills/product-surface-check && 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 "product-surface-check" agent skill from https://github.com/elliothux/open-compute/tree/main/.agents/skills/product-surface-check into .github/skills/product-surface-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-surface-check", 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 elliothux/open-compute --skill product-surface-check -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install elliothux/open-compute product-surface-check --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/elliothux/open-compute.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/product-surface-check .opencode/skills/product-surface-check && 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 "product-surface-check" agent skill from https://github.com/elliothux/open-compute/tree/main/.agents/skills/product-surface-check into .opencode/skills/product-surface-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-surface-check", 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
product-surface-check- GitHub stars
- 1.8k
- Token cost
- ~2.4k tokens
- SKILL.md length
- 1,128 words
- Files
- 2
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Manually review changed open-compute behavior for drift across maintained user, operator, API, SDK, configuration, deployment, capability, CLI, Dashboard, and release surfaces.
- Works in 4 steps: Inspect staged, unstaged, and untracked… → If the worktree is clean, compare HEAD… → Do not fetch merely to find a base. Do… → …
- Tasks that involve Deployment
- SKILL.md covers Resolve the review scope, Identify externally meaningful…, Check the maintained product… and Report
- Calls git
What it does
Product Surface Check is an agent skill from elliothux/open-compute. Manually review changed open-compute behavior for drift across maintained user, operator, API, SDK, configuration, deployment, capability, CLI, Dashboard, and release surfaces. Use only when explicitly invoked for this cross-surface check.
Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Development, covering Deployment. It works with Cloudflare Workers and Git. The repository describes itself as: Self-hosted Cloudflare Workers-compatible platform with Workers、KV、D1、R2、DO、Queues、Workflows、Cron、Cache、Images、Vectorize、AI Search、Artifacts、Static Assets、Service… The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Deployment
Example prompts
- “/product-surface-check”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Inspect staged, unstaged, and untracked files. If any exist, review only those uncommitted changes against HEAD.
- If the worktree is clean, compare HEAD with the newest reachable annotated open-compute release tag matching exact SemVer vX.Y.Z.
- Do not fetch merely to find a base. Do not use git describe without filtering: the repository also contains workerd-style v1.YYYYMMDD.N…
- If no reachable annotated SemVer release exists, report the missing base and review the available change scope without inventing one.
What it can do on your machine
Read from SKILL.md and the folder at commit 6ebd701. 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:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, 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 no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Product Surface Check loads about 2.4k tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 1,128 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 elliothux/open-compute at commit 6ebd701, republished under its Apache-2.0 licence (© elliothux). 1,128 words, ~2,436 tokens.
Download SKILL.mdSave it as
.claude/skills/product-surface-check/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- product-surface-check
- description
- Manually review changed open-compute behavior for drift across maintained user, operator, API, SDK, configuration, deployment, capability, CLI, Dashboard, and release surfaces. Use only when explicitly invoked for this cross-surface check.
Product Surface Check
Perform a read-only consistency review. Report required updates; do not edit files unless the user separately asks for fixes.
Resolve the review scope
Use a user-specified revision or range when provided. Otherwise:
- Inspect staged, unstaged, and untracked files. If any exist, review only those uncommitted changes against
HEAD. - If the worktree is clean, compare
HEADwith the newest reachable annotated open-compute release tag matching exact SemVervX.Y.Z. - Do not fetch merely to find a base. Do not use
git describewithout filtering: the repository also contains workerd-stylev1.YYYYMMDD.Ntags that are not open-compute releases. - If no reachable annotated SemVer release exists, report the missing base and review the available change scope without inventing one.
Inventory untracked files with git ls-files --others --exclude-standard; ordinary git diff does not include them. For a release comparison, use the exact tag-to-HEAD range rather than a merge-base range because the tag must be an ancestor of HEAD.
Identify externally meaningful changes
Trace changed behavior before judging presentation files. Look for changes to product topology, ownership, supported capabilities, configuration, defaults, commands, flags, output, installation, lifecycle, security boundaries, limits, recovery, and operator or developer workflows. Ignore internal refactors that preserve all of those observable contracts.
Inspect changed producers and their consumers. A presentation file appearing in the diff is not proof that it is current; compare its content with the implemented behavior.
Check the maintained product surfaces
README and product architecture diagram
Check README.md, README.zh.md, and share/open-compute-architecture.svg / .png when the change affects product positioning, setup commands, supported products, headline counts, deployment topology, component ownership, trust boundaries, persistent authorities, or important data flows.
Require a diagram update only for architectural information a diagram should communicate. Do not request diagram churn for local implementation details. Treat the SVG as inspectable source and the PNG as the README-rendered artifact; if one needs changing, verify that both remain synchronized.
Product website and docs site
Check the marketing copy in apps/website/src/i18n/ and the maintained documentation in both:
apps/website/src/content/docs/docs/apps/website/src/content/docs/zh/docs/
Inspect root docs/ only when the changed contract is represented there. Require English and Chinese documentation to describe the same behavior. Flag stale commands, configuration, defaults, supported-surface claims, operational procedures, links, and architecture explanations.
Also enforce the documentation lifecycle defined by docs/references/README.md whenever root documentation changes or the reviewed implementation completes an active plan:
docs/*.mdanddocs/workerd/*.mdcontain only work that still requires implementation;- completed implementation summaries live in
docs/implemented/; - completed implementations with only external, cross-platform, long-running, or release qualification remaining keep the implementation summary in
docs/implemented/and the remaining work indocs/acceptance/; - genuinely externally blocked work lives in
docs/blocked/; - maintained current contracts and runbooks live in
docs/references/.
Check that document moves update docs/README.md, the destination index, generators, and repository links without leaving redirects, stubs, duplicate copies, or completed plans in the active root. Flag broken relative links, stale worktree/branch language, obsolete TODOs, unnumbered lifecycle documents, and PASS/verified claims that are not backed by a recorded successful check. Do not ask to archive a maintained current contract merely because its original implementation is complete.
Default configuration and deployment artifacts
Check share/default-config.toml, scripts/install.sh, and the systemd, launchd, and container examples under examples/ when configuration shape, defaults, paths, permissions, installation, service scope, process ownership, startup, shutdown, or upgrade behavior changed. These are shipped operator inputs, not illustrative snippets that may drift independently.
Check developer examples and Wrangler configuration only when their supported workflow or generated types changed. Do not request unrelated example churn.
Public API, SDK, and generated developer contracts
Check openapi/**, packages/sdk/**, and affected generated types or developer examples when HTTP routes, request or response fields, errors, pagination, authentication, supported operations, SDK methods, or public identifiers changed. Verify the authoritative OpenAPI/capability inputs and generated SDK surface agree; do not treat documentation prose or a passing route test as a substitute for the machine-readable contract.
Keep this separate from ocd capabilities: the API/SDK contract describes callable management surfaces, while capabilities describe advertised support and runtime/product qualification.
Show full SKILL.md (470 more words)Show less
Dashboard
Check apps/dashboard/** when authentication/session behavior, instance selection, terminology, navigation, resource operations, capability presentation, API fields, errors, or destructive confirmations changed. The Dashboard must use the same current public contract and names as the API and docs; Cloudflare wire names may remain at the SDK boundary without becoming stale product terminology in the UI.
ocd capabilities
Check whether the live capability contract needs changing when support status, public members, deviations, limits, pins, compatibility dates or flags, management support, Wrangler support, or observability support changed. Trace the authority through:
share/cloudflare-capabilities.json;crates/service/src/capabilities.rs;- the capability/deviation catalog and conformance inputs under
test/conformance/; docs/references/cloudflare-compatibility.mdanddocs/references/p1-deviations.md.
Distinguish tenant runtime compatibility from management API support. Do not request capability changes for an internal refactor or for behavior outside the declared support scope.
ocd CLI help
Check Clap declarations in crates/service/src/cli/model.rs and related subcommand models against the actual dispatch and validation paths. Flag stale or missing descriptions for commands, flags, positional arguments, defaults, conflicts, scope selection, output modes, side effects, destructive behavior, and hidden/internal commands accidentally exposed.
Compare CLI help with README and website command examples. Source review is sufficient by default; run help from an already built current binary only when it resolves uncertainty. Do not trigger a full build or Gate for this review alone.
Embedded operator docs and agent entry points
Check docs/references/runbooks/** when recovery, backup, installation, failure handling, support collection, paths, permissions, or operator commands changed. These files are embedded in the executable and exposed through ocd docs, so they are a shipped product surface.
Check apps/website/public/llms.txt when setup, command selection, supported workflows, or the canonical documentation entry points changed. Keep it small and link to detailed docs rather than duplicating them.
Release-only surfaces
Apply this section only when the user asks for release preparation, the reviewed changes include version/release metadata, or a release note for the next version already exists. Check:
docs/releases/and its index;- workspace and SDK package versions;
- formal runtime/tool pins and their documented identities;
- installer/download asset names and upgrade instructions.
Do not require release-note or version churn for an ordinary implementation review. When applicable, require release notes to describe user-visible changes, breaking configuration/data implications, operator actions, and actual verification without overstating unrun qualification.
Report
List actionable mismatches first, ordered by user impact. Each finding must include:
- the implemented change and evidence path;
- the stale or missing surface and evidence path;
- the smallest accurate update required.
Finish with exactly one row for each applicable surface using update required, no update needed, not applicable, or unverified:
| Surface | Verdict | Evidence |
|---|---|---|
| README + architecture diagram | ||
| Product website + docs site | ||
| Default config + deployment artifacts | ||
| Public API + SDK contracts | ||
| Dashboard | ||
ocd capabilities | ||
ocd CLI help | ||
Embedded runbooks + llms.txt | ||
| Release-only surfaces |
If no mismatch exists, say so directly. Do not turn a clean scoped review into a claim that all repository documentation or product behavior is correct.
© elliothux, 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 1 other file in .agents/skills/product-surface-check of elliothux/open-compute.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit 6ebd701
Compare with similar skills
Product Surface Check 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 |
|---|---|---|---|---|---|---|
| Product Surface Check this skillelliothux/open-compute | 1.8k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| ClawRouter Release ChecklistBlockRunAI/ClawRouter | 6.6k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Release Lithoxylmahmoud/lithoxyl | 146 | — | ~1.3k | Automated safety check: Pass | BSD-3-Clause | |
| AnyDrag Release RoutineXueshiQiao/AnyDrag | 227 | — | ~2.6k | Automated safety check: Pass | GPL-3.0 | |
| Deployjustrach/merjs | 357 | — | ~171 | Automated safety check: Pass | MIT | |
| Vercel Deploy Previewjeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~1.6k | Automated safety check: Pass | MIT |
Similar skills
Release Lithoxyl
mahmoud/lithoxyl
Walks through releasing the lithoxyl Python package to PyPI: CalVer version bump, tagging, pushing and checking the published release.
AnyDrag Release Routine
XueshiQiao/AnyDrag
Runs the full AnyDrag release process end to end, from cumulative bilingual release notes through version bumping to watching CI and the Homebrew cask update.
Deploy
justrach/merjs
Full production build — codegen, compile, prerender, and prepare for deployment.
Vercel Deploy Preview
jeremylongshore/tons-of-skills-marketplace
Create and manage Vercel preview deployments for branches and pull requests.
Release
MadAppGang/claude-code
Plugin release process for MAG Claude Plugins marketplace. An agent skill from MadAppGang/claude-code.
More from elliothux/open-compute
Kumo Design
elliothux/open-compute
Cloudflare product design guidance. An agent skill from elliothux/open-compute.
Grok Executor
elliothux/open-compute
Delegate a concrete, locally authorized implementation or read-only web research task from Codex to the official Grok Build CLI.
Cf Compatibility Check
elliothux/open-compute
Review branch and working-tree implementation changes for conformance with open-compute's Cloudflare Workers runtime target under explicit single-machine self-host exclusions.
Anti Cheating
elliothux/open-compute
Audit the current Lynx branch and working tree for test-, fixture-, demo-, page-, domain-, or scenario-tuned production logic.
Simplify
elliothux/open-compute
Simplify recently modified Lynx business code while preserving behavior.
Update Workerd Upstream
elliothux/open-compute
Update open-compute's workerd fork onto current Cloudflare upstream, minimize fork-owned code, regroup fork commits by capability, and coordinate the submodule, pin, tests, and docs.
Related
Works with
Categories
Questions about Product Surface Check
What does Product Surface Check do?
Manually review changed open-compute behavior for drift across maintained user, operator, API, SDK, configuration, deployment, capability, CLI, Dashboard, and release surfaces. Product Surface Check is an agent skill from elliothux/open-compute. Manually review changed open-compute behavior for drift across maintained user, operator, API, SDK, configuration, deployment, capability, CLI, Dashboard, and release surfaces.
When should I use Product Surface Check?
Product Surface Check fits situations like: tasks that involve Deployment.
How do I install Product Surface Check in Claude Code?
Run `npx skills add elliothux/open-compute --skill product-surface-check -a claude-code`. Or copy the skill folder (.agents/skills/product-surface-check in elliothux/open-compute) into .claude/skills/product-surface-check in your project. Claude Code loads it when a task matches its description.
How do I install Product Surface Check in Codex?
Run `npx skills add elliothux/open-compute --skill product-surface-check -a codex`. Or copy the skill folder (.agents/skills/product-surface-check in elliothux/open-compute) into .agents/skills/product-surface-check in your project. Codex loads it when a task matches its description.
Can I use Product Surface Check 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 elliothux/open-compute --skill product-surface-check -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/product-surface-check, .gemini/skills/product-surface-check, .github/skills/product-surface-check and .opencode/skills/product-surface-check in your project.
What does Product Surface Check need to run?
Going by SKILL.md and its folder, Product Surface Check needs the command-line tools its instructions call (git).
Does Product Surface Check access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Product Surface Check 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 Product Surface Check use?
Product Surface Check 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 Product Surface Check use?
About 2.4k tokens (SKILL.md is roughly 9.7k 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 Product Surface Check?
Skills that share tags, products or a category with Product Surface Check: ClawRouter Release Checklist (BlockRunAI/ClawRouter, 6.6k stars), Release Lithoxyl (mahmoud/lithoxyl, 146 stars), AnyDrag Release Routine (XueshiQiao/AnyDrag, 227 stars) and Deploy (justrach/merjs, 357 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Product Surface Check?
elliothux (a GitHub user) maintains it in elliothux/open-compute, which has 1,824 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 8, 2026.
Source: elliothux/open-compute on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.