openclaw-cws-publisher
OpenClaw CWS Publisher is a public ClawHub Chrome Web Store publisher skill. Use it when the user says "chrome web store publisher", "extension release publisher", "CWS publisher", or wants to package and harden a Chrome extension with CWS package, listing, design, local E2E, latest Chrome, competitor, leak, GitHub, and ClawHub gates.
What this skill does
# OpenClaw CWS Publisher
Search intent: `chrome web store publisher`, `extension release publisher`, `cws publisher`, `chrome extension publish`
## Goal
Prepare a Chrome extension repo for release with less metadata drift:
- package the extension
- validate the exact ZIP intended for upload against source manifest and CWS listing copy
- scan tracked and untracked non-ignored files for obvious leak risks
- run local reviewer/E2E gates
- enforce design, UI, screenshot, and claim-alignment score gates
- check current Chrome Stable release data before declaring E2E coverage fresh
- run a lightweight competitor and positioning differentiation check
- detect repo-local reviewer gates
- generate GitHub metadata
- generate optional ClawHub metadata and explicit tags
- render reproducible publish commands
## Use This Skill When
- the user wants a Chrome extension repo prepared for GitHub release
- the user wants CWS ZIP/listing/privacy/design/E2E readiness checked before dashboard submission
- the user wants ClawHub tags and GitHub topics kept in sync
- the user wants a leakage check before public release
- the user already has a specific repo path to release
## Operating Order
1. Build the extension ZIP intended for upload.
- `python3 {baseDir}/scripts/build_extension_zip.py --extension-dir <repo>/extension --out <zip>`
2. Validate the exact ZIP, source manifest, and listing contract.
- `python3 {baseDir}/scripts/validate_cws_package.py --zip <zip> --source-manifest <repo>/extension/manifest.json --listing-json <repo>/docs/cws/listing.json`
- Default posture blocks stale ZIPs, Manifest V2, `tabs`, `debugger`, `<all_urls>`, persistent host permissions, declarative content scripts, remote script/eval patterns, missing permission justifications, privacy-practice drift, and no-host ZIPs whose listing still carries host-permission copy.
- If a product genuinely needs host permissions, use `--allow-host-permissions` only after the listing and reviewer instructions explain the shipped user-facing need.
3. Scan tracked and untracked non-ignored files for obvious publish leaks.
- `python3 {baseDir}/scripts/scan_publish_surface.py --root <repo> --json-out <json> --markdown-out <md>`
4. Run local reviewer/E2E gates.
- `python3 {baseDir}/scripts/run_local_e2e_gates.py --repo-root <repo> --json-out <json> --markdown-out <md>`
- The script discovers `check:cws`, `check:public`, `check:public:visual`, `test:e2e:reviewer`, `test:e2e`, and `scripts/reviewer_gate.py` when present.
5. Enforce the design/UI/UX evidence gate.
- `python3 {baseDir}/scripts/check_design_gate.py --design-report <repo>/docs/design-gate.json --screenshot-metadata <repo>/assets/listing/screenshot-1.png.source.json`
- Every changed public page, popup, CWS screenshot, promo tile, hero, and media asset must score at least `8/10` for product clarity, visual trust, evidence integrity, responsive polish, accessibility, and claim alignment.
6. Check current Chrome Stable release data.
- `python3 {baseDir}/scripts/check_chrome_release.py --tested-chrome-version <local chrome version> --json-out <json> --markdown-out <md>`
- Source: Chrome for Testing last-known-good Stable feed, cross-checked with ChromiumDash, Chrome Releases, and Chrome for Developers release notes when making decisions.
7. Run a competitor/differentiation check.
- `python3 {baseDir}/scripts/check_competitors.py --listing-json <repo>/docs/cws/listing.json --competitors-json <repo>/docs/cws/competitors.json --min-competitors 3 --markdown-out <md>`
- Record at least three comparable products or explicit substitutes; flag risky claims like `#1`, `best`, `official`, and close-copy positioning.
8. Generate launch metadata.
- `python3 {baseDir}/scripts/generate_launch_manifest.py --repo-root <repo> --owner <github-owner> --public-site-base <https://public-site.example/> --out <json>`
- If you already export `CWS_PUBLIC_SITE_BASE`, you can omit `--public-site-base` and the script will reuse that public reviewer-facing base.
9. Render publish commands.
- `python3 {baseDir}/scripts/render_publish_commands.py --manifest <json> --out <md>`
## Rules
- Operate on the repo path the user named, not on arbitrary sibling directories.
- Inspect the ZIP intended for upload, not only the source tree, before calling a Chrome Web Store package ready.
- Prefer `activeTab` plus `scripting` after an explicit user gesture over persistent host permissions.
- Do not publish when the leak scan has unresolved findings.
- Do not publish when the target repo has a reviewer gate and it fails.
- Do not publish when package/listing/privacy claims disagree with the ZIP manifest.
- Do not publish when the design/UI gate is missing or any score is below `8/10`.
- Do not publish when local E2E was only run on an older Chrome milestone without recording the current Stable release check.
- Do not publish listing copy that claims official affiliation, best-in-class status, background crawling, server sync, or broad permissions unless the shipped product and public evidence prove it.
- Keep GitHub topics and ClawHub tags explicit in the generated manifest.
- Use a dedicated public site base for support, privacy-policy, and reviewer-instructions links when the extension has one.
- If a Chrome Web Store draft is already pending review, do not recommend canceling or replacing it unless a verified acceptance blocker exists.
- Do not assume generated artifacts should be committed.
## Current Policy Anchors
- Chrome Web Store Program Policies: https://developer.chrome.com/docs/webstore/program-policies/policies
- Manifest V3 remote-code requirements: https://developer.chrome.com/docs/webstore/program-policies/mv3-requirements
- `activeTab` plus `scripting` model: https://developer.chrome.com/docs/extensions/develop/concepts/activeTab
- Permission warnings and host permission warnings: https://developer.chrome.com/docs/extensions/develop/concepts/declare-permissions
- Chrome release notes: https://developer.chrome.com/release-notes/
- Chrome release feed: https://chromiumdash.appspot.com/fetch_releases
## Bundled Scripts
- `scripts/build_extension_zip.py`
- `scripts/validate_cws_package.py`
- `scripts/scan_publish_surface.py`
- `scripts/run_local_e2e_gates.py`
- `scripts/check_design_gate.py`
- `scripts/check_chrome_release.py`
- `scripts/check_competitors.py`
- `scripts/generate_launch_manifest.py`
- `scripts/render_publish_commands.py`
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.