npm agent skills, page 16

Phase 2 — propagate an already-merged scaffold-stark-2 update out to its sibling forks and the create-stark npm template.

Scaffold-Stark/scaffold-stark-2

A skill your agent uses when bumping the pinned OpenClaw core version (openclaw npm package), when preparing a Pinchy release, or when the user asks to "update OpenClaw" / "upgrade OpenClaw" / check…

heypinchy/pinchy

A skill your agent uses when implementing save/load in a Pixi'VN game — Game.exportGameState()/restoreGameState()/jsonToGameState(), what the exported GameState contains, and how to persist it (save…

DRincs-Productions/pixi-vn

Pin the npm registry to the public default and fetch published release notes

cisco-ai-defense/skill-scanner

Bridge Server のリリース（バージョンbump + CHANGELOG + タグ → GH Actions で npm publish）

K9i-0/ccpocket

Structures complex feature work into five planning-first phases (specification, pseudocode, architecture, refinement and completion) driven through claude-flow commands.

ruvnet/agentic-flow

Write and run ryOS tests with Bun's native test runner (bun:test).

ryokun6/ryos

A skill your agent uses when building Farm locally from source, native bindings or Rust plugin artifacts are missing, or an example/E2E needs local core and plugin artifacts.

farm-fe/farm

Hands coding work such as codebase questions, bug fixes, refactors and PR reviews to the Qwen Code CLI, driven through acpx instead of scraped terminal sessions.

QwenLM/qwen-code

Drives a CLI through a TypeScript scenario and saves terminal screenshots at each step, so pull requests that change command output can be checked visually.

QwenLM/qwen-code

A skill your agent uses whenever the user asks to implement, execute, deliver, verify, or close a task from an existing Cabloy suite specification, including requests such as “implement WBS-…”…

cabloy/cabloy

Create a Mastra project using create-mastra and smoke test the studio in Chrome using Chrome MCP server

mastra-ai/mastra

Guides building standards-based Preact apps with native-first choices, HTM syntax, import maps and vendored ESM, from single-file demos to larger builds.

oaustegard/claude-skills

Check every dependency in a package.json against live CVE databases and security advisories in real time — specifically targeting vulnerabilities disclosed in the last 48 hours, the window that…

tinyfish-io/tinyfish-cookbook

Supply-chain security controls for the @cipherstash/stack monorepo.

cipherstash/stack

Author an MCP package for OtoDock: the manifest.json fields and their rules, the package layout, what the installer refuses or drops, credentials and instances, skills bundled with an MCP, and the…

OtoDock/oto-dock

Migrate an Nx package to build to a local dist/ directory with nodenext module resolution, exports map, and @nx/nx-source condition.

nrwl/nx

Use this when adding Nix-based local runs for an existing Playwright e2e suite.

srid/emanote

Maintain the bundled TypeScript package docs that ship inside Phoenix npm packages.

Arize-ai/phoenix

Canonical build → release → tag → publish procedure for the @delorenj/mcp-server-trello repo.

delorenj/mcp-server-trello

Audit all outdated dependencies with detailed research on changelogs, breaking changes, bug fixes, and deprecations.

viclafouch/meme-studio

A skill your agent uses when creating or updating a Makefile for a project, especially when standard targets (build, test, lint, format, etc.) are missing or when modifying targets that may already…

Ovid/paad

Internals of how @bradygaster/squad-cli stamps its version, how squad upgrade works (what it preserves vs overwrites), and how to probe the npm registry for the latest version from a coordinator…

kubefleet-dev/kubefleet

The Inkline release process — changesets flow, the CI gate, the not-yet-enabled publish step, post-release verification, and rollback.

inkline/inkline

Patterns for running multi-agent swarms on research, development and testing work, with four topologies and a four-phase research swarm built on claude-flow MCP tools.

ruvnet/agentic-flow

A skill your agent uses for DSH plugin compatibility, migration, upgrade, regression, or post-upgrade diagnosis, including read-only review of already-migrated plugin source and version-boundary…

NanmiCoder/dsh-auto-mode

Babashka scripting conventions for the Epupp project. An agent skill from PEZ/epupp.

PEZ/epupp

The test-driven development workflow for ZettelFlow — write a failing test first, run jest, use the Obsidian mock and the bare-specifier alias mappings, and know which code is unit-testable.

RafaelGB/Obsidian-ZettelFlow

发布 Blockless VS Code 扩展到 Visual Studio Marketplace（含发布前测试）/ ship the Blockless extension to the VS Code Marketplace.

FreakStudioCN/mpy-hardware-extension

Text-to-speech conversion using node-edge-tts npm package for generating audio from text.

sundial-org/awesome-openclaw-skills

Comprehensive verification system for Claude Code sessions. An agent skill from cloudnative-co/claude-code-starter-kit.

cloudnative-co/claude-code-starter-kit

Run or assist a release in any MUI repo, at any stage - release PR, npm publish, docs deploy, GitHub release.

mui/mui-public

Check whether newer stable versions of Node.js (24.x line), Nx, or Vite are available and, if so, generate a detailed upgrade plan markdown file at the repo root.

PackmindHub/packmind

Protocol orchestrator CLI — drives SPIR, ASPIR, AIR, TICK, and BUGFIX protocols via a state machine.

cluesmith/codev

Sequences safe dependency upgrades: read the changelog, verify the version exists upstream, pin it, and keep major bumps in separate commits behind a full gate run.

dralgorhythm/claude-agentic-framework

The hard rules for editing @kortix/sdk (packages/sdk) — a PUBLISHED npm package with constraints no other package in this repo has: TDD is mandatory (failing test first, gates run and pasted every…

kortix-ai/suna

Audit newer npm package releases against kitcn. An agent skill from udecode/kitcn.

udecode/kitcn

This skill should be used when the user asks to start, restart, keep alive, or inspect the local pikiclaw development service, including npm run dev, local debug bot startup, dashboard verification…

xiaotonng/pikiloom

Builds and verifies truST's VS Code extension - commands, webviews, snippets, debug flows, Control Studio, HMI Builder, Devices & Connections and the test harness.

johannesPettersson80/trust-platform

Clone or update https://github.com/sxhzju/ruler-progress-animator and render a ruler progress video with default parameters.

vibe-motion/skills

Embed alibaba/page-agent into your own web application — a pure-JavaScript in-page GUI agent that ships as a single <script tag or npm package and lets end-users of your site drive the UI with…

Tommy-yw/RunbookHermes

Analyze dependencies for known security vulnerabilities and outdated versions.

jeremylongshore/tons-of-skills-marketplace

Independently verifies whether a completed task meets its defined goal conditions.

k1ein-chen/Harness-Starter

Building, compiling, and resolving dependency issues across languages

vstorm-co/pydantic-deepagents

Creating and developing startup hooks for Claude Code on the web.

asgeirtj/system_prompts_leaks

Development guide for setting up, debugging, and testing SWPM locally.

deinsoftware/swpm

A skill your agent uses when developing or modifying the @handsontable/vue3 wrapper package - Vue 3 SFC components, deep watchers, and provide/inject patterns for settings propagation

handsontable/handsontable

Validate or update example-level E2E coverage. An agent skill from farm-fe/farm.

farm-fe/farm