By saif-shines
Skills for building SDKs, CLI tools, MCP servers, agent plugins, and skill creation — plus the devex-kit router.
Design, build, restructure, and ship Claude Code plugins using the modern skills-first + agents + externalized references model. Use this skill when creating a new plugin, writing or refactoring skills, building spawnable agents, externalizing reference material into references/ or docs/, de-emphasizing commands, or asking about "plugin development", "create skill", "write agent", "restructure plugin", "SKILL.md best practices", "references/ in plugins", "agent orchestration", "pr-review-toolkit", "docs-engineering plugin", or the 5 restructure principles. Also activates for questions about lean SKILL.md, progressive disclosure, scalekit-code-doctor pattern, plugin.json, tile.json, or packaging for devex-kit and marketplaces.
Create new skills and iteratively improve existing ones using devex-kit conventions. Use when users want to create a skill from scratch, turn a workflow into a SKILL.md, write or edit a skill, improve skill triggering/description, package a skill for distribution, or follow the lean + references + progressive disclosure model. Also activates for questions about skill anatomy, frontmatter quality, imperative writing style, test cases for skills, or when the user says "create a skill", "write SKILL.md", "improve this skill", "package my skill".
Build CLI tools and API utilities that developers on your platform actually use. Covers CLI design (command hierarchy, flags, completions, cross-platform UX) and API collection generation (Postman/OpenAPI from Express, Next.js, Fastify, Hono routes). Use this skill when building a developer-facing CLI tool, adding subcommands or flags, implementing shell completions, designing interactive prompts, generating Postman collections from code, creating API testing artifacts, or building any developer utility. Also activates for questions about argument parsing (commander, click, typer, cobra), progress indicators, terminal UX, or Postman collection format.
Build MCP servers that AI agents actually want to use. Covers the full lifecycle — tool design (naming, schemas, descriptions), resource design (URIs, templates, subscriptions), project structure, transport selection (stdio vs Streamable HTTP), security, error handling, and testing. Use this skill when building a new MCP server, adding tools or resources to an existing one, reviewing an MCP server for quality, choosing between stdio and HTTP transport, designing tool schemas for LLM consumption, or hardening an MCP server for production. Also activates for questions about tool naming conventions, Pydantic Field descriptions, Zod validation for MCP, resource URI schemes, or MCP server security patterns.
Design, build, document, and ship SDKs that developers love. Covers the full SDK lifecycle — from API surface design and type safety through implementation, bundling, documentation, versioning, and publishing. Use this skill whenever someone is creating a new SDK, extracting shared code into a client library, improving SDK developer experience, planning a breaking change or migration guide, or reviewing an SDK for quality. Also activates for questions about error message design, client library patterns, type-safe API design, SDK packaging (ESM/CJS), or npm publishing.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A collection of agent skills for developer experience work — distributed as both a Claude Code plugin marketplace and skills.sh-compatible skill repo.
The canonical starting skill (inspired by superpowers' using-superpowers).
Always invoke first on any devex-kit-eligible task:
/using-devex-kit <describe the work>
It classifies intent, returns the exact target skill + copy/paste invocation, handles sequencing for multi-skill flows (story → DX → authoring is common), and gives local load instructions. Treat it as the router that makes every other skill discoverable and correctly applied.
Install it individually or as part of the full kit — then start every relevant session by typing /using-devex-kit.
Generic devrel skills for documentation workflows — useful to any devrel professional regardless of tech stack.
Routes documentation contributions to the right content type, placement, template, and workflow — before the contributor writes a single line.
Five branches:
_setup-*, _usage-*, _section-* templates and pnpm run sync-agent-connectorsScalekit-specific paths are in references/scalekit-*.json. External consumers drop their own configs at <docs-repo>/.devex-kit/ — no edits to SKILL.md required.
Two-mode writing guide.
Scalekit-specific prompt block in references/scalekit-style-prompt-block.md. Template for other sites in references/_template-style-prompt-block.md.
Diagnostic skill for documentation quality — skimmability, writing clarity, and reader helpfulness.
Assistive skill for sidebar navigation: group labels, item labels, and order should follow a developer journey (setup → core loop → scale → ship). Includes a reference model derived from Scalekit Full stack auth in sidebar.config.ts and label rules from the docs standards (concise, sentence case, outcome-focused).
Skills for building SDKs, CLI tools, and developer utilities — the artifacts devrel professionals ship to their developer communities.
Design, build, document, and ship SDKs that developers love. Covers the full SDK lifecycle:
Consolidates guidance from SDK design philosophy, TypeScript SDK development, and SDK documentation generation into one lifecycle skill. Includes language idiom guides for Python, JavaScript, Go, and Java.
Build CLI tools and API utilities that developers on your platform actually use. Two domains:
Includes framework-specific scanner implementations and UX pattern references.
Build MCP servers that AI agents actually want to use. Covers the full lifecycle:
npx claudepluginhub saif-shines/devex-kit --plugin toolingDocumentation contribution routing, writing style enforcement, cookbook quality audits, and sidebar navigation design.
Developer go-to-market skills — authentic storytelling, TAB playbooks, DX for first success, and content taxonomy.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,561 supported skills.