AgentKit Dev Skills
13 MIT-licensed SKILL.md skills for everyday developer work: review-my-diff, repro-first-debugging, pr-description, safe-refactor, dependency-upgrade (shows the target version and…
Plugin-Paket · von agentkitco
Überblick
AgentKit Dev Skills ist ein Plugin-Paket für KI-Coding-Tools von agentkitco. Marktplätze, die wir lesen und die es listen: 1 (Community GitHub marketplaces). Wir haben es erstmals am 2026-10-25 gesehen und seither keine Änderung erfasst. Stand unseres Marktplatz-Durchlaufs vom 2026-10-29.
13 MIT-licensed SKILL.md skills for everyday developer work: review-my-diff, repro-first-debugging, pr-description, safe-refactor, dependency-upgrade (shows the target version and files and waits for a yes before changing anything), explain-codebase, security-quick-review, prove-it-ran (make the agent show real test output before saying done), session-handoff, brag-doc-from-git, write-agents-md, agents-md-audit (with a small read-only Python audit script) and write-subagent. Skills only: no hooks, no MCP servers, no settings, no network calls.
Was es abfragt
- Wird als Plugin-Paket installiert
Keiner der Marktplätze, die wir lesen, veröffentlicht seine Tools oder die abgefragten Einstellungen.
Was es deklariert, abfragt und ausführt, vollständig
Installieren Sie nur Plugins von Entwicklern, denen Sie vertrauen. Wir zeigen, was die Marktplätze veröffentlichen, und testen keine Plugins.
Funktioniert mit
- Claude Code
Nach den Marktplätzen, die ihn listen, und dem angegebenen MCP-Transport, wie jeder Client sie dokumentiert. Wir testen keine Plugins.
Verbinden
Befehle und Konfigurationen nur aus den Angaben der Marktplätze. Wir führen sie nicht für Sie aus und testen keine Plugins.
Als Claude-Code-Plugin
Erstellt aus den Angaben von Community GitHub marketplaces.
/plugin marketplace add davepoon/buildwithclaude
/plugin install agentkit-dev-skills@buildwithclaudeWo es veröffentlicht ist
| Marktplatz | Status | Version | Zahlen | Verifiziert | Erstmals gesehen |
|---|---|---|---|---|---|
| Community-Marktplatz davepoon/buildwithclaude (Quelle auf GitHub öffnen) | Gelistet | 1.2.2 | Forks (GitHub): 0 Sterne (GitHub): 0 |
Nicht markiert |
Jede Zahl stammt vom jeweiligen Marktplatz und wird nie über Marktplätze hinweg addiert. Ein Marktplatz ohne veröffentlichte Zahl zeigt keine: keine Zahl ist nicht null.
In einem Community-Marktplatz gelistet
| Marktplatz | Repository | Sterne (GitHub) |
|---|---|---|
| buildwithclaude | davepoon/buildwithclaude | 3 691 |
Was das Paket enthält
So veröffentlicht auf Community GitHub marketplaces.
Skills: 13
agents-md-auditbrag-doc-from-gitdependency-upgradeexplain-codebasepr-descriptionprove-it-ranrepro-first-debuggingreview-my-diffsafe-refactorsecurity-quick-reviewsession-handoffwrite-agents-md
Weitere anzeigen: 1
write-subagent
Was sich geändert hat
- Wird seitdem als Produkt geführt
- Community GitHub marketplaces: erschienen
Ähnliche Plugins
Produkte, deren eigene Namen, Beschreibungen, Werkzeuge und Skills diesem der Bedeutung nach am nächsten sind, auf allen Marktplätzen, die wir lesen. Die Nähe ist nur innerhalb dieser Liste geordnet.
-
Analyze any repository and generate AI-ready configuration — AGENTS.md, copilot-instructions.md, CI workflows, issue templates, and more. Mines your PR review patterns and creates…
-
Bring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
-
Session-level orchestration for Claude Code - structures development work into 5 typed waves (Discovery → Core → Polish → Quality → Finalization) with parallel subagent execution…
-
Coding workflow skills: intelligent commits, push & PR, branch cleanup, CLAUDE.md maintenance, README generation, changelog creation, README updating, and GitHub Actions setup
-
Skills for AI coding agents: code review, test writing, design docs, debugging, security and dependency audits, git history surgery, refactoring, copywriting, and cleaning up…
-
Contract-driven agentic coding workflow. spectre guides you through Scope, Plan, Execute, Clean, Test, Rebase, and Learn flows. Start with /spectre:scope.
-
Send your implementation plan to OpenAI Codex CLI for iterative review. Claude and Codex go back-and-forth until Codex approves the plan.
Ähnliche Plugins nach Marktplatz
Dieselbe Frage an jeden Marktplatz einzeln: Gibt es dort ein Gegenstück zu diesem Plugin?
Gelistet auf Claude Code: claude-plugins-community (5)
-
Session-level orchestration for Claude Code - structures development work into 5 typed waves (Discovery → Core → Polish → Quality → Finalization) with parallel subagent execution…
-
Send your implementation plan to OpenAI Codex CLI for iterative review. Claude and Codex go back-and-forth until Codex approves the plan.
-
A Claude Code skill that works on GitHub issues like a senior developer — structured analysis, TDD implementation, and clean PR delivery. Follows the proper developer process and…
-
AI-powered code review in Claude Code, powered by Octopus. Review PRs with natural language or slash commands, automatically fix review comments from the Octopus bot, and get…
-
Structured, artifact-driven development pipeline for Claude Code — plan, implement, review, and ship features with three ceremony tiers. 25 pipeline skills, 14 specialist agents.
Gelistet auf Claude Code: claude-plugins-official (5)
-
Bring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
-
Analyze codebases and recommend tailored Claude Code automations such as hooks, skills, MCP servers, and subagents.
-
AI code review agent for GitHub and GitLab. View and resolve Greptile's PR review comments, run reviews on your working branch, and search your organization's knowledge base and…
-
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
-
Your code review partner. CodeRabbit provides external validation using a specialized AI architecture and 40+ integrated static analyzers—offering a different perspective that…
Gelistet auf Claude: knowledge-work-plugins (5)
-
Bring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
-
Streamline engineering workflows — standups, code review, architecture decisions, incident response, and technical documentation. Works with your existing tools or standalone.
-
Official Buildkite skills for Claude Code, Cursor, and other AI coding agents — pipelines, migration, preflight, agent runtime, CLI, and API
-
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…
-
MCP server for terminal commands, file operations, and process management
Gelistet auf Codex: openai-curated (openai/plugins) (5)
-
AI-powered code review in Codex, powered by CodeRabbit.
-
Inspect repositories, triage pull requests and issues, debug CI, and publish changes through a hybrid GitHub connector and CLI workflow.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Qodo setup, code intelligence, and review workflows.
-
An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.
Gelistet auf Community GitHub marketplaces (4)
-
Analyze any repository and generate AI-ready configuration — AGENTS.md, copilot-instructions.md, CI workflows, issue templates, and more. Mines your PR review patterns and creates…
-
Bring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
-
Session-level orchestration for Claude Code - structures development work into 5 typed waves (Discovery → Core → Polish → Quality → Finalization) with parallel subagent execution…
-
Coding workflow skills: intelligent commits, push & PR, branch cleanup, CLAUDE.md maintenance, README generation, changelog creation, README updating, and GitHub Actions setup
Gelistet auf Copilot CLI: github/awesome-copilot (5)
-
Analyze any repository and generate AI-ready configuration — AGENTS.md, copilot-instructions.md, CI workflows, issue templates, and more. Mines your PR review patterns and creates…
-
Meta prompts that help you discover and generate curated GitHub Copilot agents, instructions, prompts, and skills.
-
Generic cross-repo command center canvas for GitHub Copilot with onboarding, focus planning, repo health, work signals, and session cleanup.
-
Visualize and guide the GitHub Copilot Modernize CLI Assess, Plan, and Execute workflow for .NET, Java, and C++ application repositories.
-
Review GitHub pull requests in a read-only canvas with AI-grouped changes, expandable diffs, and questions scoped to groups, files, or hunks.
Gelistet auf Copilot CLI: github/copilot-plugins (5)
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
Advanced Security plugin for GitHub Copilot.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
Navigate and interact with your C++ code using the Microsoft C++ Language Server.
-
code-apps-preview
Build and deploy Power Apps code apps using React, Vite, and Power Platform connectors.
Gelistet auf Cursor: cursor/plugins (5)
-
Skills for building on the Cursor Origin API. Fetch the live spec first, then follow the Origin rules for credentials, scopes, webhooks, paging, and errors. Includes a skill that…
-
Manage repos, issues, pull requests, and Actions.
-
if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.
-
Internal team workflows for CI, code review, shipping, local automation, and verification.
-
Render PR diffs as review canvases grouped by importance.
Gelistet auf Docker MCP Catalog (5)
-
Stop stitching context for Copilot and Cursor. With Sequa MCP, your AI tools know your entire codebase and docs out of the box.
-
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
-
Tools for interacting with Git repositories.
-
Tools for interacting with the GitHub API, enabling file operations, repository management, search functionality, and more.
-
A Model Context Protocol (MCP) for analyzing and querying GitHub repositories using the GitHub Chat API.
Gelistet auf Official MCP Registry (5)
-
dev-changes ai.openhelm/dev-changes
Turn described changes into reviewed pull requests: propose, triage, review, dependency audits.
-
patchwork — Codebase Conventions for AI Agents
Scan any codebase, generate CONVENTIONS.md, expose conventions as MCP tools for AI agents.
-
consult io.github.neelsatyavolu/consult
Get a second opinion on your code from every coding agent you have. No API keys.
-
An MCP server that stores Copilot customizations from the Awesome Copilot repository
-
PAPI: Persistent Adaptive Project Intelligence
Adaptive plan/build/review cycles for AI coding assistants, persisted across sessions.
Gelistet auf PyPI (MCP servers) (5)
-
repo-graph io.github.James-Chahwan/repo-graph
Structural graph map of any codebase so LLMs navigate by structure, not guesswork.
-
Let one coding-agent CLI consult another: Codex, Claude Code, OpenCode, Copilot or Antigravity.
-
Zero-config MCP server for searchable documentation. SQLite or PostgreSQL.
-
Retrieves code by symbol via tree-sitter, so an agent reads the function it needs, not the file.
-
mcp-gitlab io.github.vish288/mcp-gitlab
GitLab MCP server (MCP 2026-07-28): projects, MRs, pipelines, CI/CD, issues; writes or read-only
Gelistet auf npm registry (MCP servers) (5)
-
codescene-mcp-server com.codescene/codescene-mcp-server
An MCP server that provides CodeScene Code Health analysis tools.
-
Octocode MCP - AI Context Platform
AI code research platform. Search, analyze, and extract insights from any GitHub repository.
-
speclock io.github.sgroy10/speclock
AI Constraint Engine — enforces CLAUDE.md and .cursorrules as laws. 51 MCP tools.
-
The context platform for AI agents: code search, team decisions, and grounded project context.
-
review-assist-mcp io.github.uditk2/review-assist-mcp
Turns an AI coding agent session into a reviewable Intent Document, validated against the diff.
Nach Bedeutung gefunden, nicht über gemeinsamen Code oder ein gemeinsames Repository: Ähnliche Plugins bleiben getrennte Produkte, und dies ist weder eine Bewertung noch eine Empfehlung.
Möchten Sie dieses Zeichen für Ihr Plugin in unserem Katalog?
Belegen Sie mit einer Datei im Repository, einer Datei auf Ihrer Domain oder einem DNS-Eintrag, dass Sie es pflegen, und Sie können dieses Zeichen auf der Karte zeigen, dazu Live-Banner für Ihre Website und Ihr README. So funktioniert die Verifizierung
Außerdem erhalten Sie Hinweise, wenn ein Marktplatz es aufnimmt, entfernt, sein Verified-Zeichen oder seine Anforderungen ändert, und sein Remote-Endpunkt wird wie ein Webdienst überwacht.
Daten von Community GitHub marketplaces. Die Zahlen stammen aus unseren eigenen regelmäßigen Durchläufen über die Marktplätze, zuletzt abgerufen am . Kontaktdaten von Plugin-Herausgebern veröffentlichen wir nicht.