Sieh dir die Reihenfolge im öffentlichen Plugin-Verzeichnis von ChatGPT nach Erfassungsdatum an. Popular ist eine redaktionelle Auswahl. Installations- und Nutzungszahlen werden dort nicht veröffentlicht.
Zuletzt beobachtet
Swifty LLC
Build, compose, review, and maintain FLOWSTACK interfaces using exact-version Agent Knowledge from installed Atom, Brick, Colors, and Theme packages. The plugin keeps finished interfaces Brick-first, validates package and ownership boundaries, and reports genuine component or product gaps instead of silently inventing APIs.
ITSalt
NaCl (reading as Natrium Chloride) is an open-source full-SDLC framework, and its core innovation is how it solves the hardest problem in agentic development: storing and retrieving project knowledge. Instead of markdown specs that agents must re-read every session, all project knowledge — requirements, architecture decisions, entities, rules, and their relationships — lives in a Neo4j knowledge graph as first-class queryable objects. The measured effect: planning a single use case takes ~550 tokens (one targeted Cypher query) instead of ~150,000 tokens (reading a ~70-file markdown spec, because the agent doesn't know in advance where the relevant facts live) — a 99.6% reduction in context per use case, repeated in every planning session. Around the graph we've built the full tooling for agentic development and testing: 57 skills covering BA → SA → TDD development → review → QA → release, quality gates before production, and an autonomous goal orchestrator (/nacl-goal). The framework answers "how is this built and why" for any part of the system, regardless of project scale or iteration count. Benchmarked on a real production project (EV charging station management): a classical team was estimated at 5,831 person-hours; running fully on NaCl the same scope takes 1,480 person-hours — 4x fewer person-hours and 60% lower cost.
Syed Fasih Haider Raza Rizvi
Turn ideas, screenshots, and designs into clean, responsive HTML, CSS, and JavaScript. Build landing pages, websites, portfolios, business pages, store pages, blogs, emails, forms, navigation, dashboards, UI components, mini apps, and more. Get help with Tailwind, Bootstrap, animations, accessibility, SEO, performance, debugging, code reviews, code conversion, and publishing. Responses may include a clearly disclosed HTML Code Generator affiliate link.
rainmanjam
Mistake-proof your code, your pipeline, and your agents. Audits code for mistakes that are possible, designs APIs where misuse cannot be expressed, installs guardrails, and turns incidents into devices that prevent recurrence.
Write submission materials
citrolabs
Control ego lite through the packaged ego-browser Skill while keeping agent browsing isolated from the user's own tabs.
Armature
Armature helps developers inspect configured MCP servers, review recorded agent sessions and use cases, investigate recurring issues, and report missing app capabilities through ChatGPT.
CompText Labs
Compile explicit requirements into a compact operational context with constraints, order, dependencies, blockers, recovery paths, validation, and a canonical digest.
Pavel Bochkov Rastopchin
Developer tooling for Codex to resume repository work across sessions and persist plans, findings, evidence and checkpoints. Use this when work must survive context compaction or reviewed failure lessons need to move into another repository you own. Project OS inspects, bootstraps, validates, repairs and upgrades visible repository records with previews before writes. ChatGPT is a companion for explanation, supplied project files and portable knowledge bundles. Do not use it for ordinary one-session coding or as an automatic global knowledge service.
Hugging Face
Developer tools for working with the Hugging Face Hub. Search model, dataset, and Space repositories; inspect repository metadata, cards, and files; browse research papers; and discover Spaces for a task. Connected accounts can create repositories, invoke supported Spaces, inspect and manage Jobs, and work with hosted sandboxes. Private content and account actions require Hugging Face sign-in and appropriate permissions. Remote compute may require plan access and incur charges.
Split specs into tickets
Rubikpara
Rubikpara’nın ödeme çözümlerini keşfedin; ürünler, API entegrasyonları, teknik dokümantasyon ve hata kodları hakkında ihtiyaç duyduğunuz resmi bilgilere yapay zekâ desteğiyle hızlı ve kolayca ulaşın.
EzzyBills
Access the authoritative EzzyBills developer specification, REST API contracts, authentication models, and integration guidance for building EzzyBills applications such as approval dashboards, email response workflows, and purchase order tools.
Fernando Tonon
QtMesh Cloud helps users inspect 3D asset quality from ChatGPT. Users can list their projects, review scan summaries, inspect findings and scan reports, check quality gate settings, update owner-scoped quality gates, and control whether a project's public report is visible.
Configure Matt skills in repos
Ethereal Material Pty Ltd
Guides ChatGPT or Codex to use a user-controlled OpenAI API gateway tool when explicitly requested, with clear billing boundaries and secure credential handling.
Promptfoo
Promptfoo skills for configuring providers and targets, writing eval suites, and setting up or running red team workflows against LLM apps.
Local memory for Codex
Abhishek Samar Singh
Apprentice spots code that sends the same shape of request to a frontier model over and over, in a loop, a cron job or an endpoint. It shows you how to capture verified examples from calls you already make, then test whether an optimized prompt or a small fine-tuned model holds quality for less.
Oren Ashkenazy
Clears AI reviewer feedback on a GitHub PR without leaving your coding agent. Waits for the configured reviewer (Codex, CodeRabbit, Copilot, or any compatible bot), reads real review-thread state via GraphQL so resolved, outdated, and already-answered threads are skipped, then fixes what is actionable in severity order. Findings are clustered by kind, so a pattern flagged at two sites gets swept across the PR's changed files in one cycle instead of dripping back over three reviews. Every fix is gated on your repository's own tests and linters before it is pushed, and re-review requests are hard-capped (default 3) so the loop cannot spam the PR. Optional per-finding triage flags false positives before you spend a cycle on them, and each run leaves an audit trail plus local stats.
Debug HTTP and HTTPS traffic
Risk-scaled repository methods
Check documentation drift
The Doers Firm
Diagram Generator converts requirements, code context, and system descriptions into readable diagrams. It selects an appropriate diagram type, produces renderable Mermaid by default, and supports architecture, flowchart, sequence, ERD, state, timeline, mind map, deployment, and user-journey views.
