Search live directory results

Planagram is a social media scheduler for small businesses, creators and agencies: personal or business, every account in one calendar. Claude AI writes your posts, Planagram posts them. Works with Instagram, Facebook, TikTok, YouTube, LinkedIn, X, Pinterest, Threads, Bluesky and Google Business. Business accounts post automatically at the time you pick; personal Instagram and Facebook profiles get a one-tap reminder at that time. What you can do from Claude: - See your connected social accounts across all 10 networks. - Ask Claude to write a post and save it as a draft, schedule it for a specific date and time, or publish it right away. - Plan a whole week in one chat: "Write and schedule 5 posts for my bakery this week." - Review what's scheduled this week or month, and see drafts, published and failed posts. - Edit or reschedule a post that hasn't gone out yet, or delete drafts and scheduled posts. - Check where a published post went live and see any publishing errors. Example requests: - "Schedule this to my Instagram and Facebook for Thursday at 9:30 AM." - "What's scheduled for next week?" - "Move tomorrow's LinkedIn post to Friday morning." - "Write three posts announcing our weekend sale and save them as drafts." Requirements: a Planagram account (free plan: 25 posts a month, no credit card; paid plans from $24/month) with at least one connected social account. Posts created from Claude count toward your plan's monthly post limit. You approve access on a Planagram consent screen and can disconnect anytime from Planagram settings.

Sales-And-Marketing

Planagram

By Planagram

Tools: 6

Plateful is where you keep the recipes you actually cook, shared with everyone in your household. This plugin brings that library into ChatGPT. Ask what to make tonight and the answer comes from recipes you have already saved and rated, not from the open web. Paste a recipe out of a conversation and save it straight to your library. Adjust servings and keep the result. Sort loose recipes into collections, or record what you thought of a dish after you cooked it.

Other

Plateful

By Kerim Ismail Oglou

Tools: 21 · Prompts: 3

Help families in Tokyo find and compare after-school childcare facilities using published facility data from gakudosagashi.jp. Search by area or school pickup and compare published fees, hours, holiday care, Saturday care, subsidies, and facility features. Availability and eligibility are not guaranteed; users should confirm details with the facility.

学童さがし

By 学童さがし（運営：アディティヤ・シン）

Tools: 5 · Prompts: 3

Choose womenswear, menswear, or both, then explore three photo-based style directions for each category. Set your price preference and use your photo to preview a shoppable outfit. Find pieces in Accessible, Premium, Luxury, or mixed price ranges. Expand your look into 3 to 14 separate capsule wardrobes with outfit images and shopping links. Image editing and live product browsing must be available in the ChatGPT experience.

Other

Style Me by yanabana

By YANA WELINDER

Prompts: 3

IntelliVen Operations Advisor helps leaders and teams use Manage to Lead to clarify goals, align their thinking, and guide execution. Draft or refine WHAT-WHO-WHY, assess a Mandate, develop Enterprise and Initiative Change Frameworks, and compare and consolidate team perspectives. IVOA applies packaged IntelliVen tutorials and rubrics, distinguishes evidence from inference, and preserves consequential disagreements for the team to resolve.

IVOA

By IntelliVen, L.L.C.

Prompts: 3

Chiedi a Lea è l'assistente di supporto per gli utenti del software LeanEco di Lean Solutions. Aiuta a consultare il manuale ufficiale e a individuare le procedure operative per utilizzare le funzionalità del software dedicate alla gestione dei rifiuti, ai formulari, ai registri di carico e scarico e al RENTRI. Le indicazioni si riferiscono alle versioni standard documentate; personalizzazioni e configurazioni specifiche possono comportare differenze. Le risposte sono generate dall'intelligenza artificiale, possono contenere errori e non sostituiscono la consulenza legale, normativa o professionale.

Chiedi a Lea...

By Lean Software

Prompts: 3

Research ecommerce products, keywords, markets and competitors. Connect your Nexscope account from the conversation and save results as files.

Data & Analytics

Nexscope

By Nexscope

Prompts: 3

Tell it what you have actually done — the work, the clients or employers, the outcomes — and it writes the document that proves it: a resume, a resume tailored to one job posting, or a capability statement for your business. Every bullet is tied to a real engagement, and tailoring re-orders what you have rather than inventing what you don't. Anything you didn't state is marked so you can fill it in, and credentials you didn't claim are simply left out. You get a real .docx in your colors that opens in Word, Pages or Google Docs — fill in the amber placeholders by clicking and typing, then export a PDF when you're ready to send it. No account needed and nothing uploaded. It can also give you a link to start a B12 website in the same colors.

Business & Operations

Resume & Credentials

By B12

Prompts: 3

Build or repair importable n8n workflow JSON, check its structure and test valid, duplicate and invalid events in isolation. Includes a read-only checker and a manual fixture tested on n8n 2.23.4. No account connection, network requests or activation by the bundled checker.

Samautomation Workflows

By Samautomation

Prompts: 2

Diagnose technical SEO in Lovable and React projects by comparing saved raw HTML with the rendered DOM. Inspect titles, canonicals, robots directives and links, then verify a targeted repair. Includes a local Python comparator. No account connection, telemetry or ranking promises.

LovableSEO

By LovableSEO

Prompts: 2

Cloudish by Hal9 helps coding agents prepare and deploy containerized websites, APIs, dashboards, and services. The plugin guides project inspection, Dockerfile preparation, runtime ports, persistent storage, encrypted secrets, deployment status, and troubleshooting using Cloudish's current API documentation. Cloudish builds containers server-side and provides a hosted URL. The plugin contains deployment instructions; it does not include a connected MCP server or interactive app.

Cloudish

By Hal9 Inc

Prompts: 1

APODICTIC is a developmental editing assistant for authors and editors revising fiction and nonfiction manuscripts. Its main purpose is to turn a draft into a structural editorial assessment and a prioritized revision plan. For fiction, it examines plot, pacing, character arcs, continuity, and the experience promised to readers. For argumentative nonfiction, it examines the central claim, supporting evidence, missing logical connections, and unanswered objections. It returns an editorial letter with prioritized findings and suggested types of revision. It diagnoses structure without rewriting the manuscript or inventing prose. Writers can also use it to organize feedback and plan revision sessions. Bundled scripts support mechanical checks and annotated manuscript exports when the host can execute them. Saved-project resume requires persistent workspace files; independent pass agents require host delegation; optional SETEC measurements require a separate compatible installation. Availability depends on the host. APODICTIC has no author-operated backend.

Creativity

APODICTIC Development Editor

By anotherpanacea

Prompts: 3

Turn an audio-plugin idea into a scoped implementation brief, an original mono LV2 gain scaffold, and an evidence-based build handoff. Includes portable Python scripts for fixed-recipe compilation, offline audio checks, exact-byte packaging, and truthful release receipts. Native execution needs an available authorized local runtime and C compiler; ChatGPT web and mobile do not gain access to your computer. No account credentials, automatic signing, publishing, or paid services are required. This first release does not provide JUCE, AU, VST3, AAX, ASIO, or universal DAW compatibility.

Dispro

By Kaizen Strategic AI Inc.

Prompts: 3

Guides you through PTS (Pivotal Token Search), an open-source framework for finding the reasoning events that change whether a language model solves a task. The workflow explains the three scales PTS searches (latent workspace meta-tokens, emitted pivotal tokens, and reasoning sentences called thought anchors), installs PTS from its README after asking you, and shows how to run a search on a task with a small local model. It explains how to read the output: probability shifts, the shared category labels, and why latent readout scores are not comparable to probability changes. It covers the hosted visualizer, linking events into chains, and exporting results as datasets for preference tuning or steering. It states the limits plainly: searches are expensive because they sample many continuations, results are observational unless you run an intervention with controls, and findings depend on the task, the model and the sampling settings. This plugin contains instructions only; everything runs on your own machine.

Scientific Research

PTS Pivotal Token Search

By PTS (codelion)

Prompts: 3

Technical help for Nek5000 users: building and running the solver, configuring cases, diagnosing errors, performance and scaling, I/O, and restarts. Answers use a layered structure with links to official NekDoc documentation, examples, source code, and relevant user discussions. Maintained by Yu-Hsiang Lan. This is a skills-only plugin; it does not operate a separate backend or store conversation data outside ChatGPT.

Nek5000 Assistant

By Yu-Hsiang Lan

Prompts: 3

Guides you through adaptive-classifier, an open-source Python library for text classifiers built on pretrained language models that learn new examples and new classes without retraining from scratch. The workflow helps you decide whether the library fits your problem (small labeled sets, label sets that change, routing, intent and moderation use cases) or whether standard fine-tuning is the better choice for a large static dataset. It checks whether the library is installed and points you to the README install steps without running them, asks before anything downloads model weights or datasets, and walks through a quickstart, adding examples and new classes later, multi-label use, strategic (anti-gaming) prediction modes, and the standard versus ONNX inference paths. It explains how to evaluate honestly: a held-out split, per-class results, calibration checks, and a comparison against a trivial baseline. It covers saving and loading and states the limits plainly, including order dependence in online learning and the cost of wrong pooling or blend settings. This plugin contains instructions only; everything runs on your own machine.

Adaptive Classifier

By adaptive-classifier (codelion)

Prompts: 3

Ask about the state of the world and get answers grounded in Our World in Data's published research: the numbers come straight from the data behind its charts, the organisation that produced them is named, and you get a link to the chart to check it yourself. Our World in Data covers poverty, health, population, energy, climate, food, education, democracy, war and more, for most countries in the world and often over decades or centuries. Use it to: - find the right chart or article on a topic - get the actual figures behind a chart, for the countries and years you need - check a number or a claim against the data - understand what a chart measures, and where its data comes from - embed a chart in a web page, or get an image of it for a slide It only uses what Our World in Data has published, from public pages on ourworldindata.org, so it can't answer questions its data doesn't cover. No account needed. Most of the data comes from other organisations, such as the UN and the World Bank; the plugin credits them, and their licences apply when you republish.

Our World in Data

By Our World in Data

Prompts: 3

Bring Lead360 Work Mode into your Claude workflow. Give Claude the authorized business and workforce context it needs to understand your account, plan work with Ask360, and review progress. Use it alongside your Claude or Duet Work Mode setup. Claude can discover available capabilities, inspect their inputs, and read permitted records across contacts, calendars, conversations, pipelines, campaigns, commerce, reporting, and other supported areas. Four discovery-and-read tools provide access to a catalog of 59 reviewed read operations; your account permissions determine which ones are available. Claude helps coordinate and reason about the work. Ask360 execution continues through Lead360’s existing governed Work Mode workflows and handoffs. This connector provides read context; it does not itself dispatch bots, send messages, publish campaigns, edit CRM records, enable schedules, or provide browser or desktop control. Requires a Lead360 account with developer access to the selected sub-account and an active private integration with supported read scopes. Sign in to Lead360, choose that integration, and approve OAuth access—no private API token is pasted into Claude. Each connection is bound to one sub-account and can be revoked from Lead360’s connector-connections page.

Lead360 Work Mode

By Lead360

Tools: 4 · Prompts: 3

Turn your notes, documents, and conversations into question-and-answer flashcards. Download an Anki-compatible APKG deck and import it into Study Daily or Anki to review with spaced repetition. The file is generated in the conversation's Python environment, with no Study Daily server or account required. Includes a Study Daily import guide. Supports basic text cards only; no media, cloze cards, review history, sync, or automatic import. Requires a conversation with Python execution and downloadable file support. Large sources can be split into multiple decks to fit file-size and execution limits. Study Daily is independent of Anki and OpenAI.

Study Daily — Flashcards

By StudyDaily

Prompts: 2

Use callable API-first tools injected into external Chrome, build missing reusable tools, and send privacy-safe feedback.

Pluno WebMCP for Anything

By Pluno

Prompts: 1

loudkit is an open-source speech engine with open weights. It runs on your own computer, with no account and no cloud API. This plugin adds local speech to a Python, JavaScript, Rust, Go or Swift project and helps you pick one of 28 voices in 10 languages. In a coding agent with a shell, on your computer or in a cloud task, it also makes WAV files from text and clones a voice from a short recording you have the right to use. Without a shell, it gives you the code and commands to run on your own computer. Your text and recordings are never sent to us: we run no servers. The model is downloaded once, then everything runs offline.

loudkit

By LoudReader

Prompts: 3

Aevral is an AI security reviewer for GitHub pull requests. Each review looks for access control, business logic, injection, XSS, SSRF, path traversal, unsafe deserialization, token and session flaws, and LLM-integration risks, and posts each finding with a suggested fix you apply. This plugin is a setup skill: it walks you through installing the Aevral GitHub App so reviews run server-side. It does not review code on your machine. After the App is installed, the next pull request can already be reviewed, including before anyone signs in to the console. Reviews are advisory and never block a merge. The optional whole-repo scan reads authorization, IDOR, and business-logic access control only; it is not secret, dependency, or memory-corruption scanning, and not a general SAST. GitHub only. By Better ISMS.

Aevral

By Better ISMS

Prompts: 3

Build product onboarding with Frigade Engage directly from ChatGPT or Codex. Create announcements, guided product tours, onboarding checklists, forms, surveys, banners, cards, NPS surveys, and flow collections. Manage flow content, targeting, publishing, versions, and promotion from development to production. Includes 23 workflow recipes, 10 technical references, and 7 YAML examples, with instructions for integrating @frigade/react into React and Next.js applications. This is a skills-only plugin. Executing workspace operations requires a Frigade account, API credentials configured securely in your project, and an execution environment with access to your application files and the Frigade API. In chat-only environments, it can prepare drafts and implementation guidance. It defaults to development, preserves production and destructive-operation safeguards, and keeps private API keys out of client-side application code. Based on the FrigadeHQ/frigade-engage-skill repository and adapted for ChatGPT and Codex.

Frigade Engage

By Frigade

Prompts: 1