Track competitors while you build your plugin.

Publisher full description

…saved logic instead of asking a model to reinvent every step. Scripted control flow makes repeated execution more predictable and reduces opportunities for model errors to accumulate across long tasks. For illustration, an independent 1% error probability per decision produces a 99.3% chance of at… …ligence is needed: generating text, images or video, interpreting a page, and making judgments. Let code handle the reusable workflow around those calls. Replacing 100 comparable model calls with one means 100x fewer calls; actual savings depend on the workflow, tokens and providers. Script executio…

Publisher full description

…ister BetterContext callable MCP tools. Memory and relay work through the assistant's local command execution and require Python 3.10+ plus access to your chosen persistent folder. Ordinary hosted ChatGPT chats cannot access your computer's memory database by installing this plugin. Hosted ChatGPT W… …y queues messages; it does not itself wake another chat. An optional helper can wake selected local Codex tasks when the destination computer is running and has a compatible Codex CLI. Windows helper installation is tested; new Linux/macOS installers and reboot behavior remain unverified. Hosted Cha…

Publisher full description

…on available host capabilities and user authorization; the plugin itself does not operate a hosted code-execution service.

Publisher full description

Connect ChatGPT or Codex to the Candao Circles explicitly granted to the signed-in account. Work in a Slack-like Circle experience: read workspace context and assigned tasks, participate in topics, create permission-sco… …ublished AI workflows without crossing Circle or topic boundaries. Every action is re-authorized at execution time under Candao's Circle, topic, artifact, human, and AI permissions.

Publisher full description

Professional, deterministic FFmpeg and FFprobe workflows for ChatGPT and Codex. Inspect media, edit video and audio, convert formats, compose clips and slideshows, diagnose and repair media, plan streaming workflows, and author reusable YAML pipelines. The included Skills… …ion. Executable workflows require Node.js 22+ and FFmpeg/FFprobe 6.1+; environments without command execution can still use the plugin to plan commands and author deterministic pipelines.

Publisher full description

…ted figures are inspected for readability. References cover OpenFOAM, SU2, FDS, MFiX, DualSPHysics, code_saturne, Basilisk, Nek5000/nekRS, Palabos, OpenLB, Nektar++, PyFR, and PyIB. Solver choice depends on the problem and available evidence. Actual simulations require host tools that can access the… …does not bundle solvers, provide a hosted computation service, or require an MCP server. Available execution features depend on the host and the user's environment. Developed by Zhaoyue Xu, Experimental Zoology Group, Wageningen University & Research (WUR), Netherlands.

Publisher full description

…ws for business, research, projects, controlled implementation packages, risk-adaptive coding-agent execution, representation-first creative production, lean harness architecture, task and context control, oracle-first evidence validation, intermediate checkpoint verification, independent review, hi… …documentation migration, software execution, high-fidelity interfaces, realtime 3D, defect repair, code migration, performance, regression testing, continuity, media, writing, finances, real estate, learning and everyday planning. ChatGPT selects the smallest relevant workflow, production represent…

Publisher full description

…L warehouses, Microsoft Fabric/OneLake, data quality, lineage and incident response. Inspect actual code, logs, query plans and data contracts where the user supplies them or authorized tools are available; identify root causes, plan safe replay and backfills, check schema/row grain, and validate fi… …s exist. Skills-only: no automatic access to clusters, credentials, datasets or production systems; executions and changes require enabled tools and permissions.

Publisher full description

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 p… …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 pro…

Publisher full description

…eports are written only to a new output path when requested. Requires Python 3.9+ and a terminal or code execution environment. Host chat and execution-environment data handling still applies. It does not apply patches or determine API compatibility without a supplied contract. Independent community soft…

Publisher full description

Troubleshoot recurring MCP server connection errors, Claude Code and Cursor tooling failures, Codex authentication errors, and CI or dependency failures by finding prior public investigations. Search a short, sanitized exact error, then read a relevant Problem… …version-dependent changes. KFA contains imported public knowledge, source-reported workarounds and execution reports. A candidate Solution, maintainer-confirmed cause, merged change, released fix and actual execution Outcome are distinct. An Outcome describes one reported execution; independent rep…

Publisher full description

…pplications and tool-using agent systems without adding unnecessary autonomy. Compare deterministic code, single model calls, bounded tools, directed workflows, autonomous agents and multi-agent systems. Define secure tool contracts, permissions, approval flows, MCP integration, state and memory, ev… …, technical references and offline fixtures. It is skills-only: coding, real subagents, tools, eval execution and deployment require user-authorized capabilities available in the host environment.

Publisher full description

…into a client-ready intervention brief: a justified move, usable pitch or work draft, and separate execution and outcome checks. Supports AI visibility, GEO/AEO, SEO content discovery and digital PR planning. Includes the existing Machine Relations Index research skill and four read-only tools for… …purchase, outreach sending or paid measurement panel. Public MRI data is licensed CC BY 4.0; plugin code is MIT.

Publisher full description

…It runs on the Mergify CLI, a single static binary with no runtime to install, so it needs a local execution environment: Codex, or ChatGPT desktop with local execution. You need a GitHub repository with Mergify enabled. Install the CLI with 'brew install mergifyio/tap/mergify-cli', sign in once with 'mergify auth login'…

Publisher full description

…as board decisions. You can revise choices and regenerate the draft. Designed for ChatGPT Work and Codex environments that can run bundled scripts. Node.js is required for deterministic generation. Word export also requires Python and python-docx; an editable Markdown draft is available without Word export. Without script execution, the plugin can guide the questionnaire and explain the template, but cannot claim to generate the deterministic document. No external app account or email is required. This package contains…

Publisher description

Bring Nooks revenue execution data and workflows into ChatGPT and Codex.

Publisher full description

…ers, analytics engineers, and platform teams who already manage Preset or Apache Superset assets as code. Limitations: the skills assume the `sup` CLI is installed and authenticated in the execution environment, and they act only on workspaces the signed-in user can already reach. They do not bundle credentials, and they do not create or administer Preset accounts.

Publisher full description

Build and refine strategy code for TradingView, Python, MultiCharts, MT4, MT5, NinjaTrader and cTrader, with static audits, backtest analysis, Monte Carlo simulations, walk-forward reports and portfolio analysis. Supports Pine… …mported results do not prove runtime correctness or future profitability. No broker access or trade execution.

Publisher description

Live SEO evidence, deterministic analysis, information-gain research, and safe execution workflows for ChatGPT and Codex.

Publisher full description

…voice, copyright-aware quotations and transparent uncertainty. Real web access, source inspection, code execution, publication and multi-agent workflows depend on the host tools and user authorization; this skills-only plugin does not provide its own remote data collection or publishing service.

Publisher description

SalesTouch is the LinkedIn MCP for AI agents. Connect ChatGPT or Codex to LinkedIn tools to find prospects, research context, build relationships and keep outreach moving from one conversation. Extract prospect lists from LinkedIn searches, posts and groups. Read p… …ermissions, account controls, daily limits, working hours, queues, cooldowns and activity logs keep execution within your settings. Production use requires a SalesTouch account with an active trial or plan and a connected LinkedIn account. Sales Navigator is optional for supported premium sources.

Publisher full description

…e existing webhooks. New products default to draft. Each requested change has its own tool, tracked execution status and duplicate protection; successful creates and edits are read back where supported. Read-only keys remain read-only. Live changes require a store-owner Read/Write key and explicit w… …ge cards, initiate payments or send money through a payment gateway. No arbitrary WordPress routes, code execution, plugin installation, credential changes, new webhook destinations or arbitrary custom metadata. Only selected non-secret core settings are exposed. The designated reviewer demo uses cl…

Publisher full description

…licit visual systems, platform-aware implementation, security and testing guidance, and independent code/visual review. Supports real subagents and coding tools only where the host provides them; does not itself include a hosted coding service or promise deployment, simulator access or live execution without tools.

Publisher full description

…sting runs, fitness changes and stored training analysis from their own Yigri account in ChatGPT or Codex. Read recent runs, stored run analysis, fitness trends with comparison dates, key findings, weekly execution and stored Weekly Readout. Access is read-only and requires approval for each AI connection. Supported sources are Garmin and COROS through Stridee, and Apple Health. Accounts with a current…