Triages Outlook inboxes using Microsoft Graph API v1.0 with delta query support for incremental mail sync.
Score 70/100
Read and manage Outlook calendar and inbox via PowerShell COM interop or Microsoft Graph API
Score 70/100
Queue an existing Outlook draft into Cody's S3 approval queue. Use after a draft is created and the user wants it staged for SEND/EDIT/SKIP approval. Never sends the message.
Score 70/100
Creates and manages Outlook email rules programmatically using the Microsoft Graph API /me/mailFolders/inbox/messageRules endpoint.
Score 70/100
Send a queued Outlook draft via Microsoft Graph AFTER the user has explicitly approved the SEND. Reads the draft record from the S3 approval queue, calls POST…
Score 70/100
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly.
Score 70/100
Use the Agent class for multi-step tool loops, conversation history, and reusable LLM agents. Use when building agents with skills, structured output, or stateful conversations.
Score 70/100
Generate workflow skeleton files using the Output SDK CLI. Use when starting a new workflow, scaffolding project structure, or understanding the generated file layout.
Score 70/100
Create evaluator functions in evaluators.ts for Output SDK workflows. Use when implementing quality assessment, validation logic, or content evaluation.
Score 70/100
Workflow folder structure conventions for Output SDK. Use when creating new workflows, organizing workflow files, or understanding the standard project layout.
Score 70/100
Create .prompt files for LLM operations in Output SDK workflows. Use when designing prompts, configuring LLM providers, or using Liquid.js templating.
Score 70/100
Create step functions in steps.ts for Output SDK workflows. Use when implementing I/O operations, error handling, HTTP requests, or LLM calls.
Score 70/100
Create types.ts files with Zod schemas for Output SDK workflows. Use when defining input/output schemas, creating type definitions, or fixing schema-related errors.
Score 70/100
Calculate and display the cost of an Output SDK workflow execution run. Use when checking LLM token costs, API service costs, or total spend for a specific workflow run.
Score 70/100
Create workflow.ts files for Output SDK workflows. Use when defining workflow functions, orchestrating steps, or fixing workflow structure issues.
Score 70/100
Anti-laziness enforcement — bans placeholder patterns (// ..., // TODO, // rest of code), enforces complete code generation, handles token-limit splits cleanly.
Score 70/100
Fix direct I/O in Output SDK workflow functions. Use when workflow hangs, returns undefined, shows "workflow must be deterministic" errors, or when HTTP/API calls are made…
Score 70/100
Fix HTTP client misuse in Output SDK steps. Use when seeing untraced requests, missing error details, axios-related errors, or when HTTP calls aren't being properly logged and…
Score 70/100
Fix missing schema definitions in Output SDK steps. Use when seeing type errors, undefined properties at step boundaries, validation failures, or when step inputs/outputs aren't…
Score 70/100
Fix non-determinism errors in Output SDK workflows. Use when seeing replay failures, inconsistent results between runs, "non-deterministic" error messages, or workflows behaving…
Score 70/100
Fix try-catch anti-pattern in Output SDK workflows. Use when retries aren't working, errors are being swallowed, seeing unexpected FatalError wrapping, or when step failures don't…
Score 70/100
Fix Zod schema import issues in Output SDK workflows. Use when seeing "incompatible schema" errors, type errors at step boundaries, schema validation failures, or when schemas…
Score 70/100
Audit an existing eval suite for trustworthiness. Use when inheriting evals, suspecting evals miss real failures, or after significant pipeline changes.
Score 70/100
Design diverse eval datasets using dimension-based variation. Use when bootstrapping eval datasets, when real traces are sparse, or when existing datasets miss edge cases.
Score 70/100
Systematically review workflow traces to identify failure modes before building evaluators. Use when starting an eval project, after significant pipeline changes, or when…
Score 70/100
Design effective LLM judge .prompt files for evaluators. Use when creating judgeVerdict/judgeScore/judgeLabel prompts, or when existing judges produce unreliable results.
Score 70/100
Validate LLM judges against human labels using TPR/TNR metrics and train/dev/test splits. Use after writing a judge prompt to verify it agrees with human judgment.
Score 70/100
Post-flight validation for Output SDK workflow operations. Systematic verification of step completion, convention compliance, quality validation, and deliverable verification.
Score 70/100
Pre-flight validation checks for Output SDK workflow operations. Ensures conventions are followed, requirements are gathered, and quality gates are passed before workflow…
Score 70/100
Comprehensive guide to Output.ai Framework for building durable, LLM-powered workflows orchestrated by Temporal.
Score 70/100
Upgrade a project between versions of the Output framework. Use when the user asks to upgrade, migrate, or move to a newer Output version.
Score 70/100
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly.
Score 70/100
List all available Output SDK workflows in the project. Use when discovering what workflows exist, checking workflow names, exploring the project's workflow structure, or when…
Score 70/100
Re-run an Output SDK workflow from after a specific completed step, creating a new run that replays up to that point and re-executes subsequent steps.
Score 70/100
Get the result of an Output SDK workflow execution. Use when retrieving the output of a completed workflow, getting the return value, or checking what a workflow produced after…
Score 70/100
Start an Output SDK workflow asynchronously without waiting for completion. Use when starting long-running workflows, getting a workflow ID for later monitoring, running workflows…
Score 70/100
Check the status of an Output SDK workflow execution. Use when monitoring a running workflow, checking if a workflow completed, or determining workflow state (RUNNING, COMPLETED,…
Score 70/100
Stop a running Output SDK workflow execution. Use when cancelling a workflow, stopping a long-running process, terminating a stuck workflow, or when you need to abort a workflow…
Score 70/100
Evaluate CEOs and companies using Thorndike's Outsider framework. Trigger on: \"Is this CEO a good capital allocator?\", \"How should a company use excess cash?\", \"Should…
Score 70/100
Phân tích khung hình bằng vision LLM không phải Gemini để đề xuất vị trí text/image/video overlay tránh che chủ thể và tránh vùng unsafe, dùng khi cần quyết định placement cho…
Score 70/100
Automate Owl Protocol tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Hotel owner and asset manager reporting. Use when the user asks to 'build an owner report', 'quarterly business review', 'asset manager update', 'investor report', 'management…
Score 70/100
Internal process for the owner-router agent. Defines the step-by-step procedure for determining likely bug owners using strict 6-level routing precedence with staleness detection.
Score 70/100
Verify the junior can explain and defend every line of code they wrote. This gate BLOCKS completion if failed.
Score 70/100
Oxipng is a multithreaded lossless PNG and APNG compression optimizer written in Rust. It reduces PNG file sizes without any quality loss using advanced compression techniques…
Score 70/100
Generate images with Pruna P-Image models via inference.sh CLI. Models: P-Image, P-Image-LoRA, P-Image-Edit, P-Image-Edit-LoRA.
Score 70/100
Generate videos with Pruna P-Video and WAN models via inference.sh CLI. Models: P-Video, WAN-T2V, WAN-I2V.
Score 70/100
Peer-to-peer networking patterns using commonware for building decentralized Guts network
Score 70/100
TanStack Pacer patterns for rate limiting, debouncing, and throttling. Activates when implementing search inputs, API rate limiting, or performance optimization.
Score 70/100
Turn documentation sites, GitHub repos, and PDFs into installable agent skill packages when hand-authoring a reusable skill would be slow or inconsistent.
Score 70/100
Bundle a single plugin into a distributable marketplace archive, validating metadata and optionally publishing
Score 70/100
Manage remotely installed AIWG packages sourced from Git repositories via list, info, and remove subcommands
Score 70/100
Model and verify unlocked package dependencies, version pinning, and promotion. NOT for 1GP managed packages.
Score 70/100
specialized protocol for automated machine image creation using HashiCorp Packer, OS auto-installs (Kickstart/Preseed), and Cloud-init orchestration.
Score 70/100
Génère une checklist de voyage personnalisée selon la destination, la durée et le type de voyage. Se déclenche aussi avec "quoi emmener", "valise", "checklist voyage", "je pars…
Score 70/100
PaddleOCR is a powerful, lightweight OCR toolkit developed by Baidu that converts documents and images into structured, AI-friendly data like JSON and Markdown.
Score 70/100
Use when auditing a specific page's SEO performance, content quality, and competitive position. The agent fetches the URL, Googles the primary keyword, reads the top 3…
Score 70/100
Web page monitoring, change detection, and availability tracking. Use when tracking content changes, detecting when pages go down, monitoring for updates, preserving content…
Score 70/100
Automate Page X tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Pagefind is a static search library written in Rust that indexes your built site and adds a search bundle requiring no server infrastructure.
Score 70/100