Skills
A skill is a folder of instructions a compatible client loads when it becomes relevant. Filter by what a skill ships and what its author declares, then read it before you install it.
Ordered one entry per publisher in turn, so a page shows as many publishers as it has rows. Every skill is listed.
- orchestrateby pleasefixaiUse only when the user explicitly types `orchestrate:orchestrate <goal>` to decompose a large task, spawn a tree of…
- orthogonalby pleasefixaiDiscover, compare, price, and run third-party tools or data APIs through the connected Orthogonal MCP server. Use when…
- orthogonal-cliby pleasefixaiUse the official Orthogonal CLI to discover and inspect APIs, quote or run endpoints, generate integration code, manage…
- orthogonal-mcpby pleasefixaiConfigure or troubleshoot Orthogonal's hosted MCP server in Codex, Claude Code, Cursor, Grok Bot, or another Streamable…
- orthogonal-sdkby pleasefixaiBuild or review application code using Orthogonal's official TypeScript/JavaScript or Python SDK. Use when installing…
- OctoparseSponsoredNo-code web scraping, on a schedule.Scrape with Octoparse
- output-build-workflowby pleasefixaiImplement an Output SDK workflow from a plan document. Use when the user asks to build, implement, or code a workflow…
- output-credentials-editby pleasefixaiView, edit, and set encrypted credentials in an Output.ai project. Use when adding secrets, updating API keys,…
- output-credentials-env-varsby pleasefixaiWire encrypted credentials to environment variables using the credential: convention. Use when setting up LLM provider…
- output-credentials-initby pleasefixaiInitialize encrypted credentials for an Output.ai project. Use when setting up credentials for the first time, adding…
- output-debug-workflowby pleasefixaiDebug Output SDK workflow issues. Use when user reports a workflow failing, erroring, hanging, producing wrong results,…
- output-dev-agent-classby pleasefixaiUse the Agent class for multi-step tool loops, conversation history, streaming progress, and reusable LLM agents. Use…
- output-dev-code-styleby pleasefixaiCode style conventions for Output SDK workflow projects. Use when writing or reviewing any TypeScript/JavaScript code.…
- output-dev-cost-hooksby pleasefixaiSubscribe to cost events (cost:http:request, llm:generation:metering) to forward LLM and API spend to your own…
- output-dev-create-skeletonby pleasefixaiGenerate workflow skeleton files using the Output SDK CLI. Use when starting a new workflow, scaffolding project…
- output-dev-credentialsby pleasefixaiStore and reference encrypted secrets in Output SDK workflows using @outputai/core/credentials. Use when integrating…
- output-dev-eval-testingby pleasefixaiCreate offline evaluation tests for Output SDK workflows using @outputai/evals. Use when implementing test evaluators…
- output-dev-evaluator-functionby pleasefixaiCreate evaluator functions in evaluators.ts for Output SDK workflows. Use when implementing quality assessment,…
- output-dev-folder-structureby pleasefixaiWorkflow folder structure conventions for Output SDK. Use when creating new workflows, organizing workflow files, or…
- output-dev-http-client-createby pleasefixaiCreate shared HTTP clients in src/shared/clients/ for Output SDK workflows. Use when integrating external APIs,…
- output-dev-llm-streamingby pleasefixaiImplement LLM text streaming in Output workflow steps with generateTextWithStreaming, Agent.generateWithStreaming,…
- output-dev-model-selectionby pleasefixaiPick the right LLM model for an Output SDK prompt file. Use when writing a new .prompt file, reviewing a model choice,…
- output-dev-prompt-fileby pleasefixaiCreate .prompt files for LLM operations in Output SDK workflows. Use when designing prompts, configuring LLM providers,…
- output-dev-scenario-fileby pleasefixaiCreate test scenario JSON files for Output SDK workflows. Use when creating test inputs, documenting expected…
- output-dev-skill-fileby pleasefixaiCreate .md skill files for Output framework's lazy-loaded instruction system. Use when adding skills to prompts,…
- output-dev-step-functionby pleasefixaiCreate step functions in steps.ts for Output SDK workflows. Use when implementing I/O operations, error handling, HTTP…
- output-dev-types-fileby pleasefixaiCreate types.ts files with Zod schemas for Output SDK workflows. Use when defining input/output schemas, creating type…
- output-dev-upgrade-prompt-modelsby pleasefixaiBulk-upgrade the model field across .prompt files to the latest version of each prompt's existing family. Use when…
- output-dev-workflow-costby pleasefixaiCalculate and display the cost of an Output SDK workflow execution run. Use when checking LLM token costs, API service…
- output-dev-workflow-functionby pleasefixaiCreate workflow.ts files for Output SDK workflows. Use when defining workflow functions, orchestrating steps, or fixing…
- output-error-direct-ioby pleasefixaiFix direct I/O in Output SDK workflow functions. Use when workflow hangs, returns undefined, shows "workflow must be…
- output-error-http-clientby pleasefixaiFix HTTP client misuse in Output SDK steps. Use when seeing untraced requests, missing error details, axios-related…
- output-error-missing-schemasby pleasefixaiFix missing schema definitions in Output SDK steps. Use when seeing type errors, undefined properties at step…
- output-error-nondeterminismby pleasefixaiFix non-determinism errors in Output SDK workflows. Use when seeing replay failures, inconsistent results between runs,…
- output-error-try-catchby pleasefixaiHandle errors caught in Output workflows without losing failure context. Use when adding workflow try/catch logic,…
- output-error-zod-importby pleasefixaiFix Zod schema import issues in Output SDK workflows. Use when seeing "incompatible schema" errors, type errors at step…
- output-eval-auditby pleasefixaiAudit an existing eval suite for trustworthiness. Use when inheriting evals, suspecting evals miss real failures, or…
- output-eval-dataset-designby pleasefixaiDesign diverse eval datasets using dimension-based variation. Use when bootstrapping eval datasets, when real traces…
- output-eval-error-analysisby pleasefixaiSystematically review workflow traces to identify failure modes before building evaluators. Use when starting an eval…
- output-eval-judge-promptby pleasefixaiDesign effective LLM judge .prompt files for evaluators. Use when creating judgeVerdict/judgeScore/judgeLabel prompts,…
- output-eval-validate-judgeby pleasefixaiValidate LLM judges against human labels using TPR/TNR metrics and train/dev/test splits. Use after writing a judge…
- output-meta-post-flightby pleasefixaiPost-flight validation for Output SDK workflow operations. Systematic verification of step completion, convention…
- output-meta-pre-flightby pleasefixaiPre-flight validation checks for Output SDK workflow operations. Ensures conventions are followed, requirements are…
- output-meta-project-contextby pleasefixaiComprehensive guide to Output.ai Framework for building durable, LLM-powered workflows orchestrated by Temporal. Covers…
- output-migrateby pleasefixaiUpgrade a project between versions of the Output framework. Use when the user asks to upgrade, migrate, or move to a…
- output-plan-workflowby pleasefixaiUse when the user asks to create, build, generate, scaffold, or plan a new workflow. Orchestrates the full planning…
- output-services-checkby pleasefixaiVerify Output SDK development services are running. Use when debugging workflows, starting development, encountering…
- output-workflow-listby pleasefixaiList all available Output SDK workflows in the project. Use when discovering what workflows exist, checking workflow…
- output-workflow-resetby pleasefixaiRe-run an Output SDK workflow from after a specific completed step, creating a new run that replays up to that point…
