Development
Plugin
output
The open-source TypeScript framework for building AI workflows and agents. Designed for Claude Code — describe what you want, Claude builds it, with all the best practices already in place. One framework.
Plugin Signal89/100Strong
maintained99
capable87
documented100
adopted56
Install on Claude Code
> /plugin marketplace add growthxai/output> /plugin install outputai@outputai
Stats
430
Stars
12
Forks
Active
Maintenance
JavaScript
Language
Apache-2.0
License
4h ago
Last commit
4mo ago
Created
Repo: growthxai/output
In this plugin
- skills
- llm-output-schema-constraints
- prompt-file-provider-options
- validate
- output-build-workflow
- output-credentials-edit
- output-credentials-env-vars
- output-credentials-init
- output-debug-workflow
- output-dev-agent-class
- output-dev-code-style
- output-dev-create-skeleton
- output-dev-credentials
- output-dev-eval-testing
- output-dev-evaluator-function
- output-dev-folder-structure
- output-dev-http-client-create
- output-dev-model-selection
- output-dev-prompt-file
- output-dev-scenario-file
- output-dev-skill-file
- output-dev-step-function
- output-dev-types-file
- output-dev-upgrade-prompt-models
- output-dev-workflow-cost
- output-dev-workflow-function
- output-error-direct-io
- output-error-http-client
- output-error-missing-schemas
- output-error-nondeterminism
- output-error-try-catch
- output-error-zod-import
- output-eval-audit
- output-eval-dataset-design
- output-eval-error-analysis
- output-eval-judge-prompt
- output-eval-validate-judge
- output-meta-post-flight
- output-meta-pre-flight
- output-meta-project-context
- output-migrate
- output-plan-workflow
- output-services-check
- output-workflow-list
- output-workflow-reset
- output-workflow-result
- output-workflow-run
- output-workflow-runs-list
- output-workflow-start
- output-workflow-status
- output-workflow-stop
- output-workflow-trace-file
- output-workflow-trace
- agents
- commands
What's inside
Skills
52/llm-output-schema-constraintsZod schema constraints that Anthropic rejects or silently ignores when sent as structured-output tool definitions via Output.object(). Use when writing or reviewing Zod schemas passed to Output.object(), or debugging structured-output validation errors./prompt-file-provider-optionsGuide to the providerOptions structure in .prompt files — decision tree for where an option goes, common mistakes, per-provider quick reference, and Anthropic prompt caching. Use when writing or reviewing .prompt file frontmatter (provider, model, providerOptions,/validateRun lint, build, and tests to validate changes are correct/output-build-workflowImplement an Output SDK workflow from a plan document. Use when the user asks to build, implement, or code a workflow from an existing plan, or after output-plan-workflow has produced a plan and the user is ready to build./output-credentials-editView and edit encrypted credentials in an Output.ai project. Use when adding secrets, updating API keys, verifying credential values, or retrieving a specific credential./output-credentials-env-varsWire encrypted credentials to environment variables using the credential: convention. Use when setting up LLM provider keys (ANTHROPIC_API_KEY, OPENAI_API_KEY) or any env var that should come from encrypted credentials.
Show all 52 skillsShow fewer
/output-credentials-initInitialize encrypted credentials for an Output.ai project. Use when setting up credentials for the first time, adding environment-specific credentials, or adding per-workflow credentials./output-debug-workflowDebug Output SDK workflow issues. Use when user reports a workflow failing, erroring, hanging, producing wrong results, or asks to debug, troubleshoot, or investigate a workflow execution./output-dev-agent-classUse 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./output-dev-code-styleCode style conventions for Output SDK workflow projects. Use when writing or reviewing any TypeScript/JavaScript code. Discovers the project's own linting rules first; falls back to Output SDK conventions when no linter is configured./output-dev-create-skeletonGenerate workflow skeleton files using the Output SDK CLI. Use when starting a new workflow, scaffolding project structure, or understanding the generated file layout./output-dev-credentialsStore and reference encrypted secrets in Output SDK workflows using @outputai/credentials. Use when integrating API keys, database passwords, or third-party tokens./output-dev-eval-testingCreate offline evaluation tests for Output SDK workflows using @outputai/evals. Use when implementing test evaluators with verify(), creating dataset YAML files, building eval workflows, or running workflow tests via CLI./output-dev-evaluator-functionCreate evaluator functions in evaluators.ts for Output SDK workflows. Use when implementing quality assessment, validation logic, or content evaluation./output-dev-folder-structureWorkflow folder structure conventions for Output SDK. Use when creating new workflows, organizing workflow files, or understanding the standard project layout./output-dev-http-client-createCreate shared HTTP clients in src/shared/clients/ for Output SDK workflows. Use when integrating external APIs, creating service wrappers, or standardizing HTTP operations./output-dev-model-selectionPick the right LLM model for an Output SDK prompt file. Use when writing a new .prompt file, reviewing a model choice, or upgrading a stale model. Walks through priority (reasoning/balance/speed/cost), provider selection, and a live lookup against the Vercel AI Gateway model/output-dev-prompt-fileCreate .prompt files for LLM operations in Output SDK workflows. Use when designing prompts, configuring LLM providers, or using Liquid.js templating./output-dev-scenario-fileCreate test scenario JSON files for Output SDK workflows. Use when creating test inputs, documenting expected behaviors, or setting up workflow testing./output-dev-skill-fileCreate .md skill files for Output framework's lazy-loaded instruction system. Use when adding skills to prompts, configuring skill loading, or debugging skill resolution./output-dev-step-functionCreate step functions in steps.ts for Output SDK workflows. Use when implementing I/O operations, error handling, HTTP requests, or LLM calls./output-dev-types-fileCreate types.ts files with Zod schemas for Output SDK workflows. Use when defining input/output schemas, creating type definitions, or fixing schema-related errors./output-dev-upgrade-prompt-modelsBulk-upgrade the model field across .prompt files to the latest version of each prompt's existing family. Use when prompt models have drifted (eg sonnet-4 → sonnet-4-6), after a long pause between framework updates, or as part of a periodic model-freshness pass. Within-family/output-dev-workflow-costCalculate 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./output-dev-workflow-functionCreate workflow.ts files for Output SDK workflows. Use when defining workflow functions, orchestrating steps, or fixing workflow structure issues./output-error-direct-ioFix 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 directly in workflow code./output-error-http-clientFix 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 retried./output-error-missing-schemasFix 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 being properly typed./output-error-nondeterminismFix non-determinism errors in Output SDK workflows. Use when seeing replay failures, inconsistent results between runs, "non-deterministic" error messages, or workflows behaving differently on retry./output-error-try-catchHandle errors caught in Output workflows without losing failure context. Use when adding workflow try/catch logic, fallbacks, partial-failure handling, custom Error classes, or typed checks for errors thrown by steps and evaluators./output-error-zod-importFix 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 don't match between steps./output-eval-auditAudit an existing eval suite for trustworthiness. Use when inheriting evals, suspecting evals miss real failures, or after significant pipeline changes./output-eval-dataset-designDesign diverse eval datasets using dimension-based variation. Use when bootstrapping eval datasets, when real traces are sparse, or when existing datasets miss edge cases./output-eval-error-analysisSystematically review workflow traces to identify failure modes before building evaluators. Use when starting an eval project, after significant pipeline changes, or when production quality drops./output-eval-judge-promptDesign effective LLM judge .prompt files for evaluators. Use when creating judgeVerdict/judgeScore/judgeLabel prompts, or when existing judges produce unreliable results./output-eval-validate-judgeValidate 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./output-meta-post-flightPost-flight validation for Output SDK workflow operations. Systematic verification of step completion, convention compliance, quality validation, and deliverable verification./output-meta-pre-flightPre-flight validation checks for Output SDK workflow operations. Ensures conventions are followed, requirements are gathered, and quality gates are passed before workflow execution./output-meta-project-contextComprehensive guide to Output.ai Framework for building durable, LLM-powered workflows orchestrated by Temporal. Covers project structure, workflow patterns, steps, LLM integration, HTTP clients, CLI commands, and the full inventory of available agents and skills./output-migrateUpgrade a project between versions of the Output framework. Use when the user asks to upgrade, migrate, or move to a newer Output version. Detects the current @outputai/* version in the project, fetches the matching migration guide from docs.output.ai, applies the changes, and/output-plan-workflowUse when the user asks to create, build, generate, scaffold, or plan a new workflow. Orchestrates the full planning process including architecture, steps, prompts, evaluators, and testing strategy using specialized subagents./output-services-checkVerify Output SDK development services are running. Use when debugging workflows, starting development, encountering connection errors, services may be down, or when you see "ECONNREFUSED" or timeout errors./output-workflow-listList 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 unsure which workflows are available to run./output-workflow-resetRe-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. Use when iterating on a later step's prompt or logic without re-running the entire workflow, or when recovering from a failure/output-workflow-resultGet 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 async execution./output-workflow-runExecute an Output SDK workflow synchronously and wait for the result. Use when running a workflow and needing immediate results, testing workflow execution, or getting the output directly in the terminal./output-workflow-runs-listList Output SDK workflow execution history. Use when finding failed runs, reviewing past executions, identifying workflow IDs for debugging, filtering runs by workflow type, or investigating recent workflow activity./output-workflow-startStart an Output SDK workflow asynchronously without waiting for completion. Use when starting long-running workflows, getting a workflow ID for later monitoring, running workflows in the background, or executing multiple workflows in parallel./output-workflow-statusCheck 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, FAILED, TERMINATED)./output-workflow-stopStop 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 in progress./output-workflow-trace-fileRead and render the output of a local Output SDK workflow trace file as clean readable markdown. Use when the user wants to view what a recent workflow produced, see the result from a local trace file, or render trace output as a document./output-workflow-traceAnalyze Output SDK workflow execution traces. Use when debugging a specific workflow, examining step failures, analyzing input/output data, understanding execution flow, or when you have a workflow ID to investigate.
Agents
11api-expertUse this agent for Output.ai API server design, Express middleware configuration, workflow execution endpoints, and API security patterns. Specializes in workflow integration via REST APIs.docker-expertUse this agent for Output.ai containerization including Docker Compose configuration, Node.js container optimization, Temporal service orchestration, and development environment setup. Specializes in Output deployment patterns.llm-expertUse this agent for AI SDK integration, LLM provider configuration, prompt template management, error handling for AI APIs, and optimizing LLM workflow patterns within Output. Specializes in Anthropic Claude and OpenAI integrations.nodejs-expertUse this agent for Node.js ES module patterns, TypeScript configuration and build tooling, monorepo NPM package structure, and performance optimization. Specializes in Output.ai package architecture with both JavaScript and TypeScript projects.temporal-expertUse this agent for Output.ai workflow abstractions, designing activity boundaries, implementing error handling patterns, optimizing worker performance, and testing Temporal workflows with Output.ai patterns. Specializes in LLM workflow integration and Output.ai best practices.testing-expertUse this agent for Output.ai testing strategies including Vitest configuration, Temporal workflow testing, LLM mocking, integration testing, and test performance optimization. Specializes in JavaScript testing patterns with Output.ai abstractions.
Show all 11 agentsShow fewer
workflow_context_fetcherUse proactively to retrieve and extract relevant information from Output SDK project documentation files. Checks if content is already in context before returning.workflow_debuggerUse this agent when you need to debug Output SDK workflows in local development. Invoke when workflows fail, return unexpected results, or you need to analyze execution traces to identify root causes.workflow_plannerDesign new workflows for the Output SDK system, plan complex workflow orchestrations, or create comprehensive implementation blueprints. Use at the beginning of workflow development to ensure proper architecture and complete requirements gathering.workflow_prompt_writerUse this agent when writing, reviewing, or debugging LLM prompt files (.prompt). Specializes in Liquid.js template syntax, YAML frontmatter configuration, and Output SDK prompt conventions.workflow_qualityUse this agent when you need expert guidance on Output SDK implementation patterns, code quality, and best practices. Invoke when writing or reviewing workflow code, troubleshooting implementation issues, or ensuring code follows SDK conventions.
Badges
5
README
1Output
The open-source TypeScript framework for building AI workflows and agents. Designed for Claude Code — describe what you want, Claude builds it, with all the best practices already in place.
One framework. Prompts, evals, tracing, cost tracking, orchestration, credentials. No SaaS fragmentation. No vendor lock-in. Everything in your codebase, everything your AI coding agent can reach.
Why Output
Every piece of the AI stack is becoming a separate subscription. Prompts in one tool. Traces in another. Evals in a third. Cost tracking across five dashboards. None of them talk to each other. Half of them will get acquired or shut down before your product ships.
Output brings everything together. One TypeScript framework, extracted from thousands of production AI workflows. Best practices baked in so beginners ship professional code from day one, and experienced AI engineers stop rebuilding the same infrastructure.
Build AI using AI
Output is the first framework designed for AI coding agents. The entire codebase is structured so Claude Code can scaffold, plan, generate, test, and iterate on your workflows. Every workflow is a folder — code, prompts, tests, evals, traces, all together. Your agent reads one folder and has full context.
Own your prompts
.prompt files with YAML frontmatter and Liquid templating. Version-controlled, reviewable in PRs, deployed with your code. Switch providers by changing one line. No subscription needed to manage your own prompts.
See everything that happens
Every LLM call, HTTP request, and step traced automatically. Token counts, costs, latency, full prompt/response pairs. JSON in logs/runs/. Zero config. Claude Code analyzes your traces and fixes issues — because the data is in your file system.
Test AI like software
LLM-as-judge evaluators with confidence scores. Inline evaluators for production retry loops. Offline evaluators for dataset testing. Deterministic assertions and subjective quality judges.
Use any model
Anthropic, OpenAI, Azure, Vertex AI, Bedrock. One API. Structured outputs, streaming, tool calling — all work the same regardless of provider.
Scale without worrying
Temporal under the hood. Automatic retries with exponential backoff. Workflow history. Replay on failure. Child workflows. Parallel execution with concurrency control. You don't think about Temporal until you need it — then it's already there.
Keep secrets secret
AI apps need a lot of API keys. Sharing .env files is risky, and coding agents shouldn't see your secrets. Output encrypts credentials with AES-256-GCM, scoped per environment and workflow, managed through the CLI. No external vault subscription needed.
Quick Start
Requirements:
- Node.js 20+
- Docker Desktop
- An LLM API key (e.g. Anthropic)
Scaffold a project and add your API key to .env (ANTHROPIC_API_KEY=sk-ant-...):
npx @outputai/cli init
cd <project-name>
Start the full development environment — Temporal server, API server, a worker with hot reload, and the Temporal UI at http://localhost:8080:
npx output dev
Run your first workflow and inspect the execution:
npx output workflow run blog_evaluator paulgraham_hwh
npx output workflow debug <workflow-id>
For the full getting started guide, see the documentation.
Core Concepts
Workflows
Orchestration layer — deterministic coordination logic, no I/O.
// src/workflows/research/workflow.ts
workflow({
name: 'research',
fn: async (input) => {
const data = await gatherSources(input);
const analysis = await analyzeContent(data);
const quality = await checkQuality(analysis);
return quality.passed ? analysis : await reviseContent(analysis, quality);
}
});
Steps
Where I/O happens — API calls, LLM requests, database queries. Each step runs once and its result is cached for replay.
// src/workflows/research/steps.ts
step({
name: 'gatherSources',
fn: async (input) => {
const results = await searchApi(input.topic);
return { sources: results };
}
});
Prompts
.prompt files with YAML configuration and Liquid templating.
---
provider: anthropic
model: claude-sonnet-4-20250514
temperature: 0
---
<system>You are a research analyst.</system>
<user>Analyze the following sources about {{ topic }}: {{ sources }}</user>
Evaluators
LLM-as-judge evaluation with confidence scores and reasoning.
// src/workflows/research/evaluators.ts
evaluator({
name: 'checkQuality',
fn: async (content) => {
const { output } = await generateText({
prompt: 'evaluate_quality',
variables: { content },
output: Output.object({
schema: z.object({
isQuality: z.boolean(),
confidence: z.number().describe('0-100'),
reasoning: z.string()
})
})
});
return new EvaluationBooleanResult({
value: output.isQuality,
confidence: output.confidence,
reasoning: output.reasoning
});
}
});
SDK Packages
| Package | Description |
|---|---|
| @outputai/core | Workflow, step, and evaluator primitives |
| @outputai/llm | Multi-provider LLM with prompt management |
| @outputai/http | HTTP client with tracing |
| @outputai/cli | CLI for project init, dev environment, and workflow management |
Example Workflows
Production-ready workflows you can run locally, learn from, and fork — all from the output-examples gallery:
| Workflow | Description | APIs |
|---|---|---|
| blog_evaluator | Evaluate blog post signal-to-noise quality | Jina Reader |
| call_scorer | Score sales call transcripts against MEDDIC, BANT, or SPIN | LLM only |
| changelog_generator | Generate categorized changelogs from GitHub commits and PRs | GitHub |
| dependency_audit | Audit npm dependencies for vulnerabilities, licenses, and abandonment | GitHub, OSV, npm |
| recipe_extractor | Extract structured recipes from blog URLs | Jina Reader |
| url_summarizer | Summarize any webpage into TLDR, key points, and FAQ | Jina Reader |
| youtube_summarizer | Summarize YouTube videos with key moments and takeaways | YouTube |
| ai_hn_digest | Personalized Hacker News digest published to Beehiiv newsletter | HN, Jina Reader, Beehiiv |
| sales_call_processor | Process sales call transcripts into notes + parallel recipe analyses | LLM only |
Browse the full gallery at output.ai/gallery.
Projects using Output
| Project | Description |
|---|---|
| CheckThat is an AEO platform built on Output's durable, deterministic LLM workflows — tracking how B2B brands show up across ChatGPT, Claude, Perplexity, and Google AI, covering 2.6M+ AI responses spanning 5,875+ brands. |
Configuration
For production configuration and advanced settings (LLM providers, Temporal Cloud, tracing, and more), see the operations docs.
Contributing
See CONTRIBUTING.md.
License
Apache 2.0 — see LICENSE file.
Acknowledgments
Built with Temporal, Vercel AI SDK, Zod, LiquidJS.
File tree
1042growthxai/outputView on GitHub
.changeset/
calm-lions-env.md
calm-results-display.md
clear-errors-return.md
config.json
cozy-peas-stand.md
direct-results-flow.md
fancy-wombats-buy.md
heavy-friends-beg.md
honest-years-smash.md
lazy-suits-stop.md
neat-cups-drop.md
petite-rivers-melt.md
pink-wings-judge.md
plain-llm-errors.md
quick-bat-fly.md
README.md
red-dragon-fly.md
shaggy-ads-march.md
short-keys-begin.md
shy-foxes-try.md
stale-crabs-kiss.md
swift-balloons-march.md
swift-snails-bet.md
swift-things-sort.md
true-parents-worry.md
two-socks-post.md
.claude/
.claude-plugin/
marketplace.json
agents/
api-expert.md
docker-expert.md
llm-expert.md
nodejs-expert.md
temporal-expert.md
testing-expert.md
commands/
pr-review.md
settings.json
skills/
llm-output-schema-constraints/
SKILL.md
prompt-file-provider-options/
SKILL.md
validate/
SKILL.md
.dockerignore
.github/
dependabot.yml
ISSUE_TEMPLATE/
bug_report.md
config.yml
feature_request.md
pull_request_template.md
scripts/
post_pr_review_comment.mjs
pr_review_markdown.js
pr_review_markdown.spec.js
pr_review.schema.json
workflows/
auto_pr_review.yml
claude.yml
docs_regenerate.yml
publish_dev.yml
publish_next.yml
publish.yml
release.yml
validation_dependabot.yml
validation_e2e.yml
validation.yml
.gitignore
.husky/
pre-commit
.npmrc
.tool-versions
api/
CHANGELOG.md
openapi.json
package.json
README.md
scripts/
generate_openapi.js
src/
clients/
errors.js
event_serialization.js
event_serialization.spec.js
event_types.js
event_types.spec.js
s3_client.js
s3_client.spec.js
temporal/
catalog.js
catalog.spec.js
connection_monitor.js
connection_monitor.spec.js
index.js
index.spec.js
types.js
types.spec.js
workflow/
workflow_result.js
workflow_result.spec.js
communication.js
communication.spec.js
describe_workflow.js
describe_workflow.spec.js
fetch_history_page.js
fetch_history_page.spec.js
get_history.js
get_history.spec.js
get_input.js
get_input.spec.js
get_result.js
get_result.spec.js
get_status.js
get_status.spec.js
index.js
list_runs.js
list_runs.spec.js
reset.js
reset.spec.js
run.js
run.spec.js
start.js
start.spec.js
stop.js
stop.spec.js
stream_history.js
stream_history.spec.js
terminate.js
terminate.spec.js
configs.js
configs.spec.js
handlers/
trace_log.js
trace_log.spec.js
utils.js
workflow_history_stream.js
workflow_history_stream.spec.js
workflow_history.js
workflow_history.spec.js
workflow_run.js
workflow_run.spec.js
index.js
index.spec.js
logger.js
middleware/
deprecated.js
error_handler.js
error_handler.spec.js
http_logger.js
http_logger.spec.js
request_id.js
utils.js
utils.spec.js
assets/
checkthat.png
home.png
CLAUDE.md
CODE_OF_CONDUCT.md
coding_assistants/
claude/
plugins/
outputai/
.claude-plugin/
plugin.json
agents/
workflow_context_fetcher.md
workflow_debugger.md
workflow_planner.md
workflow_prompt_writer.md
workflow_quality.md
hooks/
hooks.json
SESSION_START_CONTEXT.md
skills/
output-build-workflow/
SKILL.md
output-credentials-edit/
SKILL.md
output-credentials-env-vars/
SKILL.md
output-credentials-init/
SKILL.md
output-debug-workflow/
SKILL.md
output-dev-agent-class/
SKILL.md
output-dev-code-style/
SKILL.md
output-dev-create-skeleton/
SKILL.md
output-dev-credentials/
SKILL.md
output-dev-eval-testing/
SKILL.md
output-dev-evaluator-function/
SKILL.md
output-dev-folder-structure/
SKILL.md
output-dev-http-client-create/
SKILL.md
output-dev-model-selection/
SKILL.md
output-dev-prompt-file/
SKILL.md
output-dev-scenario-file/
SKILL.md
output-dev-skill-file/
SKILL.md
output-dev-step-function/
SKILL.md
output-dev-types-file/
SKILL.md
output-dev-upgrade-prompt-models/
SKILL.md
output-dev-workflow-cost/
SKILL.md
output-dev-workflow-function/
SKILL.md
output-error-direct-io/
SKILL.md
output-error-http-client/
SKILL.md
output-error-missing-schemas/
SKILL.md
output-error-nondeterminism/
SKILL.md
output-error-try-catch/
SKILL.md
output-error-zod-import/
SKILL.md
output-eval-audit/
SKILL.md
output-eval-dataset-design/
SKILL.md
output-eval-error-analysis/
SKILL.md
output-eval-judge-prompt/
SKILL.md
output-eval-validate-judge/
SKILL.md
output-meta-post-flight/
SKILL.md
output-meta-pre-flight/
SKILL.md
output-meta-project-context/
SKILL.md
output-migrate/
SKILL.md
output-plan-workflow/
SKILL.md
output-services-check/
SKILL.md
output-workflow-list/
SKILL.md
output-workflow-reset/
SKILL.md
output-workflow-result/
SKILL.md
output-workflow-run/
SKILL.md
output-workflow-runs-list/
SKILL.md
output-workflow-start/
SKILL.md
output-workflow-status/
SKILL.md
output-workflow-stop/
SKILL.md
output-workflow-trace/
output-workflow-trace-file/
SKILL.md
SKILL.md
README.md
context7.json
CONTRIBUTING.md
docker-compose.dev.yml
docker-compose.prod.yml
docker-compose.temporal.yml
docs/
guides/
api/
authentication.mdx
configuration.mdx
errors.mdx
index.mdx
changelog/
index.mdx
CLAUDE.md
clients/
index.mdx
cookbook/
assets/
zapier-app-connections.png
overview.mdx
zapier-sdk.mdx
costs/
cost-events.mdx
index.mdx
data/
releases.json
docs.json
evaluators/
best-practices.mdx
datasets-and-cli.mdx
datasets.mdx
evaluator-step.mdx
index.mdx
verdicts.mdx
workflow-evaluators.mdx
favicon.svg
index.mdx
llm/
index.mdx
providers.mdx
logo/
logo.svg
migrations/
index.mdx
v0.1.12-to-v0.2.0.mdx
v0.10.0-to-v0.11.0.mdx
v0.2.0-to-v0.3.0.mdx
v0.3.0-to-v0.4.0.mdx
v0.4.0-to-v0.5.0.mdx
v0.5.2-to-v0.6.0.mdx
v0.6.0-to-v0.7.0.mdx
v0.7.0-to-v0.8.0.mdx
v0.8.0-to-v0.9.0.mdx
v0.9.0-to-v0.10.0.mdx
openapi.json
operations/
credentials.mdx
deployment/
deployment.mdx
advanced.mdx
railway.mdx
render.mdx
error-handling.mdx
error-hooks.mdx
external-workflow-packages.mdx
testing.mdx
tracing.mdx
worker-tuning.mdx
packages/
cli.mdx
core.mdx
credentials.mdx
evals.mdx
http.mdx
llm.mdx
prompts/
best-practices.mdx
index.mdx
skills.mdx
templating.mdx
README.md
scripts/
build_releases_json.mjs
lib/
changeset_parser.mjs
renderer.mjs
store.mjs
regenerate.mjs
start-here/
claude-code.mdx
getting-started.mdx
learning-path.mdx
steps/
best-practices.mdx
index.mdx
TODO_pages.md
workflows/
child-workflows.mdx
context.mdx
external-integration.mdx
index.mdx
parallel-execution.mdx
running.mdx
eslint.config.js
LICENSE
ops/
alert.sh
api.Dockerfile
assert_changelog_synced.sh
bump_prerelease.sh
bump_release.sh
ensure_eof_blank_line.sh
extra_files_error.sh
extra_files_warning.sh
format_files.sh
get_bump.sh
mint.Dockerfile
publish_api.sh
publish_npm.sh
README.md
regenerate_docs.sh
tag.sh
... 923 moreFAQ
output is a Claude Code plugin with 52 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes llm-output-schema-constraints, prompt-file-provider-options, validate. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is output?
- The open-source TypeScript framework for building AI workflows and agents. Designed for Claude Code — describe what you want, Claude builds it, with all the best practices already in place. One framework.
- How do I install output?
- Run these in Claude Code: /plugin marketplace add growthxai/output then /plugin install outputai@outputai. Then prompt normally.
- Does output auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is output free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.