How do I install the Examples skill?

Run npx skillmds@latest add agents-store/examples-22 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Examples safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Examples?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Examples free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Examples?

agents-store (@agents-store) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Examples by agents-store — Agent Skill

Name: Examples
Author: agents-store

Examples

Trigger.dev code examples, end-to-end workflow templates, MCP tool usage patterns, and scenario walkthroughs. Use when the user asks for "trigger.dev examples", "task templates", "MCP tool patterns", "trigger.dev workflow examples", or needs reference implementations.

agents-store 53735cd 6 files · 18.0 KB Updated Sep 17, 2026

File contents

Examples & Patterns

Ready-to-use examples and complete workflow scenarios.

MCP Tool Examples

File	Description
@references/mcp/tool-patterns.md	Common MCP tool call patterns and workflows

Scenario Walkthroughs

File	Description
@references/scenarios/webhook-processor.md	Complete webhook processing task with queue and retry
@references/scenarios/ai-pipeline.md	AI agent pipeline with chaining, tools, and streaming
@references/scenarios/cron-data-sync.md	Scheduled data sync with batch processing

Quick Reference Patterns

Initialize New Project

1. list_orgs() → pick org
2. initialize_project(orgParam, projectName, cwd)
3. get_current_worker(environment="dev") → verify

Trigger and Monitor

1. get_current_worker() → find task + schema
2. trigger_task(taskId, payload) → get run ID
3. wait_for_run_to_complete(runId) → get result

Debug Failures

1. list_runs(status="FAILED", period="1d")
2. get_run_details(runId) → read trace + span IDs
3. get_span_details(runId, spanId) → AI enrichment (model, tokens, cost) if GenAI span
4. Fix code, redeploy
5. trigger_task(taskId, payload) → retry

Deploy to Production

1. deploy(environment="staging") → test first
2. trigger_task(environment="staging") → verify
3. deploy(environment="prod") → ship it
4. list_deploys(environment="prod", limit=1) → confirm

Run Dev Server from an Agent

1. start_dev_server(configPath?)             → launches `trigger dev` in background
2. dev_server_status(lines=50)               → poll until status="ready"
3. get_current_worker(environment="dev")     → task list
4. trigger_task(...)                         → test task
5. stop_dev_server()                         → tear down

Analyze Failures with TRQL

1. get_query_schema(table="runs")
2. query({
     query: "SELECT task_identifier, count() AS n
             FROM runs
             WHERE status = 'Failed'
             GROUP BY task_identifier
             ORDER BY n DESC LIMIT 10",
     period: "7d"
   })

LLM Cost Breakdown

1. get_query_schema(table="llm_metrics")
2. query({
     query: "SELECT model, sum(cost_usd) AS usd
             FROM llm_metrics
             GROUP BY model
             ORDER BY usd DESC",
     period: "30d"
   })

Switch Profile Mid-Session

1. whoami()                           → current profile + API URL
2. list_profiles()                    → available profiles
3. switch_profile("self-hosted-prod") → subsequent tool calls use new profile

Prompt Override Hotfix

1. list_prompts(environment="prod")                              → find slug
2. get_prompt_versions(slug, environment="prod")                 → see current/override state
3. create_prompt_override(slug, textContent, commitMessage)      → apply hotfix
4. (iterate) update_prompt_override(slug, textContent)
5. remove_prompt_override(slug)                                  → revert after code fix deploys

---name: examples-22description: Trigger.dev code examples, end-to-end workflow templates, MCP tool usage patterns, and scenario walkthroughs. Use when the user asks for "trigger.dev examples", "task templates", "MCP tool patterns", "trigger.dev workflow examples", or needs reference implementations.---# Examples & PatternsReady-to-use examples and complete workflow scenarios.## MCP Tool Examples| File | Description ||------|-------------|| @references/mcp/tool-patterns.md | Common MCP tool call patterns and workflows |## Scenario Walkthroughs| File | Description ||------|-------------|| @references/scenarios/webhook-processor.md | Complete webhook processing task with queue and retry || @references/scenarios/ai-pipeline.md | AI agent pipeline with chaining, tools, and streaming || @references/scenarios/cron-data-sync.md | Scheduled data sync with batch processing |## Quick Reference Patterns### Initialize New Project```1. list_orgs() → pick org2. initialize_project(orgParam, projectName, cwd)3. get_current_worker(environment="dev") → verify```### Trigger and Monitor```1. get_current_worker() → find task + schema2. trigger_task(taskId, payload) → get run ID3. wait_for_run_to_complete(runId) → get result```### Debug Failures```1. list_runs(status="FAILED", period="1d")2. get_run_details(runId) → read trace + span IDs3. get_span_details(runId, spanId) → AI enrichment (model, tokens, cost) if GenAI span4. Fix code, redeploy5. trigger_task(taskId, payload) → retry```### Deploy to Production```1. deploy(environment="staging") → test first2. trigger_task(environment="staging") → verify3. deploy(environment="prod") → ship it4. list_deploys(environment="prod", limit=1) → confirm```### Run Dev Server from an Agent```1. start_dev_server(configPath?) → launches `trigger dev` in background2. dev_server_status(lines=50) → poll until status="ready"3. get_current_worker(environment="dev") → task list4. trigger_task(...) → test task5. stop_dev_server() → tear down```### Analyze Failures with TRQL```1. get_query_schema(table="runs")2. query({ query: "SELECT task_identifier, count() AS n FROM runs WHERE status = 'Failed' GROUP BY task_identifier ORDER BY n DESC LIMIT 10", period: "7d" })```### LLM Cost Breakdown```1. get_query_schema(table="llm_metrics")2. query({ query: "SELECT model, sum(cost_usd) AS usd FROM llm_metrics GROUP BY model ORDER BY usd DESC", period: "30d" })```### Switch Profile Mid-Session```1. whoami() → current profile + API URL2. list_profiles() → available profiles3. switch_profile("self-hosted-prod") → subsequent tool calls use new profile```### Prompt Override Hotfix```1. list_prompts(environment="prod") → find slug2. get_prompt_versions(slug, environment="prod") → see current/override state3. create_prompt_override(slug, textContent, commitMessage) → apply hotfix4. (iterate) update_prompt_override(slug, textContent)5. remove_prompt_override(slug) → revert after code fix deploys```

Frequently asked questions