Add building with ai/skills pages and updated intro #2962
Conversation
|
WalkthroughAdds a new documentation group "Building with AI" and page Estimated code review effort🎯 4 (Complex) | ⏱️ ~45 minutes 🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 inconclusive)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. 📜 Recent review detailsConfiguration used: Repository UI Review profile: CHILL Plan: Pro 📒 Files selected for processing (1)
🧰 Additional context used🧠 Learnings (2)📚 Learning: 2025-11-27T16:27:35.304ZApplied to files:
📚 Learning: 2025-11-27T16:27:35.304ZApplied to files:
🔇 Additional comments (16)
✏️ Tip: You can disable this entire section by setting Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In `@docs/skills.mdx`:
- Around line 10-15: The installation paths listed are inaccurate for some
tools; update the docs around the "SKILL.md" and "npx skills add
triggerdotdev/skills" section to show correct destination directories (use
~/.cursor/skills/ for Cursor skills, ~/.copilot/skills/ for GitHub Copilot
integration, and keep .claude/skills/ for Claude) or add a short note explaining
when alternative paths are intentionally shown; edit the text that currently
lists `.cursor/rules/` and `.github/copilot-instructions/` to the correct paths
or clarify the multiple installation methods so the CLI behavior is accurately
described.
📜 Review details
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
⛔ Files ignored due to path filters (1)
docs/images/intro-ai.jpgis excluded by!**/*.jpg
📒 Files selected for processing (4)
docs/building-with-ai.mdxdocs/docs.jsondocs/introduction.mdxdocs/skills.mdx
🧰 Additional context used
📓 Path-based instructions (1)
**/*.{js,ts,jsx,tsx,json,md,yaml,yml}
📄 CodeRabbit inference engine (AGENTS.md)
Format code using Prettier before committing
Files:
docs/docs.json
🧠 Learnings (1)
📚 Learning: 2026-01-15T11:50:06.067Z
Learnt from: CR
Repo: triggerdotdev/trigger.dev PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-01-15T11:50:06.067Z
Learning: Keep the `.claude/skills/trigger-dev-tasks/` skill in sync with the latest rules version when SDK features change
Applied to files:
docs/skills.mdx
🔇 Additional comments (3)
docs/building-with-ai.mdx (1)
1-24: Solid overview page and calls-to-action.Concise copy and clear entry points to MCP Server and Skills.
docs/docs.json (1)
46-55: Navigation update looks coherent.The new “Building with AI” group cleanly organizes the new overview, MCP Server, and Skills pages.
docs/introduction.mdx (1)
19-20: Image assetintro-ai.jpgexists and is correctly referenced. No action needed.
✏️ Tip: You can disable this entire section by setting review_details to false in your review settings.
Update example paths to use correct skill directories: - .cursor/skills/ (not .cursor/rules/) - .github/skills/ (not .github/copilot-instructions/)
Review CompleteYour review story is ready! Comment !reviewfast on this PR to re-generate the story. |
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In `@docs/skills.mdx`:
- Line 10: Update the sentence in docs/skills.mdx to clarify that a "skill" is a
directory that contains a SKILL.md file (not a standalone file): reword the line
"Skills install as `SKILL.md` files..." to something like "Skills are installed
as directories that contain a `SKILL.md` file; each `SKILL.md` includes YAML
frontmatter (name, description) and markdown instructions..." to clearly
distinguish the skill (directory) from the `SKILL.md` file it contains.
📜 Review details
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
docs/skills.mdx
🧰 Additional context used
🧠 Learnings (1)
📚 Learning: 2026-01-15T11:50:06.067Z
Learnt from: CR
Repo: triggerdotdev/trigger.dev PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-01-15T11:50:06.067Z
Learning: Keep the `.claude/skills/trigger-dev-tasks/` skill in sync with the latest rules version when SDK features change
Applied to files:
docs/skills.mdx
🪛 LanguageTool
docs/skills.mdx
[uncategorized] ~14-~14: The official name of this software platform is spelled with a capital “H”.
Context: ..., .claude/skills/, .cursor/skills/, .github/skills/, etc. ```bash npx skills add ...
(GITHUB)
✏️ Tip: You can disable this entire section by setting review_details to false in your review settings.
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In `@docs/skills.mdx`:
- Around line 24-36: Update the broken "View all →" link in docs/skills.mdx:
locate the markdown line with the "View all →" anchor and replace the invalid
URL (https://skills.sh/docs/supported-agents) with the correct, live URL for the
supported agents page (e.g., https://skills.sh/supported-agents or the project's
canonical supported-agents docs path) so the link returns 200.
📜 Review details
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
docs/skills.mdx
🧰 Additional context used
🧠 Learnings (1)
📚 Learning: 2026-01-15T11:50:06.067Z
Learnt from: CR
Repo: triggerdotdev/trigger.dev PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-01-15T11:50:06.067Z
Learning: Keep the `.claude/skills/trigger-dev-tasks/` skill in sync with the latest rules version when SDK features change
Applied to files:
docs/skills.mdx
🔇 Additional comments (4)
docs/skills.mdx (4)
1-10: LGTM on the introduction and skills explanation.The frontmatter is well-structured, and the explanation of what agent skills are is clear. Line 10 correctly describes skills as directories containing a
SKILL.mdfile, which addresses the previous review feedback.
38-62: LGTM on the available skills section.The code examples are clear, and the skills table provides a helpful overview of what each skill covers. The recommendation to install
trigger-tasksas a default is sensible guidance for new users.
64-79: LGTM on the next steps section.The CardGroup provides logical navigation to related documentation. The mix of internal links (
/mcp-introduction,/tasks/overview,/guides/ai-agents/overview) and the external link toskills.shis appropriate.
20-20: The attribution is accurate—skillsis indeed an open-source CLI created and maintained by Vercel (Vercel Labs), open-sourced at vercel-labs/skills on GitHub.
✏️ Tip: You can disable this entire section by setting review_details to false in your review settings.
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In `@docs/mcp-tools.mdx`:
- Around line 97-103: The description for cancel_run uses "task" but the tool
operates on runs; update the copy in docs for the cancel_run entry so it
consistently uses "run" terminology (e.g., change "Cancel a running or queued
task." to "Cancel a running or queued run."), and verify the example lines under
cancel_run still match the updated terminology; locate the cancel_run section in
the doc and change the wording there.
📜 Review details
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (4)
docs/mcp-agent-rules.mdxdocs/mcp-introduction.mdxdocs/mcp-tools.mdxdocs/skills.mdx
💤 Files with no reviewable changes (2)
- docs/mcp-agent-rules.mdx
- docs/mcp-introduction.mdx
🚧 Files skipped from review as they are similar to previous changes (1)
- docs/skills.mdx
🔇 Additional comments (4)
docs/mcp-tools.mdx (4)
1-17: LGTM - Clean structure with practical examples.The updated description and example-driven format for
search_docsis clear and user-friendly. The italicized natural language prompts effectively demonstrate how users can interact with the tool.
18-50: LGTM - Project Management Tools section is well organized.Consistent formatting across
list_orgs,list_projects,create_project_in_org, andinitialize_project. Each tool has a concise description followed by practical example prompts.
52-69: LGTM - Task Management Tools section is comprehensive.The
get_current_workerdescription clearly explains its purpose, andtrigger_taskappropriately mentions the available options (delay, tags, retries, machine size, TTL, idempotency key) without being overly verbose.
105-132: LGTM - Deployment Tools section and warning callout are clear.The
deploy,list_deploys, andlist_preview_branchessections follow the established pattern. The warning callout about--dev-onlymode is appropriately placed and informative.
✏️ Tip: You can disable this entire section by setting review_details to false in your review settings.
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Fix all issues with AI agents
In `@docs/mcp-tools.mdx`:
- Around line 131-133: Update the warning Callout text to also mention
list_deploys as unavailable under the --dev-only flag: locate the Callout
component containing "The deploy and list_preview_branches tools are not
available when the MCP server is running with the `--dev-only` flag." and change
it to read "The deploy, list_deploys, and list_preview_branches tools are not
available when the MCP server is running with the `--dev-only` flag."
- Around line 54-57: The current doc entry for get_current_worker incorrectly
says it "Get all tasks registered in a project along with their payload
schemas"; update the description for get_current_worker to match actual tool
behavior by replacing that sentence with the official description indicating it
returns the current worker version, SDK version, and task schemas (including any
task registry info), and ensure the summary text and any surrounding docs that
mention get_current_worker reflect these returned fields.
📜 Review details
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
docs/mcp-tools.mdxdocs/skills.mdx
🚧 Files skipped from review as they are similar to previous changes (1)
- docs/skills.mdx
✏️ Tip: You can disable this entire section by setting review_details to false in your review settings.
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
docs/mcp-introduction.mdx (1)
300-349: Update--scopeoption: onlyuserandprojectare supported, notlocal.The documentation lists
--scopeas supporting "user, project, or local", but the CLI help shows it only supports "user or project". Additionally, the--clientoption should document the supported clients (claude-code, cursor, vscode, zed, windsurf, gemini-cli, crush, cline, openai-codex, opencode, amp, ruler) for clarity. The--log-leveloption is also missing the default value ("log") and the note that it does not affect task log levels.
🤖 Fix all issues with AI agents
In `@docs/mcp-introduction.mdx`:
- Around line 28-295: The AMP config block is wrong — remove the nested "amp"
object and instead specify the top-level setting key "amp.mcpServers" with the
trigger server entry (fix the AMP snippet currently showing
~/.config/amp/settings.json and the nested amp object); also update the Crush
section text to state the file priority order explicitly as ".crush.json →
crush.json → $HOME/.config/crush/crush.json" and ensure the Crush config
examples reflect the highest-priority filename or mention the priority. Locate
and edit the AMP block and the Crush block in the Tabs (symbols: the AMP Tab
title and the Crush Tab title) to apply these changes.
🧹 Nitpick comments (2)
docs/snippets/step-cli-init.mdx (1)
23-37: Tighten the MCP tip placement and example-task wording.The tip currently splits the lead-in from the list, and the example-task instruction is repeated. Consider moving the tip above the lead-in and consolidating the “Hello World” guidance.
✂️ Suggested wording/flow tweak
-It will do a few things: - -<Tip title="MCP Server"> - Our [Trigger.dev MCP server](/mcp-introduction) gives your AI assistant direct access to Trigger.dev tools; search docs, trigger tasks, deploy projects, and monitor runs. We recommend installing it for the best developer experience. -</Tip> +<Tip title="MCP Server"> + Our [Trigger.dev MCP server](/mcp-introduction) gives your AI assistant direct access to Trigger.dev tools; search docs, trigger tasks, deploy projects, and monitor runs. We recommend installing it for the best developer experience. +</Tip> + +It will do a few things: ... -5. Ask where you'd like to create the `/trigger` directory and create it with an example task. +5. Ask where you'd like to create the `/trigger` directory and (optionally) install the "Hello World" example task. 6. Create a `trigger.config.ts` file in the root of your project. -Install the "Hello World" example task when prompted. We'll use this task to test the setup. +If you opt in, choose the "Hello World" example task so we can test the setup.docs/quick-start.mdx (1)
16-19: Clarify the self-host onboarding path.The sentence implies the cloud onboarding flow applies to self-hosting. Consider splitting it to avoid confusion.
✏️ Suggested wording tweak
-Sign up at [Trigger.dev Cloud](https://cloud.trigger.dev) (or [self-host](/open-source-self-hosting)). The onboarding flow will guide you through creating your first organization and project. +Sign up at [Trigger.dev Cloud](https://cloud.trigger.dev). The cloud onboarding flow will guide you through creating your first organization and project. +If you’re [self-hosting](/open-source-self-hosting), follow the self-hosting setup to create your first organization and project.
📜 Review details
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (4)
docs/building-with-ai.mdxdocs/mcp-introduction.mdxdocs/quick-start.mdxdocs/snippets/step-cli-init.mdx
🚧 Files skipped from review as they are similar to previous changes (1)
- docs/building-with-ai.mdx
🧰 Additional context used
🧠 Learnings (15)
📚 Learning: 2025-11-27T16:27:35.304Z
Learnt from: CR
Repo: triggerdotdev/trigger.dev PR: 0
File: .cursor/rules/writing-tasks.mdc:0-0
Timestamp: 2025-11-27T16:27:35.304Z
Learning: Applies to **/trigger/**/*.{ts,tsx,js,jsx} : Use the `task()` function from `trigger.dev/sdk/v3` to define tasks with id and run properties
Applied to files:
docs/quick-start.mdxdocs/snippets/step-cli-init.mdx
📚 Learning: 2025-11-27T16:27:35.304Z
Learnt from: CR
Repo: triggerdotdev/trigger.dev PR: 0
File: .cursor/rules/writing-tasks.mdc:0-0
Timestamp: 2025-11-27T16:27:35.304Z
Learning: Run `npx trigger.devlatest init` to initialize a Trigger.dev project
Applied to files:
docs/quick-start.mdxdocs/snippets/step-cli-init.mdxdocs/mcp-introduction.mdx
📚 Learning: 2025-11-27T16:27:35.304Z
Learnt from: CR
Repo: triggerdotdev/trigger.dev PR: 0
File: .cursor/rules/writing-tasks.mdc:0-0
Timestamp: 2025-11-27T16:27:35.304Z
Learning: Applies to **/trigger.config.ts : Configure Trigger.dev project in `trigger.config.ts` using `defineConfig()` with project ref and task directories
Applied to files:
docs/quick-start.mdxdocs/snippets/step-cli-init.mdx
📚 Learning: 2025-11-27T16:27:35.304Z
Learnt from: CR
Repo: triggerdotdev/trigger.dev PR: 0
File: .cursor/rules/writing-tasks.mdc:0-0
Timestamp: 2025-11-27T16:27:35.304Z
Learning: Run `npx trigger.devlatest dev` to start the Trigger.dev development server
Applied to files:
docs/quick-start.mdxdocs/snippets/step-cli-init.mdxdocs/mcp-introduction.mdx
📚 Learning: 2025-11-27T16:27:35.304Z
Learnt from: CR
Repo: triggerdotdev/trigger.dev PR: 0
File: .cursor/rules/writing-tasks.mdc:0-0
Timestamp: 2025-11-27T16:27:35.304Z
Learning: Applies to **/trigger/**/*.{ts,tsx,js,jsx} : Use `yourTask.trigger()` to trigger a task from inside another task with specified payload
Applied to files:
docs/quick-start.mdxdocs/snippets/step-cli-init.mdx
📚 Learning: 2025-11-27T16:27:35.304Z
Learnt from: CR
Repo: triggerdotdev/trigger.dev PR: 0
File: .cursor/rules/writing-tasks.mdc:0-0
Timestamp: 2025-11-27T16:27:35.304Z
Learning: Applies to **/trigger/**/*.{ts,tsx,js,jsx} : Attach metadata to task runs using the metadata option when triggering, and access/update it inside runs using metadata functions
Applied to files:
docs/quick-start.mdx
📚 Learning: 2025-11-27T16:27:35.304Z
Learnt from: CR
Repo: triggerdotdev/trigger.dev PR: 0
File: .cursor/rules/writing-tasks.mdc:0-0
Timestamp: 2025-11-27T16:27:35.304Z
Learning: Applies to **/trigger/**/*.{ts,tsx,js,jsx} : Use `yourTask.batchTrigger()` to trigger multiple runs of a task from inside another task
Applied to files:
docs/quick-start.mdx
📚 Learning: 2025-11-27T16:27:35.304Z
Learnt from: CR
Repo: triggerdotdev/trigger.dev PR: 0
File: .cursor/rules/writing-tasks.mdc:0-0
Timestamp: 2025-11-27T16:27:35.304Z
Learning: Applies to **/trigger/**/*.{ts,tsx,js,jsx} : Use `trigger.dev/sdk/v3` for all imports in Trigger.dev tasks
Applied to files:
docs/quick-start.mdxdocs/snippets/step-cli-init.mdx
📚 Learning: 2025-11-27T16:27:35.304Z
Learnt from: CR
Repo: triggerdotdev/trigger.dev PR: 0
File: .cursor/rules/writing-tasks.mdc:0-0
Timestamp: 2025-11-27T16:27:35.304Z
Learning: Applies to **/trigger/**/*.{ts,tsx,js,jsx} : Use logger methods (debug, log, info, warn, error) from `trigger.dev/sdk/v3` for structured logging in tasks
Applied to files:
docs/quick-start.mdxdocs/snippets/step-cli-init.mdx
📚 Learning: 2026-01-15T11:50:06.067Z
Learnt from: CR
Repo: triggerdotdev/trigger.dev PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-01-15T11:50:06.067Z
Learning: Applies to **/*.{ts,tsx} : Every Trigger.dev task must be exported and have a unique `id` property with no timeouts in the run function
Applied to files:
docs/quick-start.mdx
📚 Learning: 2025-11-27T16:26:58.661Z
Learnt from: CR
Repo: triggerdotdev/trigger.dev PR: 0
File: .cursor/rules/webapp.mdc:0-0
Timestamp: 2025-11-27T16:26:58.661Z
Learning: Applies to apps/webapp/**/*.{ts,tsx} : Follow the Remix 2.1.0 and Express server conventions when updating the main trigger.dev webapp
Applied to files:
docs/snippets/step-cli-init.mdx
📚 Learning: 2025-11-27T16:27:35.304Z
Learnt from: CR
Repo: triggerdotdev/trigger.dev PR: 0
File: .cursor/rules/writing-tasks.mdc:0-0
Timestamp: 2025-11-27T16:27:35.304Z
Learning: Applies to **/trigger.config.ts : Use build extensions in trigger.config.ts (additionalFiles, additionalPackages, aptGet, prismaExtension, etc.) to customize the build
Applied to files:
docs/snippets/step-cli-init.mdx
📚 Learning: 2025-11-27T16:27:35.304Z
Learnt from: CR
Repo: triggerdotdev/trigger.dev PR: 0
File: .cursor/rules/writing-tasks.mdc:0-0
Timestamp: 2025-11-27T16:27:35.304Z
Learning: Applies to **/trigger/**/*.{ts,tsx,js,jsx} : Generate example payloads for tasks when possible
Applied to files:
docs/snippets/step-cli-init.mdx
📚 Learning: 2025-11-27T16:27:35.304Z
Learnt from: CR
Repo: triggerdotdev/trigger.dev PR: 0
File: .cursor/rules/writing-tasks.mdc:0-0
Timestamp: 2025-11-27T16:27:35.304Z
Learning: Applies to **/trigger/**/*.{ts,tsx,js,jsx} : Use `tasks.trigger()` with type-only imports to trigger tasks from backend code without importing the task implementation
Applied to files:
docs/snippets/step-cli-init.mdx
📚 Learning: 2025-11-27T16:27:35.304Z
Learnt from: CR
Repo: triggerdotdev/trigger.dev PR: 0
File: .cursor/rules/writing-tasks.mdc:0-0
Timestamp: 2025-11-27T16:27:35.304Z
Learning: Applies to **/trigger/**/*.{ts,tsx,js,jsx} : Use `yourTask.triggerAndWait()` to trigger a task and wait for its result from a parent task
Applied to files:
docs/snippets/step-cli-init.mdx
🔇 Additional comments (3)
docs/mcp-introduction.mdx (1)
20-27: Installer callout reads clean and actionable.Nice simplification with the interactive installer plus the fallback note.
docs/quick-start.mdx (1)
31-43: Building with AI card fits the updated navigation.Nice alignment with the new docs structure and entry points.
docs/snippets/step-cli-init.mdx (1)
9-10: The docs already show the correct command. Official Trigger.dev documentation confirmsnpx trigger.dev@latest initis the current correct syntax for theinitcommand. No changes needed.
✏️ Tip: You can disable this entire section by setting review_details to false in your review settings.
Closes #
✅ Checklist
Testing
[Describe the steps you took to test this change]
Changelog
[Short description of what has changed]
Screenshots
[Screenshots]
💯