docs: new tutorial for AI SDK#175
Draft
bguiz wants to merge 2 commits into
Draft
Conversation
Signed-off-by: Brendan Graetz <bguiz@users.noreply.github.com>
Contributor
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Workflows to automatically generate PRs for you. |
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (2)
✅ Files skipped from review due to trivial changes (2)
📝 WalkthroughWalkthroughThis PR adds a new AI SDK tutorial page for ChangesAI SDK Documentation
Estimated code review effort: 2 (Simple) | ~10 minutes Sequence Diagram(s)sequenceDiagram
participant User
participant AInjCLI
participant Harness
participant DocsMCPServer
participant MainMCPServer
User->>AInjCLI: npm install -g `@bguiz/ainj`
User->>AInjCLI: ainj install
AInjCLI-->>User: configure MCP entries and skills
User->>AInjCLI: ainj status / ainj skills
User->>Harness: invoke agent skill
Harness->>AInjCLI: run skill via CLI
User->>AInjCLI: ainj mcp docs http
AInjCLI->>DocsMCPServer: start docs MCP server
User->>AInjCLI: ainj mcp main http
AInjCLI->>MainMCPServer: start main MCP server
Possibly related PRs
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
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}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
.gitbook/developers-ai/ai-sdk.mdx (1)
27-33: 📐 Maintainability & Code Quality | 🔵 Trivial | 💤 Low valuePinned tool versions will go stale quickly.
Exact minimums for fast-moving tools like Codex (
0.139.0) and Claude Code (2.1.81) will likely be outdated soon after publishing, requiring frequent doc updates. Consider phrasing these as "check the latest version" with a link, or periodically re-verify these pins as part of doc maintenance.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In @.gitbook/developers-ai/ai-sdk.mdx around lines 27 - 33, Pinned minimum versions for fast-moving tools in the ai-sdk docs are likely to go stale, so update the table entries for Codex and Claude Code to avoid hardcoding exact versions unless you plan to maintain them regularly. Keep the rest of the version-check guidance intact, but change the wording in this section to point readers to the latest version or otherwise clearly mark these pins as maintenance items. Use the existing tool table in ai-sdk.mdx and the Codex/Claude Code rows as the place to update.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In @.gitbook/developers-ai/index.mdx:
- Around line 41-67: The new bullet list in index.mdx has a few grammar typos
that should be fixed in the relevant bullet entries: in the Agent Skills
paragraph change “may be use” to “may be used”, in the sentence describing
agents/subagents remove the duplicated “are are”, and in the AI Engineering
Harnesses description change “The operate” to “They operate”. Keep the
surrounding wording and structure intact while correcting these phrases.
---
Nitpick comments:
In @.gitbook/developers-ai/ai-sdk.mdx:
- Around line 27-33: Pinned minimum versions for fast-moving tools in the ai-sdk
docs are likely to go stale, so update the table entries for Codex and Claude
Code to avoid hardcoding exact versions unless you plan to maintain them
regularly. Keep the rest of the version-check guidance intact, but change the
wording in this section to point readers to the latest version or otherwise
clearly mark these pins as maintenance items. Use the existing tool table in
ai-sdk.mdx and the Codex/Claude Code rows as the place to update.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: 5715ffce-7be2-4603-997b-006182aa2444
📒 Files selected for processing (3)
.gitbook/developers-ai/ai-sdk.mdx.gitbook/developers-ai/index.mdx.gitbook/docs.json
Comment on lines
41
to
67
| Note that even when these are not adapted for use by LLMs, | ||
| agent skills may be use to provide thin wrappers around them. | ||
| - **MCP** - | ||
| Model-Context-Protocol (MCP) is a protocol designed for discovery and calling of tools by LLMs. | ||
| They are designed to standardize the way for different LLMs and LLM providers to invoke tools. | ||
| Previously each LLM or LLM provider had competing standards/ protocols for doing so. | ||
| - **Skills** - | ||
| These are markdown files that optionally reference supporting resources, tools, MCP servers and others. | ||
| They are designed specifically to work with AI engineering harnesses (but can be used in other contexts). | ||
| - **Agent Skills** - | ||
| These are markdown files that primarily include a detailed repeatable prompt. | ||
| They optionally reference supporting resources, tools, MCP servers and others. | ||
| They are designed specifically to work with AI engineering harnesses, | ||
| but can be used in other contexts too. | ||
| They can be recursive, for example a skill can reference other skills. | ||
| These are sometimes also referred to as "workflows", "subagents", and "agents". | ||
| In this context, workflows are usually a set of skills with a defined order; | ||
| and agents/ subagents are are sets of workflows and skills with no specified order, | ||
| where the LLM is given agency over which ones to use and in what order. | ||
| Note that the term "agents" is overused, with multiple definitions, | ||
| so the above is specific to this context. | ||
| - **AI engineering IDEs** - | ||
| so the above definition is specific to this context. | ||
| - **AI Engineering IDEs** - | ||
| These are either dedicated IDEs or plugins within IDEs that allow you to prompt LLMs, | ||
| including execution of tool calls or MCPs, | ||
| and use their output to work on the code base that is open within the IDE. | ||
| Popular ones include: Roo, Cline, and Cursor. | ||
| - **AI engineering Harnesses** - | ||
| - **AI Engineering Harnesses** - | ||
| These are command line interfaces (CLIs) or terminal user interfaces (TUIs) that are designed around | ||
| invoking LLMs for coding tasks. | ||
| The operate directly on the file system, and often come with baked-in optimizations and utilities for engineering tasks. |
Contributor
There was a problem hiding this comment.
🎯 Functional Correctness | 🟡 Minor | ⚡ Quick win
Grammar errors in the new bullet list.
Several typos in this section:
- Line 42: "may be use" → "may be used"
- Line 55: "are are sets" → duplicated word, should be "are sets"
- Line 67: "The operate" → "They operate"
✏️ Proposed grammar fixes
- agent skills may be use to provide thin wrappers around them.
+ agent skills may be used to provide thin wrappers around them.- and agents/ subagents are are sets of workflows and skills with no specified order,
+ and agents/ subagents are sets of workflows and skills with no specified order,- The operate directly on the file system, and often come with baked-in optimizations and utilities for engineering tasks.
+ They operate directly on the file system, and often come with baked-in optimizations and utilities for engineering tasks.📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| Note that even when these are not adapted for use by LLMs, | |
| agent skills may be use to provide thin wrappers around them. | |
| - **MCP** - | |
| Model-Context-Protocol (MCP) is a protocol designed for discovery and calling of tools by LLMs. | |
| They are designed to standardize the way for different LLMs and LLM providers to invoke tools. | |
| Previously each LLM or LLM provider had competing standards/ protocols for doing so. | |
| - **Skills** - | |
| These are markdown files that optionally reference supporting resources, tools, MCP servers and others. | |
| They are designed specifically to work with AI engineering harnesses (but can be used in other contexts). | |
| - **Agent Skills** - | |
| These are markdown files that primarily include a detailed repeatable prompt. | |
| They optionally reference supporting resources, tools, MCP servers and others. | |
| They are designed specifically to work with AI engineering harnesses, | |
| but can be used in other contexts too. | |
| They can be recursive, for example a skill can reference other skills. | |
| These are sometimes also referred to as "workflows", "subagents", and "agents". | |
| In this context, workflows are usually a set of skills with a defined order; | |
| and agents/ subagents are are sets of workflows and skills with no specified order, | |
| where the LLM is given agency over which ones to use and in what order. | |
| Note that the term "agents" is overused, with multiple definitions, | |
| so the above is specific to this context. | |
| - **AI engineering IDEs** - | |
| so the above definition is specific to this context. | |
| - **AI Engineering IDEs** - | |
| These are either dedicated IDEs or plugins within IDEs that allow you to prompt LLMs, | |
| including execution of tool calls or MCPs, | |
| and use their output to work on the code base that is open within the IDE. | |
| Popular ones include: Roo, Cline, and Cursor. | |
| - **AI engineering Harnesses** - | |
| - **AI Engineering Harnesses** - | |
| These are command line interfaces (CLIs) or terminal user interfaces (TUIs) that are designed around | |
| invoking LLMs for coding tasks. | |
| The operate directly on the file system, and often come with baked-in optimizations and utilities for engineering tasks. | |
| Note that even when these are not adapted for use by LLMs, | |
| agent skills may be used to provide thin wrappers around them. | |
| - **MCP** - | |
| Model-Context-Protocol (MCP) is a protocol designed for discovery and calling of tools by LLMs. | |
| They are designed to standardize the way for different LLMs and LLM providers to invoke tools. | |
| Previously each LLM or LLM provider had competing standards/ protocols for doing so. | |
| - **Agent Skills** - | |
| These are markdown files that primarily include a detailed repeatable prompt. | |
| They optionally reference supporting resources, tools, MCP servers and others. | |
| They are designed specifically to work with AI engineering harnesses, | |
| but can be used in other contexts too. | |
| They can be recursive, for example a skill can reference other skills. | |
| These are sometimes also referred to as "workflows", "subagents", and "agents". | |
| In this context, workflows are usually a set of skills with a defined order; | |
| and agents/ subagents are sets of workflows and skills with no specified order, | |
| where the LLM is given agency over which ones to use and in what order. | |
| Note that the term "agents" is overused, with multiple definitions, | |
| so the above definition is specific to this context. | |
| - **AI Engineering IDEs** - | |
| These are either dedicated IDEs or plugins within IDEs that allow you to prompt LLMs, | |
| including execution of tool calls or MCPs, | |
| and use their output to work on the code base that is open within the IDE. | |
| Popular ones include: Roo, Cline, and Cursor. | |
| - **AI Engineering Harnesses** - | |
| These are command line interfaces (CLIs) or terminal user interfaces (TUIs) that are designed around | |
| invoking LLMs for coding tasks. | |
| They operate directly on the file system, and often come with baked-in optimizations and utilities for engineering tasks. |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In @.gitbook/developers-ai/index.mdx around lines 41 - 67, The new bullet list
in index.mdx has a few grammar typos that should be fixed in the relevant bullet
entries: in the Agent Skills paragraph change “may be use” to “may be used”, in
the sentence describing agents/subagents remove the duplicated “are are”, and in
the AI Engineering Harnesses description change “The operate” to “They operate”.
Keep the surrounding wording and structure intact while correcting these
phrases.
Contributor
There was a problem hiding this comment.
Pull request overview
Adds a new “AI SDK” tutorial to the AI Developers docs, updates the AI Developers overview copy to reflect a broader set of generative AI tooling, and exposes the new page in the GitBook navigation.
Changes:
- Added a new
AI SDKtutorial page describing installation and usage of@bguiz/ainj(CLI, MCP servers, agent skills). - Expanded the AI Developers overview with updated taxonomy/definitions and an “AI SDK” section linking to the new tutorial.
- Updated GitBook navigation to include the new
developers-ai/ai-sdkpage.
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 10 comments.
| File | Description |
|---|---|
.gitbook/docs.json |
Adds the new AI SDK page to the “AI Developers” navigation group. |
.gitbook/developers-ai/index.mdx |
Updates overview content and adds a new “AI SDK” section linking to the tutorial. |
.gitbook/developers-ai/ai-sdk.mdx |
New end-to-end tutorial for installing/configuring AInj and using CLI, skills, and MCP servers. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+88
to
+89
| Use the [Injective AI SDK](/developers-ai/ai-sdk/) | ||
| which provides you agent skills, CLI, MCP servers - all in a single install. |
Comment on lines
+125
to
+126
| Note that your harness should provide tab-to-auto-complete your skills names, | ||
| e.g. when you type `$inj` (Codex) or `/inj` (Claude Code) there should be several injective-related |
ChuhanJin
reviewed
Jul 1, 2026
Signed-off-by: Brendan Graetz <bguiz@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary by CodeRabbit