Conversation
Rewrote all core docs pages (index, installation, quickstart, rest-api, mcp-server, python-client) with problem/solution framing, progressive code examples, and conversational tone. Updated OpenAPI descriptions and api.html meta tags to match. 366 additions vs 722 deletions.
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
📝 WalkthroughWalkthroughComprehensive rewrite of user-facing documentation: streamlines copy, reorganizes quick-start and installation flows, converts technical API/reference pages into concise, example-driven guides, and updates API metadata/OpenAPI descriptions for clearer, action-oriented wording. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ 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}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Fix all issues with AI agents
In `@docs/fumadocs/content/docs/mcp-server.mdx`:
- Around line 8-10: Replace the hard-coded "15,000+" skill count strings in the
MCP docs with a non-specific phrase (e.g., "thousands of skills") or remove the
numeric claim; locate the two occurrences of the literal "15,000+" in the MCP
documentation text (the sentences mentioning the `@skillkit/mcp` package and the
agent "direct line") and update them to a softer, non-stale wording (or
implement a dynamic insertion that pulls the current catalog size if you prefer
a precise number).
- Around line 54-67: The "Browse categories" tool description is missing the
tool name; update the "Browse categories" section (near other tools like
search_skills, get_skill, recommend_skills) to explicitly state that the agent
calls list_categories and returns all categories with counts—e.g., add a
sentence like "The agent calls list_categories and returns all categories with
counts" under the "Browse categories" heading so users can reference the
list_categories tool by name.
Replace hard-coded "15,000+" with non-specific wording and explicitly name the list_categories tool in the Browse categories section.
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
| class Category: | ||
| name: str | ||
| count: int | ||
| Skill(name, source, description, tags, category, content, score) |
There was a problem hiding this comment.
🟡 Python client documentation lists non-existent score field and omits actual fields
The Python client documentation incorrectly describes the Skill model fields.
Click to expand
Documentation vs Actual Model
The documentation at line 88 states:
Skill(name, source, description, tags, category, content, score)But the actual Skill model in clients/python/skillkit/models.py:5-14 is:
class Skill(BaseModel):
name: str
description: Optional[str] = None
source: str
repo: Optional[str] = None
tags: Optional[list[str]] = None
category: Optional[str] = None
content: Optional[str] = None
stars: Optional[int] = None
installs: Optional[int] = NoneIssues
scoredoesn't exist - The documentation listsscoreas a field, but the actual model has no such field. Developers trying to accessskill.scorewill get anAttributeError.- Missing fields - The documentation omits
repo,stars, andinstallswhich are actual fields on the model.
Impact
Developers following this documentation will write code expecting a score attribute that doesn't exist, leading to runtime errors.
Recommendation: Update line 88 to accurately reflect the model: Skill(name, source, description, tags, category, content, repo, stars, installs)
Was this helpful? React with 👍 or 👎 to provide feedback.
1 participant
Summary
Pages rewritten
Test plan
npx next buildpasses for fumadocs (26 pages generated)npx vite buildpasses for skillkit websiteSummary by CodeRabbit