Merge research and content skills into kagi-usage, add Claude Code plugin - #146
Conversation
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (7)
🚧 Files skipped from review as they are similar to previous changes (7)
📝 WalkthroughWalkthroughThe PR adds Claude plugin manifests, introduces ChangesClaude skill registry and guidance
Estimated code review effort: 3 (Moderate) | ~20 minutes 🚥 Pre-merge checks | ✅ 6✅ Passed checks (6 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: a2ff493e4b
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
![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
🧹 Nitpick comments (1)
.claude-plugin/plugin.json (1)
4-4: 🩺 Stability & Availability | 🔵 Trivial | ⚡ Quick winKeep a single authoritative plugin version.
Both manifests declare the plugin version. Claude Code prioritizes
plugin.json, so a future bump made only in the marketplace entry can be ignored and prevent users from receiving updates. The official documentation recommends avoiding duplicate version declarations. (code.claude.com)
.claude-plugin/plugin.json#L4-L4: retain this as the authoritative plugin version and bump it for releases..claude-plugin/marketplace.json#L16-L16: remove the duplicate plugin-levelversionfield; keepmetadata.versionfor the marketplace itself.Proposed fix
"source": "./", "description": "Kagi CLI skills for research, page content, Assistant, monitoring, and account configuration.", - "version": "0.15.0", "author": {🤖 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 @.claude-plugin/plugin.json at line 4, Keep the version in .claude-plugin/plugin.json as the authoritative plugin version and continue bumping it for releases; remove only the duplicate plugin-level version field from .claude-plugin/marketplace.json while preserving marketplace metadata.version.
🤖 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 `@skills/kagi-usage/SKILL.md`:
- Around line 44-46: Update the authentication description near the Search API
notes to replace the broad “search filters require session auth” wording with
“session-only search controls,” matching the terminology used around the
relevant quick, subscriber search, and filter behavior. Keep the documented V1
API filters usable with KAGI_API_KEY.
---
Nitpick comments:
In @.claude-plugin/plugin.json:
- Line 4: Keep the version in .claude-plugin/plugin.json as the authoritative
plugin version and continue bumping it for releases; remove only the duplicate
plugin-level version field from .claude-plugin/marketplace.json while preserving
marketplace metadata.version.
🪄 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: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro Plus
Run ID: fa1eab38-e671-4ea1-8b31-503343c61ca0
📒 Files selected for processing (14)
.claude-plugin/marketplace.json.claude-plugin/plugin.jsonREADME.mddocs/commands/skills.mdxskills/kagi-account-config/SKILL.mdskills/kagi-assistant/SKILL.mdskills/kagi-content/SKILL.mdskills/kagi-monitoring/SKILL.mdskills/kagi-research/SKILL.mdskills/kagi-usage/SKILL.mdskills/kagi/SKILL.mdsrc/agent.rssrc/cli.rstests/integration-cli.rs
💤 Files with no reviewable changes (3)
- skills/kagi-research/SKILL.md
- skills/kagi-content/SKILL.md
- skills/kagi/SKILL.md
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
|
@greptileai review |
|
@codex review |
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 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 `@src/agent.rs`:
- Around line 11-13: Preserve the legacy aliases kagi, kagi-research, and
kagi-content while keeping kagi-usage as the sole canonical registry entry.
Update skill_source and skill_locator to canonicalize those inputs before
exact-name lookup, so aliases resolve to the kagi-usage content and path. Add
regression tests covering both content retrieval and locator/path lookup for
each alias.
🪄 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: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro Plus
Run ID: 514f4852-4988-497b-8e0c-0b97e53fee04
📒 Files selected for processing (7)
CHANGELOG.mddocs/commands/skills.mdxskills/kagi-ai/SKILL.mdskills/kagi-assistant/SKILL.mdskills/kagi-usage/SKILL.mdsrc/agent.rstests/integration-cli.rs
🚧 Files skipped from review as they are similar to previous changes (3)
- docs/commands/skills.mdx
- skills/kagi-assistant/SKILL.md
- tests/integration-cli.rs
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: a4e5690cfa
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
a4e5690 to
895a789
Compare
|
PR title or description contains an excluded keyword. |
Embed a focused AI allowance guide, wire it into routing and docs, and cover it in registry tests. Fix Claude skill frontmatter validation and format the updated CLI test.
2 participants
Summary
kagi-usageguidekagi-aifor spending Assistant allowance on reasoning, coding, research, file analysis, and structured outputkagi-assistant,kagi-monitoring, andkagi-account-configfocused on their own workflowsVerification
cargo fmt --checkcargo clippy --all-targets --all-features -- -D warningscargo check --workspace --all-targets --lockedcargo test --workspace --all-targets --locked(273 passed, 13 ignored)cargo auditclaude plugin validate --strict .claude-plugin/plugin.jsonclaude plugin validate --strict .claude-plugin/marketplace.jsonquick_validate.py skills/kagi-aiDocs
docs/commands/skills.mdxlists the canonical skill setAuth / Secrets
Greptile Summary
Consolidates Kagi’s embedded agent guidance and adds Claude Code plugin packaging.
kagi-usageskill.kagi-aiguidance for paid Assistant workflows.Confidence Score: 5/5
The PR appears safe to merge because no new blocking failure eligible for this follow-up review remains.
No blocking failure remains within the scope of the displayed previous review thread.
What T-Rex did
Important Files Changed
kagi-usageand adds the newkagi-aiskill.Reviews (2): Last reviewed commit: "feat(skills): add cost-aware kagi-ai gui..." | Re-trigger Greptile
Summary by CodeRabbit
New Features
kagi-usageguidance for search and page workflows.kagi-aiguidance for AI allowance management, model selection, files, and structured outputs.Documentation