docs: add Claude Code skills distribution kit#142
Conversation
📝 WalkthroughWalkthroughAdded a marketing document positioning claude-smart as a local learning layer for Claude Code, Codex, and OpenCode, with reusable messaging and outreach materials for GitHub Discussions, X, comparison content, and owned channels. ChangesMarketing distribution kit
Estimated code review effort: 1 (Trivial) | ~3 minutes 🚥 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}
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
marketing/2026-07-20-claude-code-skills-distribution-kit.md (1)
81-81: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winMake the installation CTA concrete.
Replace “plus Codex/OpenCode variants” with the exact commands and brief restart/prerequisite notes, such as
npx claude-smart install --host codexandnpx claude-smart install --host opencode, so the eventual comparison page is actionable. (github.com)🤖 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 `@marketing/2026-07-20-claude-code-skills-distribution-kit.md` at line 81, Update the “Install CTA” section to replace the vague Codex/OpenCode reference with the exact host-specific commands, including `npx claude-smart install --host codex` and `npx claude-smart install --host opencode`, and add brief prerequisite or restart notes based on the documented installation flow.
🤖 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 `@marketing/2026-07-20-claude-code-skills-distribution-kit.md`:
- Line 9: Revise the claude-smart description to avoid implying that every
correction or successful workflow produces Preferences, Project-specific skills,
and Shared skills together. Update the wording around the referenced overview
sections to use “can produce” or explicitly map project facts, corrections, and
cross-project rollups to their appropriate artifact scopes, consistent with the
canonical contract.
---
Nitpick comments:
In `@marketing/2026-07-20-claude-code-skills-distribution-kit.md`:
- Line 81: Update the “Install CTA” section to replace the vague Codex/OpenCode
reference with the exact host-specific commands, including `npx claude-smart
install --host codex` and `npx claude-smart install --host opencode`, and add
brief prerequisite or restart notes based on the documented installation flow.
🪄 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 Plus
Run ID: c205e178-469f-418f-b23b-b235a6bc69eb
📒 Files selected for processing (1)
marketing/2026-07-20-claude-code-skills-distribution-kit.md
|
|
||
| Primary message: | ||
|
|
||
| > claude-smart turns corrections and successful workflows into durable Preferences, Project-specific skills, and Shared skills that Claude Code, Codex, and OpenCode reuse in future sessions. |
There was a problem hiding this comment.
🎯 Functional Correctness | 🟡 Minor | ⚡ Quick win
Avoid implying every correction or workflow creates all three artifacts.
The canonical contract distinguishes Preferences, Project-specific skills, and Shared skills by scope and derivation. This wording can imply that every event produces all three; use “can produce” or explicitly map project facts, corrections, and cross-project rollups to their respective artifact types. (github.com)
Also applies to: 27-31, 64-64
🤖 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 `@marketing/2026-07-20-claude-code-skills-distribution-kit.md` at line 9,
Revise the claude-smart description to avoid implying that every correction or
successful workflow produces Preferences, Project-specific skills, and Shared
skills together. Update the wording around the referenced overview sections to
use “can produce” or explicitly map project facts, corrections, and
cross-project rollups to their appropriate artifact scopes, consistent with the
canonical contract.
1 participant
Summary
Test Plan / Validation
git diff --cached --checkbefore commitMarketing rationale
This gives Yi ready-to-use, low-risk owned-channel copy for developers searching around Claude Code memory, Claude Code skills, Codex memory, and local agent learning, without taking any external posting action automatically.
Summary by CodeRabbit