docs: add AI Foundations skill guide (NES-1501)#8943
Merged
jaco-brink merged 3 commits intomainfrom Apr 1, 2026
Merged
Conversation
Single-page guide for engineers to discover and use AI skills (review-pr, handle-pr-review, reset-stage). Documents prerequisites, Cursor skills, Claude Code commands, convention rules, and troubleshooting. Added README section linking to the guide. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Repository UI Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
WalkthroughAdded documentation and README reference for an "AI Foundations" workflow that describes Cursor/Claude-based AI skills for PR review, review-thread handling, and stage-branch reset, including prerequisites, usage modes/flags, and troubleshooting. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
participant Dev as Developer (Trigger)
participant Cursor as Cursor / Claude Code
participant Local as Local Tooling / Devcontainer
participant GH as GitHub (GraphQL / PRs)
participant Slack as Slack (optional via Doppler)
Dev->>Cursor: Invoke skill (/review-pr, /handle-pr-review, /reset-stage)
Cursor->>Local: Run skill script in devcontainer
Local->>GH: Query PRs/threads & post comments / create commits
GH-->>Local: Return PR data & accept changes
Local->>Cursor: Report results
Cursor->>Dev: Post summary comment / feedback
alt Slack reporting enabled
Local->>Slack: Send status/summary via Doppler credentials
Slack-->>Dev: Deliver notification
end
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes 🚥 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 |
Contributor
|
View your CI Pipeline Execution ↗ for commit f42a7a6
☁️ Nx Cloud last updated this comment at |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
🧹 Nitpick comments (2)
docs/ai-foundations.md (2)
36-43: Consider adding a safety note about the destructive nature of--apply.While line 40 notes "(destructive, prompts for confirmation)", consider adding a brief warning that
reset-stage --applywill force-push to the stage branch and potentially discard work. This could prevent accidental data loss.📝 Suggested enhancement
### reset-stage flags +> ⚠️ **Warning**: `--apply` performs a destructive reset. It will force-push to stage and discard any uncommitted work on that branch. Always run without `--apply` first to preview changes. + ```bash ./tools/scripts/reset-stage.sh # Dry run (safe, no changes) ./tools/scripts/reset-stage.sh --apply # Actual reset (destructive, prompts for confirmation) ./tools/scripts/reset-stage.sh --apply --no-slack # Reset without Slack notification</details> <details> <summary>🤖 Prompt for AI Agents</summary>Verify each finding against the current code and only fix it if needed.
In
@docs/ai-foundations.mdaround lines 36 - 43, Add a clear safety warning to
the reset-stage documentation noting that running ./tools/scripts/reset-stage.sh
--apply will perform a destructive operation (it force-pushes to the stage
branch and can discard unmerged work), that it prompts for confirmation but
should be used with caution, and suggest performing a dry run first or backing
up local changes; reference the script name reset-stage.sh and the --apply and
--no-slack flags so readers know which command is destructive.</details> --- `44-54`: **Clarify the scope of Claude Code availability.** Line 46 states "The same skills are available in Claude Code for terminal-based workflows", but the table only shows `/review-pr` and `/handle-pr-review`. Is `/reset-stage` intentionally excluded? If so, briefly explain why (e.g., "reset-stage is a shell script and should be run directly"). <details> <summary>📝 Suggested clarification</summary> If reset-stage is intentionally excluded: ```diff ## Claude Code Commands -The same skills are available in Claude Code for terminal-based workflows. +PR-related skills are available in Claude Code for terminal-based workflows. The reset-stage skill is a standalone script (`tools/scripts/reset-stage.sh`) and should be run directly in the terminal. | Command | Equivalent Cursor skill | |---------|------------------------| | `/review-pr` | review-pr | | `/handle-pr-review` | handle-pr-review |Alternatively, if it should be included, add it to the table.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/ai-foundations.md` around lines 44 - 54, The docs claim "The same skills are available in Claude Code" but the table only lists `/review-pr` and `/handle-pr-review` and omits `/reset-stage`; clarify whether `/reset-stage` is intentionally excluded or should be listed: if excluded, add a short parenthetical note explaining why (e.g., "`/reset-stage` is a shell script and must be run directly"), otherwise add `/reset-stage` to the table as an additional row mapping to reset-stage so the table accurately reflects available Claude Code commands.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Nitpick comments:
In `@docs/ai-foundations.md`:
- Around line 36-43: Add a clear safety warning to the reset-stage documentation
noting that running ./tools/scripts/reset-stage.sh --apply will perform a
destructive operation (it force-pushes to the stage branch and can discard
unmerged work), that it prompts for confirmation but should be used with
caution, and suggest performing a dry run first or backing up local changes;
reference the script name reset-stage.sh and the --apply and --no-slack flags so
readers know which command is destructive.
- Around line 44-54: The docs claim "The same skills are available in Claude
Code" but the table only lists `/review-pr` and `/handle-pr-review` and omits
`/reset-stage`; clarify whether `/reset-stage` is intentionally excluded or
should be listed: if excluded, add a short parenthetical note explaining why
(e.g., "`/reset-stage` is a shell script and must be run directly"), otherwise
add `/reset-stage` to the table as an additional row mapping to reset-stage so
the table accurately reflects available Claude Code commands.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
Run ID: 135ce798-553b-49ba-a635-9d2b5ba83b56
📒 Files selected for processing (2)
README.mddocs/ai-foundations.md
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@docs/ai-foundations.md`:
- Line 3: Update the sentence "AI skills that automate common engineering tasks
in core. These run inside Cursor and Claude Code — no external services, no cost
beyond your existing tooling." to clarify that core skill execution runs locally
in Cursor/Claude Code but some workflows require external integrations;
explicitly call out the exceptions such as GitHub CLI access ('gh'), Doppler
authentication, and Slack notification flow so readers don’t assume zero
external configuration is ever needed.
🪄 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: Repository UI
Review profile: CHILL
Plan: Pro
Run ID: 29750e74-36d7-4742-bb72-b658cfc6c2e3
📒 Files selected for processing (1)
docs/ai-foundations.md
Address review feedback: - Reword intro to acknowledge gh CLI and Doppler dependencies instead of claiming "no external services" - Clarify that only review skills (not reset-stage) have Claude Code command equivalents Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
Collaborator
Author
Review feedback addressed (f42a7a6)Fixed (adjusted):
|
jaco-brink
deleted the
jacobusbrink/nes-1501-set-up-ai-foundations-docs-in-core-for-knowledge-sharing
branch
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
1 participant
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
docs/ai-foundations.md) documenting all AI skills available in core: review-pr, handle-pr-review, reset-stageTest plan
docs/ai-foundations.mdrenders correctly on GitHub🤖 Generated with Claude Code
Summary by CodeRabbit