FEC-332: Add AI tooling configuration and agent skills#1014
Open
FEC-332: Add AI tooling configuration and agent skills#1014
Conversation
Install agent skills, MCP server config, and AGENTS.md project context files generated by the shared skills installer. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Merge unique content from standalone/AGENTS.md and generators/AGENTS.md into the root AGENTS.md and remove the sub-package files. Also remove sub-package CLAUDE.md files since they only pointed to their local AGENTS.md. The repo is small enough that separate per-package files created more duplication than value. Also clarifies the two-level model folder structure (domain folder containing sub-model folders) which was slightly oversimplified in the generated template. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
misama-ct
requested review from
ByronDWall,
Ibidapo,
Rombelirk,
ahmehri,
kterry1,
nima-ct,
rajrdk,
tylermorrisford and
valoriecarli
…CLAUDE.md - Fix "commercetools-developer" → "commercetools-docs" to match .mcp.json - Remove /jira-create-epic-from-plan and /jira-implement-task (not installed) - Remove jira-implement-task gitignore entry Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Document the undocumented patterns an LLM needs to work effectively: - Path aliases (@/core, @/models/*, etc.) - Builder factory functions and fluent API methods - Fields config generators (fake, sequence, oneOf, bool) - GraphQL __typename requirement for non-draft models - postBuild callback pattern for computed fields - Preset export structure and naming conventions Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
ByronDWall
approved these changes
Apr 15, 2026
Contributor
ByronDWall
left a comment
ByronDWall
left a comment
There was a problem hiding this comment.
Added a few things, but overall this looks good to me. The skills are installed and run, and the AGENTS file is well-scoped and accurate
tylermorrisford
approved these changes
Apr 15, 2026
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
3 participants
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
commercetools/agent-skills.mcp.json) for commercetools-docs, context7, playwright, and sequential-thinking.claude/settings.json) with Prettier post-write hookCLAUDE.mdandAGENTS.mdproject context filesDeviation from ticket plan: The installer generated per-package
AGENTS.mdandCLAUDE.mdfiles instandalone/andgenerators/, but since this is a small two-package monorepo, there was heavy content overlap with the root file. We consolidated everything into a single rootAGENTS.mdand removed the sub-package files to avoid duplication. The unique content from each sub-package file (standalone's core exports list, dependencies, entrypoint/files-array gotchas; generators' template location, Squirrelly/tsx details) was merged into the root. We also corrected the model folder structure description to clarify the two-level nesting (domain folder > sub-model folder).Test plan
AGENTS.mdagainst actual repo structure.claude/skills//repo-healthcheck-nodeto validate setup🤖 Generated with Claude Code