feat: add ee skill command to set up ee for AI coding agents#2
Merged
Conversation
…agents Introduce `ee skill <agent>` which installs an agent-oriented ee usage guide (the "ee-usage" skill) into the convention each coding agent expects: claude -> .claude/skills/ee-usage/SKILL.md (skill frontmatter) cursor -> .cursor/rules/ee-usage.mdc (rule frontmatter) copilot -> .github/copilot-instructions.md (plain markdown) codex -> AGENTS.md (plain markdown) opencode -> AGENTS.md (plain markdown) all -> every supported agent The guide is embedded in the binary (internal/command/assets/ee-usage.md) and derived from llms.txt, restructured for agents with dedicated sections for adding ee to a new project and working with a project that already has ee configured, plus the full command reference. Supports --force, --list, --print and --quiet. Documentation (README and llms.txt) updated to describe this setup flow. Covered by Go unit tests (target resolution, frontmatter) and Python integration tests (install per agent, all, flags, error handling). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This was referenced Jul 3, 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Adds a new
ee skill <agent>command that installs an agent-oriented ee usage guide (the "ee-usage" skill) into the convention each coding agent expects. This replaces the "copyllms.txtaround" workflow with a first-class, per-agent setup command.claude.claude/skills/ee-usage/SKILL.mdcursor.cursor/rules/ee-usage.mdccopilot.github/copilot-instructions.mdcodexAGENTS.mdopencodeAGENTS.mdallWhat's in the guide
The guide is embedded in the binary (
internal/command/assets/ee-usage.md) and is the single source of truth. It's derived fromllms.txtbut restructured for agents, with dedicated sections for:eeto a new project — step-by-step (init, schema,.env, verify, gitignore)eeproject — detect.ee, read config, apply/verify, add vars/envs, push secrets, secret-safety notes.ee, schema,.env) and the full command referenceCommand
Flags:
--force,--list,--print,--quiet. Existing files are never overwritten without--force;alldedupes shared paths (codex/opencode both useAGENTS.md).Docs
README.md: new AI Coding Agent Integration section; corrected the stale command list; swapped thellms.txtbadge for an AI-skill badge.llms.txt: added an "AI Coding Agent Skill" section and anee skillcommand reference.Tests
internal/command/skill_test.go): target/path resolution, frontmatter wrappers, embedded body sections, stable agent ordering.tests/test_skill.py, 14 cases): per-agent install,all,--list,--print, unknown/missing agent errors, and force-overwrite behavior.All suites pass:
go test ./...(11 pkgs) anduv run pytest(31 tests).🤖 Generated with Claude Code