HomericIntelligence

Run section orchestrators to coordinate multi-component workflows. Use when starting work on a section.

Validate agent YAML frontmatter and configuration. Use before committing agent changes or in CI.

Reply to PR review comments using the correct GitHub API endpoint. Use when responding to inline code review feedback (not gh pr comment).

Run Mojo tests using mojo test command. Use when executing tests or verifying test coverage.

Track implementation progress against plan. Use to monitor component delivery and identify blockers.

Check agent configuration coverage across hierarchy levels and phases. Use to ensure complete agent system coverage.

Generate visual hierarchy diagrams of agent system showing levels and delegation. Use for documentation or onboarding.

Test agent delegation patterns to verify hierarchy and escalation paths. Use after modifying agent structure.

Perform a strict, full-coverage pull-request review against its issue, repository architecture, tests, security, and current target branch; supports an operator-authorized CI-free source-review profile.

Use when starting feature work that needs isolation from current workspace — creates isolated git worktrees with safety verification

Audit and clean up Git worktrees first, then safely tidy branches using required Hephaestus automation. Uses Athena's canonical dependency-resolution contract and fails if ~/.agent_brain/automation cannot be prepared. Worktree mutation always needs separate per-gate approval.

Investigate root cause before fixing bugs or unexpected behavior. Requires the Mnemosyne knowledge backend through advise and fails closed when it cannot be prepared.

Use when implementing any feature or bugfix, before writing implementation code — enforces RED-GREEN-REFACTOR cycle

Perform a full-coverage, strict repository evaluation. Supports quick and default report detail; default is the comprehensive strict review.

Search the required Mnemosyne knowledge repository before planning or implementation. Uses Athena's canonical dependency-resolution contract and fails if the backend cannot be prepared at ~/.agent_brain/knowledge.

Use before complex creative work to explore intent and requirements. Requires the Mnemosyne knowledge backend through advise and fails closed when it cannot be prepared.

Search team knowledge before starting work. Use when starting experiments, debugging unfamiliar errors, or before implementing features with unknowns.

Best practices for writing effective skill documentation. Use when creating new skills, improving skill discoverability, or documenting failed attempts.

Save session learnings as a new skill plugin. Use after experiments, debugging sessions, or when you want to preserve team knowledge.

GitHub Actions CI for validating skill plugins. Use when setting up CI/CD for a skills marketplace or enforcing plugin quality.

Fix Docker GHCR push failures when repository organization changes but IMAGE\_NAME remains hardcoded to old org

Batch rebase conflicting PR branches and fix CI failures on main

Batch rebase multiple PRs against main to resolve conflicts and fix CI failures