HADES audit event KG context: resolve a HADES design Tessera-anchored audit event + show full 5-lane RRF augmentation context (citations, callers, callees, community). Use when operator invokes /hades:audit-impact <event-id>.
HADES research-first brainstorming: dispatch SOTA research before Q&A, apply project-doctrine override on top of superpowers:brainstorming, output design spec. Use when operator invokes /hades:brainstorm or before any design work.
HADES subagent-driven plan execution: stage reality-check, per-task dispatch loop with review gates, no-tech-debt doctrine, hard gates per commit. Use when operator invokes /hades:execute-plan or when implementing a stage plan.
Canonical HADES system project skill: doctrine reminders (max-scope, no defer, no tech debt, no AI-attribution in commits), workflow patterns (brainstorm → spec → write-plan → execute-plan → release), hard rules, and pointers to project memory.
Snapshot HADES session state to .hades/session.md, commit with conventional message (no AI attribution), prepare for /clear or session end. Sister skill to /hades:start.
Recover a HADES session: read .hades/session.md TL;DR, check git status, identify active plan, present concise session-resume summary, and await operator direction.
HADES TDD-task-decomposed plan writing: master + stage files pattern, parallel stage-writer dispatch, watchdog mitigation, two-stage self-review. Use when operator invokes /hades:write-plan or after design spec is frozen.
HADES doctrine-amendment lifecycle: list, show, acknowledge, or deny doctrine-change proposals (HADES design + HADES design). All decisions audit-logged via HADES design Tessera chain. Use when operator invokes /hades:amendment-* commands.