AI Agent & Automation Workflows

Detects drift between CLAUDE.md / meta narrative and live repository state. Four checks: absolute-path resolution, 01-projects/ count claims, issue-reference freshness (closed refs in forward-looking sections), session-file existence. Invoked as an opt-in session-end phase; mirrors vault-sync's lean JSON+exit-code contract.

Monitor iterative improvement loops for convergence. Three signals — shrinking diff, pass-rate plateau, velocity — drive a Stop/Continue/Investigate decision at each inter-wave checkpoint. Distinct from /evolve (retrospective) and session-reviewer (wave output review): convergence-monitoring answers "are we making progress?" not "was the last wave correct?". Primary consumer: /autoresearch loops and wave-executor inter-wave checkpoints.

Opt-in orchestration for documentation generation and updates within a session. Maps session scope to audience-specific docs tasks (User / Dev / Vault), dispatches the docs-writer agent with source-grounded prompts, and reports coverage gaps to session-end. Gated on docs-orchestrator.enabled: true in Session Config. Zero overhead when disabled.

VCS operations reference for GitLab and GitHub: CLI commands (glab/gh), label taxonomy, issue templates, dynamic project resolution. Used as a reference by other skills and during issue management.

Use when you need a single-pane cross-repo health view across all vault-registered GitLab and GitHub projects. Discovers repos from overview.md frontmatter in /01-projects//, aggregates open issues, MRs, critical labels, and stale signals via parallel glab/gh calls, then writes an idempotent PORTFOLIO.md dashboard. Runs automatically at session-start Phase 2 when gitlab-portfolio.enabled=true. Triggers: "show portfolio status", "refresh the portfolio dashboard", "which repos have critical issues", "run /portfolio". Context: session-start, gitlab-portfolio.enabled=true, vault has 5 registered repos. user: "/session deep" assistant: "Portfolio: 3 critical issues across 2 repos — run /portfolio for details.

Use when performing manual memory consolidation (Dream-equivalent). Reviews, consolidates, and prunes memory files under ~/.claude/projects//memory/. Run after major refactors, every 5+ sessions, or when memory quality degrades (broken links, stale references, contradictions, MEMORY.md > 200 lines). Invoke with /memory-cleanup.

Deterministic mode selection for session-start. Reads Phase A STATE.md recommendations + (future) learnings, sessions, backlog, bootstrap signals and returns {mode, rationale, confidence, alternatives}. Pure-function contract — no side effects, no STATE.md writes. Phase B scaffold (issue 276); full heuristic is follow-up sub-issues.

Use when driving native-UI AX-tree snapshots and screenshots via steipete/peekaboo (MIT, macOS-only). Dispatched by skills/test-runner/ to capture native-UI AX-tree snapshots + screenshots on macOS 15+ targets, and exits with deterministic JSON output the orchestrator can parse.

Use when you need multi-persona parallel content review — domain experts, buyer personas, compliance reviewers, or custom catalog entries reviewing a target file or output. Dispatches N persona agents in parallel, consolidates verdicts via a configurable mode (voting-quorum, hard-gate-threshold, or coordinator-summary), and writes a timestamped sidecar to .orchestrator/persona-panel/. Invoked via /persona-panel .

Use when executing web tests via the canonical playwright npm package (Microsoft, Apache-2.0). Dispatched by skills/test-runner/ to execute web tests against a target, captures token-frugal AX-tree snapshots + screenshots + console output under .orchestrator/metrics/test-runs/ /, and exits with deterministic JSON output the orchestrator can parse.

Creates a structured wave execution plan with role-based assignment after user alignment. Decomposes agreed tasks into configurable waves (default 5) with optimal agent assignment, dependency ordering, and inter-wave checkpoints. Activated by session-start after Q&A phase completes.

Use when the user wants to identify unused, near-zero-use, or stale skills/agents/commands in the plugin surface so they can be demoted or retired. Combines agent-dispatch telemetry (start-events only) with static reference scanning, classifies every surface item into Active / Investigate / Demote / Retire, and emits a Markdown report plus JSON sidecar. NEVER auto-deletes — surfaces candidates for human decision. Quarterly cadence. Context: The plugin surface has grown and the maintainer wants to prune dead weight. user: "/sunset-review" assistant: "Running the sunset walk — classifying skills, agents, and commands by usage telemetry + static refs, grouped by Retire / Demote / Investigate / Active. No item is deleted automatically; I'll surface Retire/Demote candidates for your decision." The user wants a usage-driven prune candidate list; this skill runs the read-only walker, presents grouped verdicts, and writes a sidecar — it never deletes.

Use when the operator wants a prepared tmux visualization layout for the session's side-channels (STATE.md tail, CI-watch, events.jsonl tail). Renders a 4-pane default layout or debug layout. Read-only side-channel observability — the coordinator chat stays in the operator's original terminal. Trigger phrases: "tmux layout", "split panes for ci watch", "visualize session side-channels", "show me state-md tail and ci".

Use when dispatching implicit slash-command intent from the user's first message. Inspects the user's first message for implicit slash-command intent and dispatches to the highest-confidence matching entry-point skill via the Skill tool. Only active when auto-skill-dispatch: true in Session Config. Silent no-op otherwise.

Mirrors session and learning JSONL records into the Meta-Vault as Markdown notes with vault-compatible frontmatter.

Validates vault frontmatter (Zod schema) and wiki-link integrity. Phase 1: hard gate at session-end. Used by session-end skill to block close on invalid vault state.

Use when you have a PRD or design spec and need a bite-sized, executable implementation plan that any agent can follow without re-deriving structure. Produces docs/plans/YYYY-MM-DD- .md with per-task Files block, complete code per step (no placeholders), and exact verification commands. Rejects "TBD", "TODO", "add error handling", "similar to Task N".