aria_skills/agent_manager/SKILL.md
# aria-agent-manager Runtime agent lifecycle management for Aria. ## Purpose - Spawn, list, monitor, and terminate managed agent sessions. - Produce performance summaries and prune stale sessions. - Aria chooses at spawn time whether a sub-agent is ephemeral or persistent. ## Main Tools - `list_agents` — list active agent sessions - `spawn_agent` — create a raw session (engine table) - `spawn_focused_agent` — spawn → task → response, with `persistent` flag: - `persistent=false` (default): e
npx skillsauth add najia-afk/aria_moltbot aria_skills/agent_managerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Runtime agent lifecycle management for Aria.
list_agents — list active agent sessionsspawn_agent — create a raw session (engine table)spawn_focused_agent — spawn → task → response, with persistent flag:
persistent=false (default): ephemeral, auto-closes after responsepersistent=true: session stays open for multi-turn follow-upssend_to_agent — send follow-up message to a persistent sub-agent sessionterminate_agent — close any session (engine or legacy)get_agent_stats — usage metrics for a sessionprune_stale_sessions — bulk cleanupget_performance_report — aggregate metricsget_agent_health — active agents, uptime, performance# One-shot (ephemeral)
result = spawn_focused_agent(task="...", focus="research", tools=[...])
# Session auto-closes after response
# Multi-turn (persistent)
result = spawn_focused_agent(task="...", focus="analyst", tools=[...], persistent=True)
session_id = result["session_id"]
follow_up = send_to_agent(session_id=session_id, message="Now refine that...")
terminate_agent(session_id=session_id)
tools
# aria-working-memory Persistent short-term memory operations for Aria runtime context. ## Purpose - Store, retrieve, rank, checkpoint, and prune working memory. - Provide high-relevance context for decision and response flows. ## Main Tools - `remember` - `recall` - `get_context` - `checkpoint` - `restore_checkpoint` - `forget` - `update` - `reflect` - `sync_to_files`
development
```skill --- name: aria-unified-search description: "🔎 RRF-merged search across semantic + graph + memory backends" metadata: {"aria": {"emoji": "🔎"}} --- # aria-unified-search Unified search engine that queries semantic memories (pgvector cosine), knowledge graph (ILIKE), and traditional memories (text match), then merges results via Reciprocal Rank Fusion (RRF) with content-hash deduplication. ## Architecture ``` Query ↓ (parallel to 3 backends) ├── SemanticBackend (pgvector cosi
tools
# aria-telegram Telegram Bot API integration skill. ## Purpose - Send and reply to messages through bot credentials. - Fetch updates and basic bot metadata. ## Main Tools - `send_message` - `reply_to_message` - `get_updates` - `get_me`
tools
# aria-sprint-manager Sprint planning and board flow management skill. ## Purpose - Operate goal board as Product Owner. - Move, prioritize, and report sprint progress. ## Main Tools - `sprint_status` - `sprint_plan` - `sprint_move_goal` - `sprint_report` - `sprint_prioritize`