najia-afk
46 verified skills46 total stars
aria_skills/agent_manager
# 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
tools1
aria-apiclient
Centralized HTTP client for aria-api interactions
tools1
aria_skills/community
# aria-community Support level: advanced compatibility (specialist use) Community growth and engagement orchestration. ## Purpose - Track members and engagement events. - Identify champions and campaign opportunities. - Generate growth strategy and content planning outputs. ## Main Tools - `track_member` - `record_engagement` - `get_community_health` - `identify_champions` - `create_campaign` - `generate_content_calendar`
tools1
aria-datapipeline
📊 Data pipeline management and ETL operations for Data Architect
development1
aria_skills/experiment
# aria-experiment Support level: advanced compatibility (specialist use) Experiment tracking and lightweight model registry support. ## Purpose - Track experiment lifecycle and metric points. - Compare runs and register model versions. - Promote model stages across environments. ## Main Tools - `create_experiment` - `log_metrics` - `complete_experiment` - `compare_experiments` - `register_model` - `promote_model`
tools1
aria_skills/llm
# aria-llm — LLM Fallback Chain Skill **Layer:** 2 (Infrastructure) | **Category:** LLM | **Status:** Active (S-45 Phase 3) ## Purpose Provides resilient LLM completions with per-model circuit breakers and automatic fallback through the priority chain defined in `aria_models/models.yaml`. Never hardcodes model names — all routing comes from `routing.fallbacks` in models.yaml. ## Model Chain Loaded dynamically at startup from `aria_models/models.yaml` (`routing.fallbacks`). Tier order: `lo
development1
aria-memeothy
🦞 Church of Molt / Crustafarianism — join the flock, submit prophecy & sacred art, read the Great Book, view Prophets
development1
aria_skills/memory_compression
```skill --- name: aria-memory-compression description: "🗜️ 3-tier hierarchical memory compression" metadata: {"aria": {"emoji": "🗜️"}} --- # aria-memory-compression 3-tier hierarchical memory compression engine. Scores memory importance, compresses via LLM summarization (with rule-based fallback), and manages raw → recent → archive tiers. Stores compressed summaries in semantic memory. ## Architecture ``` Raw memories (limit: 20) ↓ ImportanceScorer (recency × significance × category ×
development1
aria-moltbook
Interact with Moltbook - the social network for AI agents. Post updates, comment, upvote, search, and interact with other AI agents.
testing1
aria_skills/moonshot
# aria-moonshot Moonshot/Kimi provider integration skill. ## Purpose - Execute model calls through Moonshot-compatible pathways. - Provide a stable skill interface for higher-level orchestration. ## Main Tools - Refer to `skill.json` tool definitions for this provider skill.
tools1
aria_skills/ollama
# aria-ollama (DEPRECATED) > **⚠️ DEPRECATED in v3.0.0** — Ollama has been replaced by **LiteLLM** as the model router. > Local models are now served via MLX and routed through LiteLLM. > This skill is retained for backward compatibility but is not active. ## Legacy Purpose - Route generation and utility model calls to local Ollama runtime. - Provide low-cost local fallback in model orchestration. ## Main Tools - Refer to `skill.json` tool definitions for this provider skill.
tools1
aria_skills/pattern_recognition
```skill --- name: aria-pattern-recognition description: "🔍 Behavioral pattern detection in memory streams" metadata: {"aria": {"emoji": "🔍"}} --- # aria-pattern-recognition Behavioral pattern detection engine. Analyzes memory streams to find recurring topics, temporal habits, sentiment drift, emerging interests, and knowledge gaps. Stores detected patterns in semantic memory. ## Architecture ``` Memory stream (list of memory dicts) ↓ TopicExtractor (9 keyword domains + entity regex +
data-ai1
aria_skills/pipeline_skill
# aria-pipeline-skill Cognitive pipeline orchestration skill. ## Purpose - Load pipeline definitions and execute multi-step workflows. - Track pipeline status and return structured step results. ## Main Tools - `run_pipeline` - `list_pipelines` - `get_pipeline_status`
tools1
aria-rpg-pathfinder
Pathfinder 2e rules engine — dice rolls, combat resolution, character and condition management for Aria's tabletop RPG system.
tools1
aria-schedule
Manage Aria's scheduled jobs, tasks, and background operations.
tools1
aria_skills/sentiment_analysis
```skill --- name: aria-sentiment-analysis description: "💭 Multi-dimensional sentiment analysis with adaptive tone" metadata: {"aria": {"emoji": "💭"}} --- # aria-sentiment-analysis Multi-dimensional sentiment analysis engine. Detects valence, arousal, and dominance across messages. Derives frustration, satisfaction, and confusion scores. Blends fast lexicon analysis with LLM classification. Tracks conversation trajectories and recommends adaptive response tones. ## Architecture ``` User te
development1
aria_skills/session_manager
````skill --- name: aria-sessionmanager description: Two-layer session management — filesystem delete (live) + PG mark ended (history). metadata: {"aria": {"emoji": "🧹", "always": true}} --- # aria-sessionmanager Two-layer session management for aria: 1. **Filesystem** (aria-api volume): reads sessions.json, removes keys, archives .jsonl transcripts 2. **aria-api PG**: PATCHes session status to ended (keeps history on /sessions dashboard) Sessions live on the filesystem at /app/agents/{agent
development1
aria_skills/skill_guide
# skill_guide Self-documentation reader for Aria's skill system. ## Purpose Lets Aria **read any skill's SKILL.md** before calling its tools. This enables self-onboarding: when a new skill is added with a SKILL.md, Aria can read it on demand to understand usage, parameters, and examples. ## Layer **Layer 2 — Core** (available to all agents) ## Tools ### skill_guide__read Read a skill's documentation. | Parameter | Type | Required | Description | |----
tools1
aria_skills/sprint_manager
# 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`
tools1
aria_skills/telegram
# 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`
tools1
aria_skills/_template
# {{skill_name}} > TODO: One-line summary of what this skill does. ## Purpose TODO: 2-3 sentences explaining: - What problem this skill solves - Which external services it connects to (if any) - Which agent types benefit most (e.g. "primarily for data-focused agents") ## Layer **Layer {{layer}} — {{layer_name}}** <!-- Layer reference: 0 = Kernel (read-only security), 1 = API Client (DB gateway), 2 = Core (runtime services), 3 = Domain (feature logic), 4 = Orchestration (planning/sche
tools1
aria_skills/working_memory
# 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`
tools1
aria_skills/browser
# aria-browser — Headless Browser Skill **Layer:** 2 (Infrastructure) | **Category:** Browser | **Status:** Active ## Purpose Headless browser access via the `aria-browser` (browserless/chromium) service. Navigate, snapshot, screenshot, and scrape web pages without needing a local browser binary. ## Configuration (env vars) | Variable | Default | Description | |----------|---------|-------------| | `BROWSERLESS_URL` | `http://aria-browser:3000` | Browserless service URL | | `BROWSERLESS_INT
development1
aria_skills/conversation_summary
# aria-conversation-summary Session and topic summarization into durable semantic memory. ## Purpose - Compress activity streams into concise summaries. - Extract decisions and unresolved items. - Store memory-friendly synthesis for later retrieval. ## Main Tools - `summarize_session` - `summarize_topic`
tools1
aria_skills/fact_check
# aria-fact-check Support level: advanced compatibility (specialist use) Claim extraction and structured verification workflow helpers. ## Purpose - Extract checkable claims from text. - Assess claims against evidence and produce verdict scaffolds. - Summarize verification state across claims. ## Main Tools - `extract_claims` - `assess_claim` - `quick_check` - `compare_sources` - `get_verdict_summary`
tools1
aria_skills/model_switcher
# aria-model-switcher Support level: advanced compatibility (operator override) Catalog-backed model selection and thinking-mode control. ## Purpose - List available catalog models. - Switch active model deterministically. - Toggle thinking/reasoning mode and keep history. ## Main Tools - `list_models` - `switch_model` - `get_current_model` - `set_thinking_mode` - `get_thinking_mode` - `get_switch_history`
tools1
aria-performance
Log and query Aria's performance reviews and self-assessments.
databases1
aria-securityscan
🔒 Security scanning and vulnerability detection for DevSecOps
development1
aria_skills/unified_search
```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
development1
aria-marketdata
📈 Cryptocurrency market data and analysis for Crypto Trader
data-ai1
aria-goals
Manage user goals, habits, and progress tracking. Create goals with milestones and reminders.
development1
aria-health
System health monitoring for Aria services. Check database, LLM, and API connectivity.
development1
aria-hourlygoals
Manage Aria's hourly goals and micro-tasks for short-term focus.
development1
aria-knowledgegraph
Build and query Aria's knowledge graph. Store entities and relationships.
development1
aria-litellm
Manage LiteLLM proxy, models, and API spend tracking.
development1
aria-inputguard
🛡️ Runtime security for Aria - analyzes inputs for prompt injection, validates API params, filters sensitive output
development1
aria_skills/brainstorm
# aria-brainstorm Support level: advanced compatibility (specialist use) Creative ideation and brainstorming session management. ## Purpose - Start structured brainstorming sessions. - Capture, connect, and evaluate ideas. - Apply ideation techniques and summarize outcomes. ## Main Tools - `start_session` - `add_idea` - `apply_technique` - `connect_ideas` - `evaluate_ideas` - `summarize_session`
tools1
aria-cicd
🔄 CI/CD pipeline management and automation for DevSecOps
tools1
aria_skills/focus
# Focus Skill — Personality Profile Management **Layer:** L2 (Core Services) **Version:** 1.0.0 **Author:** Aria Blue **Dependencies:** `api_client` --- ## Purpose The Focus skill provides introspection and self-activation capabilities for Aria's personality layer. Aria can list available focus modes, inspect token budgets and delegation levels, switch her own focus type mid-session, and check current focus status — all with minimal token cost. Focus profiles define Aria's operational
tools1
aria_skills/pipelines
# pipelines (support folder) This directory stores YAML pipeline definitions consumed by `aria-pipeline-skill`. It is a workflow-definition folder, not a standalone skill module. ## Contents - `*.yaml` files defining multi-step skill pipelines. ## Runtime Owner - `aria_skills/pipeline_skill/__init__.py`
devops1
aria-pytest
Run pytest for the Aria codebase and return structured results.
development1
aria-portfolio
💼 Portfolio and position management for Crypto Trader
tools1
aria-research
📰 Research and information gathering for Journalist
development1
aria-rpg-campaign
Campaign state management — sessions, world state, encounters, NPCs, quests, party, and calendar for Aria's Pathfinder 2e RPG system.
data-ai1
aria-social
Manage Aria's social presence and posts on Moltbook and other platforms.
testing1
aria_skills/sandbox
# aria-sandbox Isolated execution environment for controlled code operations. ## Purpose - Run code and tests in a contained sandbox. - Read/write temporary files safely for experimentation. ## Main Tools - `run_code` - `write_file` - `read_file` - `run_tests` - `reset`
tools1