Loading...
Loading...
Found 9 Skills
Observe user interaction patterns, extract per-session facets, update a dual-matrix soul state, and periodically synthesize a personalized Soul profile for better collaboration.
Persistent shared memory for AI agents backed by PostgreSQL (fts + pg_trgm, optional pgvector). Includes compaction logging and maintenance scripts.
Postgres-backed observability and policy store for the skill system. Provides tables for policy profiles (effect allowlists), skill execution runs, and step-level events. Use when setting up the skill system database or querying execution history.
Agent behavioral profiles that standardize how different LLMs behave. Load this skill when you need to: (1) adopt a specific behavioral mode for a task, (2) switch between creative/strict/talkative modes, (3) ensure consistent behavior across different models. Profiles define personality, decision heuristics, communication style, and quality standards.
Dynamic orchestration engine that plans multi-step agent work as DAGs with Mermaid visualization.
Version-controlled evolution engine that uses accumulated insight results to evolve soul profiles and workflow recipes with auditability, safety constraints, and rollbacks.
Meta-skill that teaches the Agent how to discover, select, execute, chain, and observe skills in the skill system. Load this skill when you need to: (1) find which skill can handle a capability, (2) execute a skill operation via its entrypoint, (3) chain multiple skill operations together, (4) check policy before executing, or (5) log skill execution for observability. This skill makes YOU the router — you decide what to run, in what order, based on context.
Expert guide for working with opencode.ai - TUI commands, CLI operations, custom commands, agents, tools, skills system, and AGENTS.md configuration
Working memory for thinking out loud.