skill-system-workflow
Skill System Workflow
skill-system-workflow is the planning layer for the skill system. It turns a goal
into a DAG with Mermaid output, prefers reusable recipes when possible, and stays
strictly read-only with respect to execution.
Ticket lifecycle operations are owned by skill-system-tkt. This skill now owns
only planning, visualization, and recipe discovery.
Overview
- Input: a goal plus optional context
- Output: a DAG document and Mermaid
flowchart TD - Planning strategy: recipe match first, dynamic planning second
- Execution: out of scope; downstream skills consume the DAG
Core Operations
plan
More from arthur0824hao/skills
skill-system-memory
Persistent shared memory for AI agents backed by PostgreSQL (fts + pg_trgm, optional pgvector). Includes compaction logging and maintenance scripts.
99skill-system-router
Deprecated compatibility shim for router behavior. skill-system-cli now owns the router runtime, while this skill remains as a compatibility/documentation surface during the transition.
73skill-system-soul
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.
67skill-system-postgres
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.
63skill-system-insight
Deprecated compatibility shim for observe-and-evolve flows. skill-system-soul is now the canonical owner; this skill remains as a redirect surface for existing commands, docs, and tests.
62skill-system-behavior
BDD-style behavior specification engine for the skill system. Use when: (1) defining a new skill's behavior before implementation, (2) validating a spec against the schema, (3) generating a behavior contract (Mermaid DAG) from a spec, (4) running structural acceptance tests against a built skill. Workflow: Spec → Test → Develop → Contract.
51