skill-router

You cannot hold 41 skills and 23 commands in your head. This is the index so you do not have to. Each entry says what it is for and how it fires: [human] you invoke it deliberately, [auto] the agent reaches for it from your prompt.

Keep this honest. When a skill is added, renamed, removed, or changes how it fits a flow, update this file in the same change. A router that points at a skill that no longer exists, or omits a new one, is worse than none.

How to use it

State the job in one line. Match it to a group below. If two skills look close, the when to reach clause is the tiebreaker. Most skills have a matching slash command of the same name, so this index covers commands too.

Self-correction and memory

• learn-rule [human] - capture a correction as a durable rule loaded on every future session.
• replay-learnings [auto] - surface past learnings relevant to the task before you start.
• insights [human] - correction trends, heatmaps, productivity view.
• skill-optimizer [human] - train a skill's SKILL.md against accumulated corrections.

Planning and decisions

• plan-interrogate [human] - resolve every open decision before code; emits a decision ledger, a shared-language CONTEXT.md, and decision records.
• domain-modeling [human] - build the project's shared vocabulary and bounded contexts up front.
• improve-architecture [human] - audit an area and propose the smallest structural moves; plan, not rewrite.
• thoroughness-scoring [auto] - score each decision point 1-10 so effort tracks stakes.
• orchestrate [human] - wire commands, agents, and skills together for a multi-phase feature.

Multi-agent and parallel work