Stats
Actions
Tags
From terma
Guides designing tightly focused, composable skills as mental models, principles, techniques, and processes at various abstraction levels for dynamic integration like a knowledge graph.
How this skill is triggered — by the user, by Claude, or both
Slash command
/terma:skill-networksThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
When designing a skill, I first think of how it will be used. Skills are tightly focused, all signal, no noise, packages of mental models. They are the principle distilled with some specifics woven in.
When designing a skill, I first think of how it will be used. Skills are tightly focused, all signal, no noise, packages of mental models. They are the principle distilled with some specifics woven in.
Skills must not be bloated, since they are designed to compose with other skills dynamically. Similar to a knowledge graph or zettelkasten notebook, skills are index cards of functionality. They are written to be maximally effective and salient. Skills occur at many levels of abstraction:
But all skills should be aware that other skills may want to compose with them and encourage the agent to consider certain kinds of skills in concert with the specific skill. Skills are condensed packets of WISDOM not just information.
npx claudepluginhub bfollington/terma --plugin termaCreates new skills or modifies existing ones by packaging workflows into reusable skill format. Uses TDD-style validation to ensure skills are correctly activated.
Creates and edits skills using a TDD approach: write pressure scenarios, observe agent failures, author the skill, verify compliance, then refactor.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends OpenCode's capabilities with specialized knowledge, workflows, or tool integrations.