From superspec
Use when starting a new session to understand how superspec skills work and when to invoke them
How this skill is triggered — by the user, by Claude, or both
Slash command
/superspec:ss-using-superspecThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
<SUBAGENT-STOP>
Superspec skills override default system prompt behavior, but user instructions always take precedence:
If CLAUDE.md says "don't use TDD" and a skill says "always use TDD," follow the user's instructions.
Use the Skill tool. When you invoke a skill, its content is loaded and presented to you — follow it directly. Never use the Read tool on skill files.
Invoke relevant skills BEFORE any response or action. If a skill clearly applies to what you're about to do, invoke it first.
digraph skill_flow {
"User message received" [shape=doublecircle];
"Skill applies?" [shape=diamond];
"Invoke Skill tool" [shape=box];
"Announce: 'Using [skill] to [purpose]'" [shape=box];
"Follow skill" [shape=box];
"Respond" [shape=doublecircle];
"User message received" -> "Skill applies?";
"Skill applies?" -> "Invoke Skill tool" [label="yes"];
"Skill applies?" -> "Respond" [label="no"];
"Invoke Skill tool" -> "Announce: 'Using [skill] to [purpose]'";
"Announce: 'Using [skill] to [purpose]'" -> "Follow skill";
}
When multiple skills could apply, use this order:
"Let's build X" → ss-brainstorming first, then implementation skills.
Superspec skills do NOT execute git write commands (commit, push, merge, rebase, branch delete). The user handles their own git workflow. Read-only git commands (status, log, diff) are fine for gathering information.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub coyoteleo/superspec --plugin superspec