From squad-ase
Use when starting any conversation in a project with squad-ase installed. Establishes skill discovery rules, priority order, and anti-rationalization guardrails. Injected automatically at session start via hook.
How this skill is triggered — by the user, by Claude, or both
Slash command
/squad-ase:using-squad-aseThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are working in a project with **squad-ase** installed — an Autonomous
You are working in a project with squad-ase installed — an Autonomous Software Engineer (ASE) skill set that orchestrates a hierarchical dev team.
When a task begins, check skills in this order:
/loop /ase-tick.If there is even a 1% chance that a skill applies to the current task, you MUST invoke it. The cost of invoking an unnecessary skill is marginal. The cost of NOT invoking a necessary skill is bugs, data corruption, or security vulnerabilities.
Watch for these rationalizations and reject them:
| Rationalization | Reality |
|---|---|
| "This task is too simple for /squad" | Squad auto-selects the right composition. A bug fix uses the quick pipeline (F3+F4). |
| "I already know what to do, I don't need planning" | Squad's F0 validates assumptions. What you "know" is often wrong. |
| "I can skip gate-keeper, the tests pass locally" | Local != CI. Only fresh verification counts. |
| "This is urgent, I'll skip the process" | Urgency doesn't eliminate risk. The process exists because skipping it causes incidents. |
/squad/gate-keeper verificationnpx claudepluginhub santiagofica/squad-ase --plugin squad-aseProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.