launch
Start a Space-Agents session. Displays welcome screen with project status.
浏览 thebrownproject 维护的已发布 AI 技能,比较用途与说明,并通过来源仓库了解安装方式。
已收录技能
20收录技能的仓库 Stars 合计
60仓库 Forks
0平均每个技能的仓库 Stars
3同一仓库中的多个技能可能共享 Stars,合计包含重复仓库数据。
Start a Space-Agents session. Displays welcome screen with project status.
Select mode, delegate to analysis skill.
End session. Reconciles exploration folders, appends context to CAPCOM, syncs Beads, displays session stats.
Run test and lint validation gate. Use after implementation to verify code quality, or invoke directly with /airlock to run project tests and linting.
Check mission status and progress via fresh subagent. Queries Beads for features, tasks, bugs, and recent work activity. Keeps HOUSTON context lean.
Execute a single task with Worker/Inspector/Analyst crew. Self-fetches work from Beads.
Mid-session context dump for fresh sessions. Generates structured handover prompt with current state, saves to comms/handover.md for copy/paste into new session.
Select feature, select mode, delegate to execution skill.
Write feature plan with tasks. HOUSTON convenes planning council, synthesizes their input, and guides user through approval stages.
Use to install Space-Agents in a project. Creates .space-agents/ directory and initializes Beads for issue tracking. Run once per project.
Interactive debugging through conversation. HOUSTON guides through 4 phases, asks questions, and suggests agents for investigation.
Launch ralph.sh in background. Best for large features (10+ tasks). Automatic execution until completion.
Interactive code review through conversation. HOUSTON guides review, spawns specialized agents, and helps create Beads for issues found.
Select feature, select mode, delegate to execution skill.
Execute a single task with Worker/Inspector/Analyst crew. Self-fetches work from Beads.
HOUSTON executes feature tasks directly. No agents. Best for small features (1-3 tasks).
Structure work into plans and Beads. Three modes: plan from brainstorm, plan from scratch, or create Beads from existing plan.
HOUSTON spawns Task agents: Worker, Inspector, Analyst per task. Best for medium features (4-10 tasks).
Run test and lint validation gate. Use after implementation to verify code quality.
Explore ideas through conversation. HOUSTON asks questions, has opinions, and suggests background agents when investigation would help.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。