Agent Building skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
gaai-oss:bootstrap
Initialize or refresh a project's GAAI OSS memory by activating the Bootstrap Agent and context-bootstrap workflow.
iterative-refinement
Disciplined, measurable iteration for a substantial refinement or investigation: loop against verifiable pass/fail conditions, fan work out to subagents, and keep the main context lean. Use when improving something measurable over repeated cycles (tuning a metric or detector, refactoring against a regression bar), chasing a surprising or suspicious number, or driving a long multi-step task where delegation and context discipline matter. Not for one-shot edits or quick lookups that don't warrant a loop.
memory-delta-triage
Apply three deterministic heuristics to a single memory-delta file to produce a structured verdict block; invoke memory-ingest on ACCEPTED candidates only in validate mode. Activate when Discovery processes a raw memory-delta from contexts/artefacts/memory-deltas/.
pneuma-mode-maker
Pneuma Mode Maker workspace guidelines. Use for ANY task in this workspace: creating modes, editing manifest.ts, pneuma-mode.ts, viewer components, skill prompts, seed files, publishing, forking, or any mode package development. This skill defines the ModeManifest reference, ViewerContract patterns, and publishing workflow. Consult before your first edit in a new conversation.
prompt-fable
Write, review, or migrate prompts, system prompts, and skills targeting Claude Fable 5.
qa-loop-ui
Presents up to 5 questions from smart-question-generator one at a time, records answers, handles per-question skip and skip-all, captures per-question response time and total session duration. Renders a streaming progress header with question count and time estimate. Used as the interaction layer of Stage 4 of the /gaai:bootstrap pipeline.
qnn
Launch a Qualitative Neural Network (QNN) — a layered, multi-epoch brainstorm of agent personas that maps divergent strategies before implementation. Use to unstick sticky debugging (deadlock, race, perf cliff, architecture trap) OR to enrich an artifact with higher-feature / higher-nuance options (metrics, APIs, UX, research features) when the local loop is thin or circling. Triggers: /qnn, /qnn-brainstorm, "qnn explore", "brainstorm ways out", "unstuck", "richer features", "solution space", multi-perspective exploration of a coding or design problem.
registry-browser
搜索已监视注册表中的社区法律技能，显示匹配项及其描述，并提供在安装前 查看完整 SKILL.md 的选项。当用户说"浏览""搜索技能""找某个方面的技能" "有什么可用的"或想添加新注册表到监视列表时使用。
related-skills-surfacer
基于其他插件中的近期活动推荐社区技能。检查社区是否已构建了与某任务 相关的内容，并以非侵入方式提及一次。当用户说"这个有没有社区技能" "还有什么可用的"或询问技能推荐时使用；也作为其他插件工作流的被动环节运行。