メニュー
SkillsMP は manutej/meta-suite から 8 件の skill を収集しています。skill を開くとソースと詳細を確認できます。
収集済み skill 8 件中 8 件を表示しています。
Design the context strategy for a project or working session — what knowledge to keep, where it lives, what to load when, how to compress it, and how to hand it off — so work stays grounded and compounds across sessions instead of starting cold every time.…
原文の言語: 英語
Apply the discipline of craft — building things that survive contact with reality and stay easy to change — to any project, and emit a project-specific craft constitution plus a Definition of Done. Use whenever someone wants work done to a senior standard…
原文の言語: 英語
Derive a typed, medium-specific DESIGN SCHEMA from any design brief, then execute it into an audited, self-contained artifact plus the design system that generates it. Use whenever the user wants to design — but design rigorously and reusably rather than by…
原文の言語: 英語
Turn a minimal prompt — even one line — into a complete, WOW-grade deliverable bundle, right-sized to the domain and scope: grounded research, a project vision, a reusable meta-prompt, an execution plan, a grounded data model, and the production-quality…
原文の言語: 英語
Generate a customized META-PLAN — a typed, example-agnostic planning scaffold — before any complete plan is written, for agentic tasks executed by one or many agents. Bridges /meta-prompting (generic tasks) to agentic planning (ultraplan-class capability).…
原文の言語: 英語
Generate a structured, example-agnostic META-PROMPT from any input task — a reusable "how to think" scaffold rather than worked examples. Use this whenever the user wants to design a prompt/system prompt for a CATEGORY of tasks, build a prompt template or…
原文の言語: 英語
Run a rigorous, task-agnostic research scaffold — decompose a question, fan out across sources, triage by credibility, cross-verify claims adversarially, and synthesize a cited answer with explicit confidence — then leave behind reusable knowledge atoms. Use…
原文の言語: 英語
Derive the right set of review lenses for any deliverable and run an adversarial, multi-perspective review that returns prioritized findings plus a reusable lesson — so the same problem gets caught automatically next time. Use whenever someone wants something…
原文の言語: 英語