菜单
Guide for collaborative ideation sessions — when to explore vs narrow, evaluating ideas, avoiding premature commitment.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Recognizing context pressure before it degrades output quality.
Writing implementation plans — small testable steps, dependency ordering, upfront risk identification.
Evidence before claims, always — run verification commands and confirm output before making any completion or success claims.
Generate Architecture Decision Records — use when asked to document a decision, create an ADR, record why we chose X, or capture architectural rationale.
Generate a structured changelog from git history — use when asked to create a changelog, release notes, or summarize what changed between versions/tags/branches.
How to write pikit workflow YAML files — steps, loops, branches, interpolation.
| name | brainstorming |
| description | Guide for collaborative ideation sessions — when to explore vs narrow, evaluating ideas, avoiding premature commitment. |
Diverge (explore): Generate many ideas without judgment. Quantity over quality. Build on others' ideas. No "but" — only "yes, and."
Converge (narrow): Evaluate, combine, and select. This comes after diverging, never during.
The most common failure mode is converging too early. If you've only generated 2-3 options, you haven't diverged enough.
Score against explicit criteria, not gut feel. Common dimensions:
A 2x2 of effort vs impact is usually enough to prioritize.
Signs you've committed too early:
Antidotes:
