菜单
Use to batch-validate all skills in this plugin. Runs deterministic repo-wide static checks (frontmatter, command delegation, cross-references, Architect model= rule, orphan references, README<->MemPalace sync) and reports pass/fail per skill.
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
| name | smoke-test-skills |
| description | Use to batch-validate all skills in this plugin. Runs deterministic repo-wide static checks (frontmatter, command delegation, cross-references, Architect model= rule, orphan references, README<->MemPalace sync) and reports pass/fail per skill. |
Type: Architect
Run the deterministic validator and report results. This is Stage A (static checks only); isolated subagent invocation of smoke-safe skills is a planned follow-up (Stage B).
bash scripts/validate-skills.sh from the repo root.FAIL: line grouped by skill and suggest the fix. Do not auto-fix — report only.Next: suggestion (e.g. re-run after fixes, or /loop 10m /vladyslav:smoke-test-skills for periodic checks).The validator is pure bash (macOS + Linux), takes an optional ROOT argument (defaults to repo root), and is safe to run anytime — it never writes files.
Use when adding a feature to a production project. Full cycle: brainstorm, plan, implement, docs.
Use when fixing a bug in a production project. Full cycle: diagnose, fix, regression test, review, docs.
Use when creating a new project. Bare AI shell by default; interactive menu adds docs / backend-infra / agents on demand.
Use after init-project to fill docs/product/start-project.md with AI research on competitors, monetization, valuation, and marketing.
Use when unsure which skill to use. Lists all vladyslav skills, workflow, and integration.
Quick-save the latest decision/problem/milestone to MemPalace with zero questions — derives everything from the current conversation. Use for a fast mid-session capture, or accept it when offered at task completion.