菜单
Capture important architectural decisions, bug patterns, feature designs, or other critical findings into the project knowledge base. Use proactively when significant technical decisions are made, non-obvious bugs are resolved, new subsystems are designed, or important product features are discussed.
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
Add a new built-in exercise to Liftosaur end-to-end — image (gymvisual.com → S3), catalog registration, description page, and the LLM/MCP exercise list. Use when adding one or more built-in exercises to the app catalog.
Write idiomatic Liftoscript code for weightlifting programs. Use when creating or editing program files in programs/builtin/.
Manually test/QA the Liftosaur app on the iOS simulator — drive the real UI, inspect live app state, and set up test data. Use when asked to test, QA, stress-test, verify a change works, reproduce a bug, or hunt for bugs in the running app.
Generate an importance-ordered guided walkthrough of your changes this session and publish it to the reviewer's editor via the aireviewer publish_walkthrough tool. Use when the user asks you to explain, walk through, or give a tour of your changes.
Interactively investigate a production Rollbar error. Accepts an occurrence id, item id, item counter, or Rollbar URL. Fetches the error data, assesses how widespread it is, drills into affected users (events, logs, storage, captured state), and works with the developer toward a fix or ignore decision. Use for collaborative debugging; use /fix-rollbar for a straight fetch-and-fix of a single occurrence.
Investigate a user-reported issue using server logs, user events, storage snapshots, and Rollbar. Use when given a user id or email plus an issue description (e.g. from a support email).
| name | kb |
| description | Capture important architectural decisions, bug patterns, feature designs, or other critical findings into the project knowledge base. Use proactively when significant technical decisions are made, non-obvious bugs are resolved, new subsystems are designed, or important product features are discussed. |
| disable-model-invocation | false |
| argument-hint | ["what to capture"] |
Capture this into the knowledge base: $ARGUMENTS
All files live in lambda/scripts/memory/. The index is at lambda/scripts/memory/INDEX.md.
Read lambda/scripts/memory/INDEX.md to understand what's already captured and avoid duplicates.
| Category | Directory | When to use |
|---|---|---|
| Architecture | architecture/ | System design, infrastructure, sync protocols, data formats, tech stack choices |
| Decisions | decisions/ | "We chose X over Y because Z" — explicit tradeoff analysis |
| Features | features/ | Product feature descriptions, UX designs, user-facing behavior |
| Bugs | bugs/ | Non-obvious bug root causes, debugging patterns worth remembering |
| Future Plans | futureplans/ | Planned work not yet started — roadmap items, RFCs for future features |
| SEO | seo/ | SEO research, keyword analysis, backlink data, Core Web Vitals |
If none fit, create a new category directory and add a section to INDEX.md.
Filename: lowercase-kebab-case, descriptive. Example: watch-echo-loop-bug.md
Entry format:
---
date: YYYY-MM-DD
tags: [relevant, tags]
---
# Title
Concise description of the finding/decision/pattern.
Keep it 5-20 lines. Link to relevant source files where useful.
Focus on the WHY and the non-obvious parts — assume the reader is a developer familiar with the codebase.
Add a one-liner entry under the appropriate category heading:
- [filename.md](category/filename.md) — concise one-liner (max 80 chars)
Keep entries sorted by relevance within each category (most important first), not by date.
Capture knowledge when ANY of these happen during a conversation:
Do NOT capture: