メニュー
Use whenever answering anything version-sensitive — library/framework/SDK APIs, package versions, model IDs, pricing, CLI flags, config, or "latest/newest" anything. Verify against current sources instead of training data.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Use when you need to research a domain, market, or technical area before planning
Use when starting any conversation — establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Audit frontend and backend implementation against every PRD file, one by one, using parallel subagents. Produces a full status table (done / partial / not-started), identifies critical-path blockers, and recommends next sprints. Use when you need to know where you stand against your PRDs.
First-time project setup for Mighty Powers. Creates config file, artifact directories, offers to generate CLAUDE.md, and explains available workflows.
Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.
| name | staying-current |
| description | Use whenever answering anything version-sensitive — library/framework/SDK APIs, package versions, model IDs, pricing, CLI flags, config, or "latest/newest" anything. Verify against current sources instead of training data. |
| allowed-tools | Bash, Read, WebSearch, WebFetch |
Training data has a cutoff. Libraries ship breaking changes, prices change, model IDs get renamed, and APIs get deprecated after that cutoff. Answering version-sensitive questions from memory is the single most common way an otherwise-correct agent ships wrong code. This skill is the standing rule for not doing that.
The Mighty Powers Currency Guard hook (UserPromptSubmit) already fires on every prompt and injects a reminder when it detects version-sensitive language. This skill is what you do when that fires — or any time you're about to state a fact whose correct answer changes over time.
Before stating any of the following, verify it against a current source. Never answer from training data alone:
| Source | Use for |
|---|---|
context7 MCP (resolve-library-id → query-docs) | Library/framework/SDK documentation and API syntax. This is the primary source for code. Use it even when you think you know the answer. |
| WebSearch / WebFetch | Versions, pricing, model IDs, release notes, deprecations, anything not in a library's docs. The current month is the search context — say "2026" in queries when recency matters. |
The project's lockfile (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, Cargo.lock) | The exact version actually installed here — always check this before assuming a version. |
import or hook call from memory for a library you haven't checked this session.When the task involves Claude, the Anthropic API, model IDs, or pricing, the same rule applies with extra force — these change frequently. Verify model IDs and pricing against current Anthropic docs before quoting them.