3,430 件 ・ 関連度順
概要と使いどころ
Build, normalize, and maintain the user's Career Context file so downstream platform outputs stay factual and consistent. Use when the user wants an agent to consolidate CV data, LinkedIn exports, GitHub history, project summaries, bio facts, achievements, or positioning into one professional source of truth before editing platform-specific assets.
日本語の概要は準備中です。原文の説明を表示しています。
Parse PDFs, Office files, images, and HTML into Markdown/structured outputs with MinerU. Use when SciForge or Codex needs document parsing/OCR for scientific papers, supplementary files, PDFs, scanned documents, tables, formulas, or URL/local-file parsing through MinerU standard or Agent lightweight APIs.
日本語の概要は準備中です。原文の説明を表示しています。
Reviews Rust FFI code for type safety, memory layout compatibility, string handling, callback patterns, and unsafe boundary correctness. Use when reviewing extern blocks, #[repr(C)] types, bindgen output, or code calling C/C++ libraries.
日本語の概要は準備中です。原文の説明を表示しています。
Execute YAML test plan, stop on first failure, output rich debug prompt
日本語の概要は準備中です。原文の説明を表示しています。
Applies fixes from a prior review-llm-artifacts run, with safe/risky classification. Respects verify-llm-artifacts output when present to skip false positives.
日本語の概要は準備中です。原文の説明を表示しています。
Vercel AI SDK for building chat interfaces with streaming. Use when implementing useChat hook, handling tool calls, streaming responses, or building chat UI. Triggers on useChat, @ai-sdk/react, UIMessage, ChatStatus, streamText, toUIMessageStreamResponse, addToolOutput, onToolCall, sendMessage.
日本語の概要は準備中です。原文の説明を表示しています。
Create PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when building AI agents, creating chat systems, or integrating LLMs with Pydantic validation.
日本語の概要は準備中です。原文の説明を表示しています。
Drive one AI agent from another through kolu's terminals: spawn a Claude Code / Codex / opencode session in a PTY, prompt it, watch the screen, read the reply, prompt again. PRIMARY PATH: the kolu MCP tools (`lifecycle_create`/`lifecycle_sendInput`, `wait_outputSettled`/ `wait_agentState`, `screen_text`, the `terminals` resource). FALLBACK: the `kolu` CLI — same verbs, same discipline. Triggers on "drive another agent", "agent drives agent", "make Claude drive Codex", or wiring a loop where one coding agent supervises another.
日本語の概要は準備中です。原文の説明を表示しています。
Code review knowledge base: quality, security (OWASP Top 10), error-handling, performance, and test-coverage checklists with severity-ranked output format. Use when reviewing code changes, PRs, or before commits. Loaded automatically by the code-reviewer agent.
日本語の概要は準備中です。原文の説明を表示しています。
Side-by-side comparison of two financial scenarios (buy vs rent, new job vs stay, payoff house vs invest, Roth vs Traditional, lease vs buy car, etc). Projects each scenario over 10 years, compares total cost, opportunity cost, risk profile, and produces a structured recommendation. Output saved as FINANCE-COMPARE.md.
日本語の概要は準備中です。原文の説明を表示しています。
Investment screener with pre-built strategies (Dividend Growth, 3-Fund Index, Bond Allocation, REITs, International Diversification, ESG) and custom criteria support. Returns curated ticker lists, allocation models, expected returns, expense ratios, and a recommended portfolio with rebalancing notes. Output saved as FINANCE-SCREEN.md.
日本語の概要は準備中です。原文の説明を表示しています。
Professional PDF financial plan generator. Scans current working directory for FINANCE-*.md files, extracts scores and financial data, then runs the bundled Python ReportLab script to produce a polished, client-ready PDF with cover page, Financial Health Score gauge, score breakdown, cash flow, debt, retirement, portfolio, and prioritized action plan. Output: FINANCE-PLAN.pdf.
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill to render a weather SVG card and a Markdown summary after the weather-agent returns a temperature payload. Activate whenever the user asks for a weather card, weather graphic, or wants the output of /weather-orchestrator rendered to disk.
日本語の概要は準備中です。原文の説明を表示しています。
HealthSim generates realistic synthetic healthcare data for testing EMR systems, claims processing, pharmacy benefits, and analytics. Use for ANY request involving: (1) synthetic patients, clinical data, or medical records, (2) healthcare claims, billing, or adjudication, (3) pharmacy prescriptions, formularies, or drug utilization, (4) HL7v2, FHIR, X12, or NCPDP formatted output, (5) healthcare testing scenarios or sample data generation.
日本語の概要は準備中です。原文の説明を表示しています。
HealthSim generates realistic synthetic healthcare data for testing EMR systems, claims processing, pharmacy benefits, and analytics. Use for ANY request involving: (1) synthetic patients, clinical data, or medical records, (2) healthcare claims, billing, or adjudication, (3) pharmacy prescriptions, formularies, or drug utilization, (4) HL7v2, FHIR, X12, or NCPDP formatted output, (5) healthcare testing scenarios or sample data generation.
日本語の概要は準備中です。原文の説明を表示しています。
HealthSim generates realistic synthetic healthcare data for testing EMR systems, claims processing, pharmacy benefits, and analytics. Use for ANY request involving: (1) synthetic patients, clinical data, or medical records, (2) healthcare claims, billing, or adjudication, (3) pharmacy prescriptions, formularies, or drug utilization, (4) HL7v2, FHIR, X12, or NCPDP formatted output, (5) healthcare testing scenarios or sample data generation.
日本語の概要は準備中です。原文の説明を表示しています。
RxMemberSim generates realistic synthetic pharmacy data for testing PBM systems, claims adjudication, and drug utilization review. Use when user requests: (1) pharmacy claims or prescription data, (2) DUR alerts or drug interactions, (3) formulary or tier cohorts, (4) pharmacy prior authorization, (5) NCPDP formatted output.
日本語の概要は準備中です。原文の説明を表示しています。
Analyzes and describes vulnerabilities for specific assets and threats within an insurance company risk register context. The output must be highly professional, eloquent, and grammatically impressive, utilizing labelled headings and subheadings.
日本語の概要は準備中です。原文の説明を表示しています。
Structures catastrophe risk assessment with model output interpretation and accumulation monitoring. Use when analyzing cat risk, interpreting cat model results, or managing cat exposure.
日本語の概要は準備中です。原文の説明を表示しています。
Route new policy briefing, policy update, regulatory update deck, regulatory change deck, compliance change summary, legal update deck, or legal/product policy presentation requests here before generic AIPPT. Use this whenever the user wants a new policy interpretation deck with timelines, impacts, risks, and recommended actions. Do not use this scene pack for email memos, FAQ-only outputs, compliance copy polishing, or non-deck legal writing.
日本語の概要は準備中です。原文の説明を表示しています。
Add a new chain to an existing warp route owned by a customer. Reads a Linear ticket, adds the new chain to the deploy.yaml, builds a customer-specific strategy file for existing chains, runs warp apply, and outputs transaction files for the customer to sign via their multisig.
日本語の概要は準備中です。原文の説明を表示しています。
Produce a complete metrics definition doc — metric name, formula, data source, segmentation, SQL or event tracking spec, and what good/bad looks like. Given a product area, outputs the full metrics spec. Use when asked to "define KPIs", "metrics framework", "what should we measure", "north star metric", or "instrument this feature".
日本語の概要は準備中です。原文の説明を表示しています。
Product landscape reconnaissance — survey existing briefs, research, strategy, and team output before writing new briefs or dispatching specialists. Use when asked to "understand the product state", "what briefs exist", "what has the team produced", "orient me on this product", or before starting a new product initiative.
日本語の概要は準備中です。原文の説明を表示しています。
Expert 5-dimension design critique — philosophical, scored, actionable. Use when asked to "critique this design", "expert review", "score my design", "how does this look", "is this good design", "design feedback", or "review this UI". Different from /form-audit (which is technical QA for consistency/compliance) — form-critique evaluates design as a craft object: philosophy, hierarchy, execution, function, and innovation each scored 0–10 with a punch list. Add "as a report" or "give me a visual report" to produce an HTML file with SVG radar chart, evidence cards, and Keep/Fix/Quick-wins action lists — useful for design reviews and stakeholder presentations instead of CLI output.
日本語の概要は準備中です。原文の説明を表示しています。