Optimize content for AI citations in ChatGPT, Perplexity, AI Overviews, Gemini, Claude. AI引用优化/GEO优化/AI搜索

Use when asked to fix short descriptions of Python type members.

Use when a Slate Yjs collaboration behavior is suspicious and Potion should be used as a live reference implementation through dev-browser, especially for offline/reconnect, selection, or history scenarios.

Mine external editor repositories for portable editor-behavior tests with ClawSweeper-style discipline: multi-pass exhaustive inventory, confidence scoring, framework-specific skip reasons, Slate/Plate coverage mapping, license-aware invariant extraction, and copy/refactor/create decisions.

Analyzes code changes from an architectural perspective for pattern compliance and design integrity. Use when reviewing PRs, adding services, or evaluating structural refactors.

Terraform IaC expert for providers, modules, state management, and planning

SQLite expert for WAL mode, query optimization, embedded patterns, and advanced features

Redis expert for data structures, caching patterns, Lua scripting, and cluster operations

Technical interview preparation expert for algorithms, system design, and behavioral questions

Docker expert for containers, Compose, Dockerfiles, and debugging

CSS expert for flexbox, grid, animations, responsive design, and modern layout techniques

Compliance expert for SOC 2, GDPR, HIPAA, PCI-DSS, and security frameworks

CI/CD pipeline expert for GitHub Actions, GitLab CI, Jenkins, and deployment automation

AWS cloud services expert for EC2, S3, Lambda, IAM, and AWS CLI

Expert knowledge for AI Twitter/X management — API v2 reference, content strategy, engagement playbook, safety, and performance tracking

Expert knowledge for AI lead generation — web research, enrichment, scoring, deduplication, and report generation

Expert knowledge for AI intelligence collection — OSINT methodology, entity extraction, knowledge graphs, change detection, and sentiment analysis

Expert knowledge for AI video clipping — yt-dlp downloading, whisper transcription, SRT generation, and ffmpeg processing

日本語の生産性コーチングモード。明示的な依頼、反復失敗、受け身、検証不足、品質不満のときに、構造化トラブルシューティングと証拠ベースの完了確認を促す。

Performance-coaching mode for repeated failures, passive behavior, completion-quality issues, or explicit try-harder requests. Uses structured troubleshooting and evidence-first delivery habits.