Home
Scenario-based tutorials with real screenshots, prompts, workflow templates and pitfalls.
A six-step prompt pipeline that turns podcast transcripts into structured knowledge cards-preprocessing, insight extraction, quote cards, action checklists, knowledge graph nodes, and critical review. Pair with Whisper/Tingwu for transcription, feed to Claude/DeepSeek long-context models.
A 6-step data cleaning method where the LLM provides judgment and Python provides execution: profile dirty points, define rules, script execution, LLM for hard rules, validate, and audit trail. Includes 3 copy-paste prompts and 5 pitfalls.
Refactoring legacy code with Claude Code/Cursor takes more than a "refactor this" prompt. This 5-step SOP hard-codes engineering discipline: build a test safety net first, define refactoring boundaries, give the AI precise context, execute step-by-step with manual diff review, then regression-verify. Includes 4 copy-ready prompt templates and 5 real-world pitfalls.
Parse your codebase into a SQLite knowledge graph with Tree-sitter so AI code reviews only read affected files, cutting tokens 38-528x across 6 repos. Four-step SOP: install, build, use, review, with real commands and pitfalls.
n8n lead auto-collect + scoring + notify workflow: multi-channel leads -> dedupe+enrich -> LLM scoring (intent/budget/timing) -> high-score push to sales + CRM. With .json template + scoring prompt + 4 pitfalls (incl. personal-data compliance).
n8n RSS aggregation + AI summary workflow: multi-source RSS scheduled fetch -> dedupe -> LLM summary + topic scoring -> into Feishu/Notion. With .json template download + scoring prompt + 4 pitfalls, a content-site topic pipeline.
AI book notes prompt pack: chapter summary -> atomic knowledge cards (Zettelkasten) -> teardown into article/mindmap/action list, three-tier copyable prompts + 4 pitfalls.
AI email writing prompt pack: intro business email -> intermediate Cold Email -> advanced follow-up/win-back/negotiation, three-tier copyable prompts + 4 pitfalls. Persona + CTA + variable placeholders.
Build an enterprise knowledge base RAG with Dify SOP: self-host/chunking/embedding/retrieval tuning full workflow + copyable system prompt + 6 pitfalls. Real params: chunk 500-1000, top-k 3-5, hybrid retrieval weights.
AI Xiaohongshu viral image-text SOP: topic/title/body/cover/publish full workflow + 5 copyable prompts + 9 pitfalls. A grounded methodology from competitor teardown to publish optimization.