lwy-project-skill-writer

This skill guides you through building autonomous agents for your project by first understanding your automation need, analyzing your codebase structure, and designing an agent tailored to your problem. It supports six agent archetypes—graders, comparators, analyzers, transformers, researchers, and validators—and requires user confirmation before generating any files.

lwy-project-rules-writer guides you through designing and generating project-specific AI rules that persist across sessions. It analyzes your codebase, confirms the rule design with you, then outputs frontmatter+markdown files to `.agents/rules/` — compatible with Trae, Cursor, Windsurf, and Claude Code. Use it to enforce naming conventions, code style, commit formats, or consistent AI behavior without creating skills or agents.

This skill analyzes your project's tech stack and workflow to recommend the best-matching skills, then installs them to a project-relative path only after you confirm. It detects languages, frameworks, build tools, and testing setups to surface relevant skill options, while delegating skill creation to specialized writers.

This skill acts as a prompt coach, evaluating every instruction you send to an AI system across seven key dimensions: clarity, specificity, context, structure, examples, constraints, and completeness. It scores each area, identifies gaps, and delivers a rewritten version designed to produce better results on the first try. Works with any prompt type—code generation, writing, analysis, or creative tasks.

lwy-self captures your daily work life—meetings, collaborations, decisions—into a private local diary that grows into a personal knowledge layer. It stores what you did and who you worked with across dated entries, people profiles, and project records, letting your AI assistant know you as a person. Pair it with lwy-llm-wiki to separate personal history from world knowledge.

Capture debugging breakthroughs, configuration wins, and operational lessons as structured Markdown files anchored to your project's IDE folder. Each insight becomes a dated, searchable doc that travels with your codebase and surfaces in future sessions on the same project. When a doc proves reusable across projects, promote it into the global knowledge wiki.