lwy-project-rules-writer
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.
lwy-project-rules-writer creates persistent project-level rules that constrain AI behavior across Trae, Cursor, and Windsurf.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-06-03
lwy-project-rules-writer creates persistent project-level rules that constrain AI behavior across Trae, Cursor, and Windsurf. 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.
Use it when
- lwy-project-rules-writer enforces code style, naming conventions (like camelCase in TypeScript), commit message formats.
- Yes.
Verify before relying
Read SKILL.md below before installing (11 files). Open directory: indexed for reading, not audited.
Install
learnwy/skills/lwy-project-rules-writer · repository language: TypeScript
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I set up AI behavior rules in my project?
lwy-project-rules-writer helps you create persistent AI behavior rules stored in your `.agents/rules/` directory. The tool analyzes your codebase, confirms your rule design with you, then generates frontmatter+markdown files that work across Trae, Cursor, Windsurf, and Claude Code. These rules constrain AI behavior across sessions without requiring custom skills or agents.
What can lwy-project-rules-writer enforce in my codebase?
lwy-project-rules-writer enforces code style, naming conventions (like camelCase in TypeScript), commit message formats, consistent logger usage, and architecture boundaries. It creates project-level constraints that apply to all AI interactions, ensuring generated code respects your project patterns and conventions automatically across all supported IDE assistants.
Can I create a rule to make AI always use the project logger?
Yes. lwy-project-rules-writer lets you define rules that enforce specific patterns like mandatory logger usage. You describe the requirement, the tool analyzes your codebase to understand your logging setup, confirms the rule design with you, then generates a rule file in `.agents/rules/` that constrains AI to follow this pattern consistently.
Where does lwy-project-rules-writer store the generated rules?
lwy-project-rules-writer outputs all generated rules to the `.agents/rules/` directory in your project. Each rule is a frontmatter+markdown file compatible with Trae, Cursor, Windsurf, and Claude Code. This persistent location ensures your AI behavior constraints apply automatically across all sessions and supported IDE assistants.
How does lwy-project-rules-writer prevent wrong imports?
lwy-project-rules-writer creates architecture boundary rules that constrain AI code generation. You specify which modules or patterns should never be imported together, the tool confirms the design against your codebase structure, then generates a rule file that makes AI respect these boundaries automatically in all generated code.
Does lwy-project-rules-writer require creating custom skills?
No. lwy-project-rules-writer generates project-level rules directly—no custom skills or agents needed. It writes frontmatter+markdown files to `.agents/rules/` that work natively with Trae, Cursor, Windsurf, and Claude Code, making AI behavior enforcement straightforward and maintainable across your entire team.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Project Rules Writer
Create rules that solve a specific problem in a specific project — never generic ones. Analyse the project first, design, confirm with AskUserQuestion, then generate.
> Core discipline: understand the problem → analyse the project → design the rule → confirm → generate. No file lands without user confirmation.
Shared writing-discipline rules across this and the other writer skills (project-skill-writer / project-agent-writer /
(truncated - see the full file via the links below)
File tree — 11 files
skills/lwy-project-rules-writer/SKILL.md
skills/lwy-project-rules-writer/agents/convention-detector.md
skills/lwy-project-rules-writer/agents/project-scanner.md
skills/lwy-project-rules-writer/agents/quality-validator.md
skills/lwy-project-rules-writer/assets/rule.md.template
skills/lwy-project-rules-writer/assets/trae-rules-docs.md
skills/lwy-project-rules-writer/evals/evals.json
skills/lwy-project-rules-writer/examples/application-modes.md
skills/lwy-project-rules-writer/references/conditional-reflection.md
skills/lwy-project-rules-writer/references/rule-types.md
skills/lwy-project-rules-writer/scripts/cli.cjs
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Create project-level rules to constrain AI behavior across sessions”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
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 transforms recurring manual tasks into standardized, reusable AI capabilities by understanding your problem, analyzing your project structure, and generating a complete skill design. It guides you through problem classification, project profiling, and skill architecture before generating executable SKILL.md files that integrate seamlessly with your codebase.
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.
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.
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.
Human Writing identifies and removes telltale signs of AI-generated text—promotional language, superficial analyses, vague attributions, and overused vocabulary—so your writing sounds like it came from a real person. Beyond just stripping AI patterns, it guides you to add genuine voice: opinions, varied rhythm, specificity, and personality that make prose feel alive.