lwy-project-agent-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-agent-writer creates project-level autonomous agents by analyzing your codebase and designing agents tailored to your automation needs.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-06-03
lwy-project-agent-writer creates project-level autonomous agents by analyzing your codebase and designing agents tailored to your automation needs. 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.
Use it when
- lwy-project-agent-writer supports six specialized agent archetypes: graders for code review and quality assessment.
- lwy-project-agent-writer helps you build worker agents by first understanding your repetitive task.
Verify before relying
Read SKILL.md below before installing (8 files). Open directory: indexed for reading, not audited.
Install
learnwy/skills/lwy-project-agent-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 create an agent for my project?
lwy-project-agent-writer guides you through building autonomous agents by first understanding your automation need, analyzing your codebase structure, and designing an agent tailored to your problem. The skill supports six agent archetypes—graders, comparators, analyzers, transformers, researchers, and validators—and requires your confirmation before generating any files.
What agent types does lwy-project-agent-writer support?
lwy-project-agent-writer supports six specialized agent archetypes: graders for code review and quality assessment, comparators for comparing outputs, analyzers for finding patterns, transformers for converting data, researchers for gathering information, and validators for enforcing rules and workflow validation.
How do I build a worker agent to automate repetitive tasks?
lwy-project-agent-writer helps you build worker agents by first understanding your repetitive task, analyzing your project structure and conventions, then designing an agent that fits your workflow. The skill generates a scaffold and asks for your confirmation before creating any files, ensuring the agent matches your needs.
Does lwy-project-agent-writer confirm designs before file creation?
Yes. lwy-project-agent-writer generates an agent scaffold and design summary, then requires your explicit confirmation before creating any files. This ensures the autonomous agent matches your project requirements and automation goals before implementation.
Can lwy-project-agent-writer design a validator agent for my workflow?
Yes. lwy-project-agent-writer can design a validator agent to enforce rules and handle workflow validation. It analyzes your project structure, understands your validation needs, and creates a specialized agent tailored to your automation requirements.
What happens after lwy-project-agent-writer analyzes my project?
After analyzing your project structure and understanding your automation need, lwy-project-agent-writer designs an agent from one of its six archetypes that fits your conventions. It then presents the agent scaffold and design for your review and confirmation before proceeding to file generation.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Project Agent Writer
Analyze the project's structure, conventions, and automation gaps, then design an agent to solve the user's problem. Always confirm with the user via AskUserQuestion before generating any files.
> Core principle: First understand the problem, then analyze the project, then design the agent, and only generate after the user confirms.
> Shared principle: This skill shares the 5 common writer disciplines with project-skill-writer / project-skill-installer / project-rules-writer. See ../project-skill-writer/references/writer-discipline.md for details.
Use
(truncated - see the full file via the links below)
File tree — 8 files
skills/lwy-project-agent-writer/SKILL.md
skills/lwy-project-agent-writer/assets/agent.md.template
skills/lwy-project-agent-writer/evals/evals.json
skills/lwy-project-agent-writer/examples/grader-agent.md
skills/lwy-project-agent-writer/references/agent-patterns.md
skills/lwy-project-agent-writer/references/conditional-reflection.md
skills/lwy-project-agent-writer/references/path-discovery.md
skills/lwy-project-agent-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 or design a project-level autonomous agent to automate workflows”
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.
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 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.
Register custom handlers at 16 lifecycle points to observe and control agent behavior. Hooks fire before and after steps, tool calls, human approvals, context compression, and sub-agent invocations, with support for tool mocking and error handling. Handlers run sequentially per operation and auto-clean on completion.
More skills mathmodel-skill (MIT) · create-agent (MIT) · lwy-knowledge-consolidation (MIT)