Understand the task: Read the task description or plan carefully. Identify what needs to change, which projects are affected, and any constraints.
Identify affected files: Use search tools to find relevant files. Understand the existing code structure before making changes. Check module boundaries — processors can only import from
sharedlibraries.Implement changes:
- Follow existing patterns in the codebase (look at similar files for reference)
- Use path aliases (
@carrot-fndn/shared/...) for cross-library imports - Use Zod schemas for runtime validation, derive types with
z.infer - Use
@faker-js/fakerandzockerfor test data, never real data - For rule processors, follow the standard structure:
.processor.ts,.lambda.ts,.processor.spec.ts,.lambda.e2e.spec.ts,.test-cases.ts
Verify after each significant change: Run quality checks incrementally to catch issues early.
pnpm lint:affected pnpm ts:affected pnpm test:affectedDebug and fix: If tests or checks fail, read the error output carefully, identify the root cause, and fix it. Do not blindly retry — understand why it failed.
Summarize: When finished, provide a concise summary of:
- What was changed and why
- Any design decisions made
- Any open questions or follow-up items
Execute Task
Autonomously implement a task following project conventions with iterative verification.
majiayu000
Updated Execute Task by majiayu000 · bafa6f0
npx skillmds@latest add majiayu000/execute-task-3 File contents
---name: execute-task-3description: Autonomously implement a task following project conventions with iterative verification.---
1. **Understand the task**: Read the task description or plan carefully. Identify what needs to change, which projects are affected, and any constraints.
2. **Identify affected files**: Use search tools to find relevant files. Understand the existing code structure before making changes. Check module boundaries — processors can only import from `shared` libraries.
3. **Implement changes**:
- Follow existing patterns in the codebase (look at similar files for reference)
- Use path aliases (`@carrot-fndn/shared/...`) for cross-library imports
- Use Zod schemas for runtime validation, derive types with `z.infer`
- Use `@faker-js/faker` and `zocker` for test data, never real data
- For rule processors, follow the standard structure: `.processor.ts`, `.lambda.ts`, `.processor.spec.ts`, `.lambda.e2e.spec.ts`, `.test-cases.ts`
4. **Verify after each significant change**: Run quality checks incrementally to catch issues early.
```bash
pnpm lint:affected
pnpm ts:affected
pnpm test:affected
```
5. **Debug and fix**: If tests or checks fail, read the error output carefully, identify the root cause, and fix it. Do not blindly retry — understand why it failed.
6. **Summarize**: When finished, provide a concise summary of:
- What was changed and why
- Any design decisions made
- Any open questions or follow-up items
majiayu000/claude-skill-registry-data/tree/main/development/task-exec commit bafa6f079a
Frequently asked questions
Run npx skillmds@latest add majiayu000/execute-task-3 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Autonomously implement a task following project conventions with iterative verification. It is listed under Productivity on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.