leonanpereirapinto/ai-utils/executar-task
Claude Code and agent skill by leonanpereirapinto/ai-utils
- community
Checking that the SKILL.md file is still in the repository.
Implements feature tasks by loading required skills, reading PRD/TechSpec context, analyzing dependencies, and executing the implementation with tests. Marks tasks as complete in tasks.md and triggers the task-reviewer agent upon completion. Use when the user asks to implement a task, execute a task, or start working on a specific task number. Do not use for creating tasks, running QA, code review, or bug fixing.
Install
npx vskill@latest install leonanpereirapinto/ai-utils/executar-taskSKILL.md
Task Execution
Procedures
Step 1: Pre-Task Configuration (Mandatory)
- Read the task definition file at
./tasks/prd-[feature-slug]/[num]_task.md. - Read the PRD at
./tasks/prd-[feature-slug]/prd.mdfor context. - Read the Tech Spec at
./tasks/prd-[feature-slug]/techspec.mdfor technical requirements. - Identify dependencies from previous tasks and verify they are complete.
- Do NOT skip any of these reads.
Step 2: Load Required Skills
- Identify the technologies involved in the task (React, Hono, shadcn, etc.).
- Load the corresponding skills from
.claude/skills/based on technologies used. - Use Context7 MCP to analyze documentation of involved languages, frameworks, and libraries.
Step 3: Task Analysis (Mandatory)
- Analyze the task considering:
- Main objectives.
- How the task fits into the project context.
- Alignment with project rules and standards.
- Possible approaches or solutions.
- Generate a task summary:
- Task ID and Name.
- PRD Context (main points).
- Tech Spec Requirements (key technical requirements).
- Dependencies.
- Main Objectives.
- Risks/Challenges.
Step 4: Approach Plan (Mandatory)
- Define a numbered step-by-step approach.
- Do NOT skip any step.
Step 5: Implementation (Mandatory)
- Begin implementation immediately after planning.
- Follow all project standards established in CLAUDE.md and project rules.
- Implement solutions without workarounds.
- Create and run all task tests before considering the task finished.
Step 6: Mark Task Complete (Mandatory)
- After successful implementation and tests, mark the task as complete in
tasks.md.
Step 7: Review (Mandatory)
- Execute the
task-revieweragent to review the implementation. - Address any issues identified by the reviewer.
- Do not finalize the task until review issues are resolved.
Error Handling
- If the task file does not exist, halt and report to the user.
- If dependencies are not complete, warn the user and ask whether to proceed.
- If tests fail, fix the issues before marking the task as complete.
- If the task-reviewer identifies critical issues, address them before finalizing.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/spec-driven/executar-task/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/leonanpereirapinto/ai-utils/executar-task)