com um clique
chore
Create a structured chore plan for maintenance tasks, bug fixes, or refactors
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Menu
Create a structured chore plan for maintenance tasks, bug fixes, or refactors
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Build and maintain the Codebase Atlas for Code Mode: propose areas, write schema-validated explanation nodes via sly-atlas, declare collections for bulk file families, run staleness-driven refreshes PLUS a coverage crawl that enriches the thinnest area every run, generate the catch-up digest, author guided tours, annotate database schemas, serve atlas context to agents, and drive the Code Mode view with navigate/highlight/deck directives
Dynamic context provider for codebase knowledge. This skill should be used when working on code, answering questions about architecture, or making changes that require understanding of project structure. Maintains area-specific reference files that are loaded on demand. Self-updating based on observed drift between references and actual code. Load this skill early in work sessions - it contains essential workflow and update protocols.
Manage kanban cards via CLI with commands for search, create, update, move, reorder, problem tracking, cross-agent notes, scheduled automations, cross-card prompt execution, AI-set status line (manual + tiered auto-status), and structured questionnaires
Send responses back to the user via their messaging channel (Telegram, Slack, Teams, etc). Use this skill when a message arrives with a channel header like [Telegram], [Slack], etc.
Create a git checkpoint of ALL recent changes
Dynamic context provider for codebase knowledge. This skill should be used when working on code, answering questions about architecture, or making changes that require understanding of project structure. Maintains area-specific reference files that are loaded on demand. Self-updating based on observed drift between references and actual code. Load this skill early in work sessions - it contains essential workflow and update protocols.
| name | chore |
| version | 1.1.1 |
| updated | "2026-02-22T00:00:00.000Z" |
| allowed-tools | Read, Write, Edit, Bash, Glob, Grep, SlashCommand |
| argument-hint | chore description (e.g., Fix WebSocket reconnection issues) |
| description | Create a structured chore plan for maintenance tasks, bug fixes, or refactors |
Create a new chore plan in documentation/chores/ to address the specified maintenance task. The plan will be created with proper naming convention including date and category.
/prime <area> or CLAUDE.md)YYYY-MM-DD_{category}_{descriptive_name}.mddocumentation/chores/ directoryWhen category is bug, explicitly announce: "This is a bug fix. I will perform additional analysis to understand the root cause."
Then follow these additional steps:
Include the optional bug sections in the plan (Steps to Reproduce, Root Cause Analysis).
# Chore: <chore name>
**Status**: ACTIVE
**Category**: <bug|refactor|performance|security|debt|docs>
**Created**: YYYY-MM-DD
## Chore Description
<describe the chore in detail, including the problem it solves>
## Steps to Reproduce (Bug Only)
<INCLUDE THIS SECTION ONLY FOR BUGS. List exact steps to reproduce the issue.>
1. <step 1>
2. <step 2>
3. <observe: expected vs actual behavior>
## Root Cause Analysis (Bug Only)
<INCLUDE THIS SECTION ONLY FOR BUGS. Explain WHY the bug occurs, not just where.>
## Context Areas
<if specific areas needed, note which project areas/modules are relevant>
- Suggested areas: [list relevant areas like frontend, backend, api, database, etc.]
- Additional context: [reference relevant documentation or architecture files]
## Relevant Files
Use these files to resolve the chore:
<find and list the files that are relevant to the chore describe why they are relevant in bullet points. If there are new files that need to be created to accomplish the chore, list them in an h3 'New Files' section.>
### New Files
<if any new files need to be created, list them here>
## Step by Step Tasks
IMPORTANT: Execute every step in order, top to bottom.
<list step by step tasks as h3 headers plus bullet points. use as many h3 headers as needed to accomplish the chore. Order matters, start with the foundational shared changes required to fix the chore then move on to the specific changes required to fix the chore. Your last step should be running the `Validation Commands` to validate the chore is complete with zero regressions.>
### Task 1: <descriptive name>
- <specific actions>
- <file modifications>
### Task 2: <descriptive name>
- <specific actions>
- <file modifications>
### Task N: Run Validation
- Execute all validation commands
- Verify no regressions
## Validation Commands
Execute every command to validate the chore is complete with zero regressions.
<list project-specific validation commands - examples:>
- Run test suite (e.g., `pytest`, `npm test`, `make test`)
- Run linters (e.g., `npm run lint`, `flake8`, `eslint`)
- Run type checking (e.g., `mypy`, `tsc --noEmit`)
- Build the project (e.g., `npm run build`, `make build`)
- <other specific tests related to the chore>
### Bug Validation (Bug Only)
<INCLUDE FOR BUGS: Commands/steps to reproduce the bug BEFORE the fix, then verify it's resolved AFTER.>
- Before fix: <how to reproduce and observe the bug>
- After fix: <same steps should now show correct behavior>
## Completion Criteria
<clear, measurable criteria that define when this chore is done>
- [ ] All tests pass
- [ ] No lint errors
- [ ] <specific criteria for this chore>
## Notes
<optionally list any additional notes or context that are relevant to the chore that will be helpful to the developer>
After creating the plan, report:
documentation/chores/YYYY-MM-DD_{category}_{name}.md/implement with the plan path$ARGUMENTS