bestdeejay-design/agent-skills / skills/plan-skill
plan-skill
Verified| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.6 KB |
| examples/implementation-plan-example.md | markdown | 2.2 KB |
| scripts/plan_validator.py | script | 4.2 KB |
| skill.json | config | 1.8 KB |
| templates/implementation-plan.md | markdown | 1.5 KB |
examples/implementation-plan-example.md
View on GitHub# Plan: Добавить `--lint` флаг в `scripts/lint.py`
> Дата: 2026-08-08
> Статус: `approved`
## Goal
Скрипт `scripts/lint.py` получает флаг `--lint`, который запускает внешний
линтер (ruff) вместо собственной проверки.
**Acceptance criteria (проверяемо):**
- [x] CR1: `python3 scripts/lint.py --lint --path src/app.py` вызывает ruff и выводит его сообщения
- [x] CR2: без `--lint` поведение скрипта не изменилось (регрессия отсутствует)
## Constraints
- Только Python 3 stdlib + вызов внешней команды (ruff) через `subprocess`
- Код функции `main()` в `scripts/lint.py` не выносится в отдельный модуль
## Steps
### Step 1: тест на флаг
- Files: `tests/test_lint.py`
- Produces: `test_lint_flag_invokes_ruff()` — падает (FAIL)
- Consumes: `main(argv)` из `scripts/lint.py`
- Action: добавить тест, проверяющий, что при `--lint` вызывается ruff через subprocess
- Verification: `python3 -m pytest tests/test_lint.py` → Expected FAIL
- [x] done
### Step 2: реализация флага
- Files: `scripts/lint.py`
- Action: распарсить `--lint` в `argparse`, вызвать `subprocess.run(["ruff", path])`
- Verification: тест из Step 1 → PASS
- [x] done
### Step 3: проверка регрессии
- Files: `scripts/lint.py`, `tests/test_lint.py`
- Action: прогнать полный набор тестов и убедиться, что старый режим работает
- Verification: `python3 -m pytest tests/` → PASS
- [x] done
## Interfaces
- Consumes → Produces:
- `Step1.fail_test` → `Step2.implementation`
- `Step2.lint_runner` → `Step3.regression_check`
## Verification (полная)
- [x] `python3 scripts/plan_validator.py examples/plan-example.md` → ✅
- [x] Тесты зелёные: `python3 -m pytest tests/`
- [x] Диагностика чистая
- [x] Ревью пройдено, замечаний нетRelated skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |