Menú
Use when you have a spec or requirements for a multi-step task, before touching code
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Orchestrates deterministic code review feedback loop — simplify → request review → receive and implement feedback → repeat until done. Run this before creating a PR.
Use this before spawning coding agents when you need to turn an idea into an execution-ready prompt file for bootstrap-task.sh or spawn-agent.sh.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Thematic brainstorming entrypoint. Use before implementation to clarify intent and produce an execution-ready prompt/spec.
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
| name | writing-plans |
| description | Use when you have a spec or requirements for a multi-step task, before touching code |
Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.
Assume they are a skilled developer, but know almost nothing about our toolset or problem domain. Assume they don't know good test design very well.
Announce at start: "I'm using the writing-plans skill to create the implementation plan."
Context: This should be run in a dedicated worktree prepared during planning or implementation setup.
Save plans to: docs/plans/YYYY-MM-DD-<feature-name>.md
Each step is one action (2-5 minutes):
Every plan MUST start with this header:
# [Feature Name] Implementation Plan
> **For Claude:** REQUIRED SUB-SKILL: Use ceo:executing-plans to implement this plan task-by-task.
**Goal:** [One sentence describing what this builds]
**Architecture:** [2-3 sentences about approach]
**Tech Stack:** [Key technologies/libraries]
---
### Task N: [Component Name]
**Files:**
- Create: `exact/path/to/file.py`
- Modify: `exact/path/to/existing.py:123-145`
- Test: `tests/exact/path/to/test.py`
**Step 1: Write the failing test**
```python
def test_specific_behavior():
result = function(input)
assert result == expected
Step 2: Run test to verify it fails
Run: pytest tests/path/test.py::test_name -v
Expected: FAIL with "function not defined"
Step 3: Write minimal implementation
def function(input):
return expected
Step 4: Run test to verify it passes
Run: pytest tests/path/test.py::test_name -v
Expected: PASS
Step 5: Commit
git add tests/path/test.py src/path/file.py
git commit -m "feat: add specific feature"
## Remember
- Exact file paths always
- Complete code in plan (not "add validation")
- Exact commands with expected output
- Reference relevant skills with @ syntax
- DRY, YAGNI, TDD, frequent commits
## Execution Handoff
After saving the plan to `docs/plans/YYYY-MM-DD-<name>.md`, hand off to the agent swarm:
```bash
./scripts/bootstrap-task.sh \
--repo <repo-path> \
--id <task-id> \
--branch <branch-name> \
--agent <agent> \
--task-type <type> \
--description "<short description>" \
--prompt-file <path-to-plan>
Agent selection by task nature (non-negotiable):
--agent codex --task-type backend-complex--agent claude --task-type frontend-ui--agent gemini --task-type ux-design--agent codex --completion-mode no-pr-specThen set up the cron watcher per AGENTS.md §Active Task Monitoring.
Do NOT offer a "subagent-driven" option. Do NOT implement tasks yourself. You write the plan. The agent executes it. Full stop.