用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/oyi77/1ai-skills --skill writing-plans命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Android and mobile application security testing — emulators, rooting, traffic interception, dynamic instrumentation. Use when testing mobile apps for vulnerabilities, reversing APKs, or bypassing security controls on Android.
Self-reflection + Self-criticism + Auto-learning from corrections + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when working with self improving.
Plan and execute a comprehensive red team engagement covering reconnaissance through post-exploitation using MITRE ATT&CK-aligned TTPs to evaluate an organization's detection and response capabilities. Use when working with conducting full scope red team engagement.
基于 SOC 职业分类
正在显示 SKILL.md
| name | writing-plans |
| description | Use when you have a spec or requirements for a multi-step task, before touching code |
| domain | development |
| author | oyi77 |
| license | Apache-2.0 |
| subdomain | software-development |
| tags | ["coding","plans","software-engineering","testing","writing"] |
| version | 1.0.0 |
persona: name: "Domain Expert" title: "Master of Writing Plans" expertise: ['Specialized Knowledge', 'Best Practices', 'Industry Standards'] philosophy: "Excellence through expertise." credentials: ['Industry leader', 'Practiced expert', 'Thought leader'] principles: ['Quality first', 'Continuous improvement', 'Evidence-based decisions', 'Customer focus']
Robert C. Martin (Uncle Bob) - Clean Code Advocate, Agile Manifesto Co-Author
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.
| Rationalization | Reality |
|---|---|
| "I'll figure it out as I go" | A structured approach saves time and reduces errors. Follow the workflow in this skill rather than improvising. |
| "I already know this topic" | Familiarity breeds shortcuts. Use the checklist to verify you haven't missed critical steps. |
| "This doesn't apply to my situation" | The patterns here generalize across contexts. Adapt, don't skip — the underlying principles hold. |
| "One more tool will fix it" | Adding complexity rarely solves process gaps. Master the core workflow first. |
Trigger phrases:
"writing plans"
"When you have requirements or a spec for a multi-step task"
"Before any code implementation begins"
"When breaking down complex features into executable tasks"
When you have requirements or a spec for a multi-step task
Before any code implementation begins
When breaking down complex features into executable tasks
When you need to coordinate multiple agents or workstreams
Plan Structure:
Save to: .sisyphus/plans/YYYY-MM-DD-<feature-name>.md
Execution gate: Momus OKAY required before execution
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 (created by brainstorming skill).
Canonical standard: agent-docs/plan-artifact-standard.md
Save plans to: .sisyphus/plans/YYYY-MM-DD-<feature-name>.md
Execution gate contract: plans written by this skill are execution-eligible only after Momus returns OKAY and evidence is recorded per the canonical standard.
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 superpowers: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]
**Plan ID:** [stable identifier]
**Status:** DRAFT
**Momus Verdict:** NOT OKAY
**Evidence Path:** [path to Momus review evidence]
---
Required minimum sections in every plan:
TL;DRContextObjectivesVerification StrategyExecution StrategyTODOsSuccess CriteriaRequired failure coverage: include at least one explicit negative or failure scenario in Verification Strategy.
Before Momus OKAY, the only allowed actions are:
Implementation execution is blocked until the plan is saved under .sisyphus/plans/ and Momus verdict is OKAY.
If execution later drifts from this approved plan:
.sisyphus/plans/OKAY### 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**
```python
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**
```bash
git add tests/path/test.py src/path/file.py
git commit -m "feat: add specific feature"
```
After saving the plan, offer execution choice:
"Plan complete and saved to .sisyphus/plans/<filename>.md. Two execution options:
1. Subagent-Driven (this session) - I dispatch fresh subagent per task, review between tasks, fast iteration
2. Parallel Session (separate) - Open new session with executing-plans, batch execution with checkpoints
Which approach?"
If Subagent-Driven chosen:
If Parallel Session chosen:
| Rationalization | Reality |
|---|---|
| "I'll do this later" | Explain why this excuse is wrong for this skill |
| "This is simple, skip steps" | Even simple tasks benefit from process |
After completing this skill, confirm: