Menulis Rencana
Rumuskan rencana tindakan yang rinci dan terstruktur untuk mencapai tujuan proyek yang kompleks.
SKILL.md Definition
Writing Plans
Overview
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 (created by brainstorming skill).
Save plans to: docs/plans/YYYY-MM-DD-<feature-name>.md
Bite-Sized Task Granularity
Each step is one action (2-5 minutes):
- "Write the failing test" - step
- "Run it to make sure it fails" - step
- "Implement the minimal code to make the test pass" - step
- "Run the tests and make sure they pass" - step
- "Commit" - step
Plan Document Header
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]
---
Task Structure
### 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, offer execution choice:
**"Plan complete and saved to `docs/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:**
- **REQUIRED SUB-SKILL:** Use superpowers:subagent-driven-development
- Stay in this session
- Fresh subagent per task + code review
**If Parallel Session chosen:**
- Guide them to open new session in worktree
- **REQUIRED SUB-SKILL:** New session uses superpowers:executing-plans
---
## About Superpowers
Superpowers is a complete software development workflow for your coding agents, built on top of a set of composable "skills".
### Philosophy
- **Test-Driven Development** - Write tests first, always
- **Systematic over ad-hoc** - Process over guessing
- **Complexity reduction** - Simplicity as primary goal
- **Evidence over claims** - Verify before declaring success
### Installation
**Note:** Installation differs by platform. Claude Code has a built-in plugin system. Codex and OpenCode require manual setup.
#### Claude Code (via Plugin Marketplace)
In Claude Code, register the marketplace first:
```bash
/plugin marketplace add obra/superpowers-marketplace
Then install the plugin from this marketplace:
/plugin install superpowers@superpowers-marketplace
Verify Installation
Check that commands appear:
/help
# Should see:
# /superpowers:brainstorm - Interactive design refinement
# /superpowers:write-plan - Create implementation plan
# /superpowers:execute-plan - Execute plan in batches
Links & Support
- Repository: https://github.com/obra/superpowers
- Issues: https://github.com/obra/superpowers/issues
Skill Unggulan
"Temukan 'agent skills' yang sempurna untuk proyek Anda"
Database ZINC
Database senyawa komersial yang dikurasi untuk penyaringan virtual.
Zarr Python
Implementasi Python dari array N-dimensi yang dikompresi dan dipotong untuk data ilmiah.
Database USPTO
Akses ke basis data Kantor Paten dan Merek Dagang Amerika Serikat.
Database UniProt
Sumber daya komprehensif, berkualitas tinggi, dan gratis untuk urutan protein dan informasi fungsional.
Agent Skills yang Kuat
Tingkatkan performa AI Anda dengan koleksi keahlian profesional kami.
Siap Digunakan
Salin dan tempel ke sistem agen mana pun yang mendukung skill.
Desain Modular
Gabungkan 'code skills' untuk menciptakan perilaku agen yang kompleks.
Optimasi
Setiap 'agent skill' disesuaikan untuk performa dan akurasi tinggi.
Sumber Terbuka
Semua 'code skills' terbuka untuk kontribusi dan personalisasi.
Multi-platform
Bekerja dengan berbagai LLM dan kerangka kerja agen.
Aman dan Terlindungi
Keahlian terverifikasi yang mengikuti praktik terbaik keamanan AI.
Cara Kerja
Mulai gunakan agent skills dalam tiga langkah sederhana.
Pilih Skill
Temukan keahlian yang Anda butuhkan dalam koleksi kami.
Baca Doc
Pahami cara kerja keahlian dan batasan-batasannya.
Salin & Gunakan
Tempelkan definisi ke dalam konfigurasi agen Anda.
Uji Coba
Verifikasi hasil dan perbaiki jika perlu.
Terapkan
Luncurkan agen AI khusus Anda.
Apa Kata Pengembang
Lihat mengapa pengembang di seluruh dunia memilih Agiskills.
Alex Smith
Insinyur AI
"Agiskills telah benar-benar mengubah cara saya membangun agen AI."
Maria Garcia
Manajer Produk
"Skill PDF Specialist menyelesaikan masalah penguraian dokumen yang kompleks bagi kami."
John Doe
Pengembang
"Keahlian profesional dan terdokumentasi dengan baik. Sangat merekomendasikan!"
Sarah Lee
Artis
"Skill Seni Algoritmik menghasilkan kode yang sangat indah."
Chen Wei
Spesialis Frontend
"Tema yang dihasilkan oleh Theme Factory sempurna di setiap piksel."
Robert T.
CTO
"Kami sekarang menggunakan Agiskills sebagai standar untuk tim AI kami."
FAQ
Segala hal yang perlu Anda ketahui tentang Agiskills.
Ya, semua keahlian publik dapat disalin dan digunakan secara gratis.