.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/superpowers/writing-plans
home/skills/obra/superpowers/writing-plans
obra avatar

writing-plans

byobra· 95 skills

Installs

201k

Stars

261k

Forks

23k

Category

Product & Project Management

View on GitHub

TL;DR

Use when you have a spec or requirements for a multi-step task, before touching code

How to install writing-plans?

obra/superpowers/writing-plans
$npx -y skills add obra/superpowers --skill writing-plans

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Use this skill

Run `npx skills use "https://github.com/obra/superpowers" --skill "obra/superpowers/writing-plans"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.

Use the whole pack

Use the skills in "https://github.com/obra/superpowers" that are relevant to the current task. Run `npx skills add "https://github.com/obra/superpowers"` and select the relevant skills, then follow their instructions.

Files · 1

View on GitHub
SKILL.md
1# Writing Plans
2 
3## Overview
4 
5Write 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.
6 
7Assume 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.
8 
9**Announce at start:** "I'm using the writing-plans skill to create the implementation plan."
10 
11**Context:** If working in an isolated worktree, it should have been created via the `superpowers:using-git-worktrees` skill at execution time.
12 
13**Save plans to:** `docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md`
14- (User preferences for plan location override this default)
15 
16## Scope Check
17 
18If the spec covers multiple independent subsystems, it should have been broken into sub-project specs during brainstorming. If it wasn't, suggest breaking this into separate plans — one per subsystem. Each plan should produce working, testable software on its own.
19 
20## File Structure
21 
22Before defining tasks, map out which files will be created or modified and what each one is responsible for. This is where decomposition decisions get locked in.
23 
24- Design units with clear boundaries and well-defined interfaces. Each file should have one clear responsibility.
25- You reason best about code you can hold in context at once, and your edits are more reliable when files are focused. Prefer smaller, focused files over large ones that do too much.
26- Files that change together should live together. Split by responsibility, not by technical layer.
27- In existing codebases, follow established patterns. If the codebase uses large files, don't unilaterally restructure - but if a file you're modifying has grown unwieldy, including a split in the plan is reasonable.
28 
29This structure informs the task decomposition. Each task should produce self-contained changes that make sense independently.
30 
31## Task Right-Sizing
32 
33A task is the smallest unit that carries its own test cycle and is worth a
34fresh reviewer's gate. When drawing task boundaries: fold setup,
35configuration, scaffolding, and documentation steps into the task whose
36deliverable needs them; split only where a reviewer could meaningfully
37reject one task while approving its neighbor. Each task ends with an
38independently testable deliverable.
39 
40## Bite-Sized Task Granularity
41 
42**Each step is one action (2-5 minutes):**
43- "Write the failing test" - step
44- "Run it to make sure it fails" - step
45- "Implement the minimal code to make the test pass" - step
46- "Run the tests and make sure they pass" - step
47- "Commit" - step
48 
49## Plan Document Header
50 
51**Every plan MUST start with this header:**
52 
53```markdown
54# [Feature Name] Implementation Plan
55 
56> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
57 
58**Goal:** [One sentence describing what this builds]
59 
60**Architecture:** [2-3 sentences about approach]
61 
62**Tech Stack:** [Key technologies/libraries]
63 
64## Global Constraints
65 
66[The spec's project-wide requirements — version floors, dependency limits,
67naming and copy rules, platform requirements — one line each, with exact
68values copied verbatim from the spec. Every task's requirements implicitly
69include this section.]
70 
71---
72```
73 
74## Task Structure
75 
76````markdown
77### Task N: [Component Name]
78 
79**Files:**
80- Create: `exact/path/to/file.py`
81- Modify: `exact/path/to/existing.py:123-145`
82- Test: `tests/exact/path/to/test.py`
83 
84**Interfaces:**
85- Consumes: [what this task uses from earlier tasks — exact signatures]
86- Produces: [what later tasks rely on — exact function names, parameter
87 and return types. A task's implementer sees only their own task; this
88 block is how they learn the names and types neighboring tasks use.]
89 
90- [ ] **Step 1: Write the failing test**
91 
92```python
93def test_specific_behavior():
94 result = function(input)
95 assert result == expected
96```
97 
98- [ ] **Step 2: Run test to verify it fails**
99 
100Run: `pytest tests/path/test.py::test_name -v`
101Expected: FAIL with "function not defined"
102 
103- [ ] **Step 3: Write minimal implementation**
104 
105```python
106def function(input):
107 return expected
108```
109 
110- [ ] **Step 4: Run test to verify it passes**
111 
112Run: `pytest tests/path/test.py::test_name -v`
113Expected: PASS
114 
115- [ ] **Step 5: Commit**
116 
117```bash
118git add tests/path/test.py src/path/file.py
119git commit -m "feat: add specific feature"
120```
121````
122 
123## No Placeholders
124 
125Every step must contain the actual content an engineer needs. These are **plan failures** — never write them:
126- "TBD", "TODO", "implement later", "fill in details"
127- "Add appropriate error handling" / "add validation" / "handle edge cases"
128- "Write tests for the above" (without actual test code)
129- "Similar to Task N" (repeat the code — the engineer may be reading tasks out of order)
130- Steps that describe what to do without showing how (code blocks required for code steps)
131- References to types, functions, or methods not defined in any task
132 
133## Self-Review
134 
135After writing the complete plan, look at the spec with fresh eyes and check the plan against it. This is a checklist you run yourself — not a subagent dispatch.
136 
137**1. Spec coverage:** Skim each section/requirement in the spec. Can you point to a task that implements it? List any gaps.
138 
139**2. Placeholder scan:** Search your plan for red flags — any of the patterns from the "No Placeholders" section above. Fix them.
140 
141**3. Type consistency:** Do the types, method signatures, and property names you used in later tasks match what you defined in earlier tasks? A function called `clearLayers()` in Task 3 but `clearFullLayers()` in Task 7 is a bug.
142 
143If you find issues, fix them inline. No need to re-review — just fix and move on. If you find a spec requirement with no task, add the task.
144 
145## Execution Handoff
146 
147After saving the plan, offer execution choice:
148 
149**"Plan complete and saved to `docs/superpowers/plans/<filename>.md`. Two execution options:**
150 
151**1. Subagent-Driven (recommended)** - I dispatch a fresh subagent per task, review between tasks, fast iteration
152 
153**2. Inline Execution** - Execute tasks in this session using executing-plans, batch execution with checkpoints
154 
155**Which approach?"**
156 
157**If Subagent-Driven chosen:**
158- **REQUIRED SUB-SKILL:** Use superpowers:subagent-driven-development
159- Fresh subagent per task + two-stage review
160 
161**If Inline Execution chosen:**
162- **REQUIRED SUB-SKILL:** Use superpowers:executing-plans
163- Batch execution with checkpoints for review

Security

Passed

  • Gen Agent Trust Hubpass
  • Socketpass
  • Snykpass
  • Runlayerpass
  • ZeroLeakspass

Preview

obra/superpowersobra/superpowers

$ npx -y skills add obra/superpowers --skill writing-plans

▸ installing to .claude/skills…

✓ writing-plans ready

Repoobra/superpowers
TypeSkills
CategoryProduct & Project Management
ForArchitectDeveloper
UpdatedJul 2026
License—
First seenJul 26, 2026

Tags

Skill

Related

6 picks
Type
  1. mattpocock avatargrill-meA relentless interview to sharpen a plan or design.SkillsJul 2026690k189k
  2. mattpocock avatartriageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026463k189k
  3. larksuite avatarlark-task飞书任务:管理任务、清单和任务智能体。创建待办任务、查看和更新任务状态、拆分子任务、组织任务清单、分配协作成员、上传任务附件、注册或注销任务智能体、更新任务智能体的主页数据、写入智能体任务记录。当用户需要创建待办事项、查看任务列表、跟踪任务进度、管理项目清单或给他人分配任务、为任务上传附件文件、注册注销任务智能体、更…SkillsJul 2026388k16k
  4. larksuite avatarlark-okr飞书 OKR:管理目标与关键结果。查看和编辑 OKR 周期、目标、关键结果、对齐关系、量化指标和进展记录。当用户需要查看或创建 OKR、管理目标和关键结果、查看对齐关系时使用。不负责:待办任务管理(lark-task)、日程/会议安排(lark-calendar)、绩效评估SkillsJul 2026324k16k
  5. obra avatarbrainstormingYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.SkillsJul 2026301k261k
  6. mattpocock avatargrillingGrill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.SkillsJul 2026295k189k