writing-plans

Name: writing-plans
Author: jamditis

336stars57forks

How to install writing-plans?

jamditis/claude-skills-journalism/writing-plans

$npx -y skills add jamditis/claude-skills-journalism --skill writing-plans

Installs into the current project.

Summary

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

Files · 1

View on GitHub

SKILL.md

1	<!--
2	Adapted from obra/superpowers writing-plans skill (v5.0.7), MIT-licensed,
3	copyright 2025 Jesse Vincent. Modifications copyright 2026 Joe Amditis.
4	v0.1.0 added a default-on research phase; v0.2.0 reverted that change
5	and made writing-plans a pure consumer of the brainstorming spec
6	(research belongs at the entry-point stage where work originates).
7	See CREDITS.md.
8	-->
9
10	# Writing Plans
11
12	## Overview
13
14	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.
15
16	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.
17
18	Announce at start: "I'm using the superjawn:writing-plans skill to create the implementation plan."
19
20	Context: This should be run in a dedicated worktree (set up via superjawn:using-git-worktrees).
21
22	Save plans to: `docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md`
23	- (User preferences for plan location override this default)
24
25	## Scope Check
26
27	If 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.
28
29	## File Structure
30
31	Before 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.
32
33	- Design units with clear boundaries and well-defined interfaces. Each file should have one clear responsibility.
34	- 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.
35	- Files that change together should live together. Split by responsibility, not by technical layer.
36	- 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.
37
38	This structure informs the task decomposition. Each task should produce self-contained changes that make sense independently.
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 superjawn:subagent-driven-development (recommended) or superjawn: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	---
65	```
66
67	## Task Structure
68
69	````markdown
70	### Task N: [Component Name]
71
72	Files:
73	- Create: `exact/path/to/file.py`
74	- Modify: `exact/path/to/existing.py:123-145`
75	- Test: `tests/exact/path/to/test.py`
76
77	- [ ] Step 1: Write the failing test
78
79	```python
80	def test_specific_behavior():
81	result = function(input)
82	assert result == expected
83	```
84
85	- [ ] Step 2: Run test to verify it fails
86
87	Run: `pytest tests/path/test.py::test_name -v`
88	Expected: FAIL with "function not defined"
89
90	- [ ] Step 3: Write minimal implementation
91
92	```python
93	def function(input):
94	return expected
95	```
96
97	- [ ] Step 4: Run test to verify it passes
98
99	Run: `pytest tests/path/test.py::test_name -v`
100	Expected: PASS
101
102	- [ ] Step 5: Commit
103
104	```bash
105	git add tests/path/test.py src/path/file.py
106	git commit -m "feat: add specific feature"
107	```
108	````
109
110	## No Placeholders
111
112	Every step must contain the actual content an engineer needs. These are plan failures — never write them:
113	- "TBD", "TODO", "implement later", "fill in details"
114	- "Add appropriate error handling" / "add validation" / "handle edge cases"
115	- "Write tests for the above" (without actual test code)
116	- "Similar to Task N" (repeat the code — the engineer may be reading tasks out of order)
117	- Steps that describe what to do without showing how (code blocks required for code steps)
118	- References to types, functions, or methods not defined in any task
119
120	## Remember
121	- Exact file paths always
122	- Complete code in every step — if a step changes code, show the code
123	- Exact commands with expected output
124	- DRY, YAGNI, TDD, frequent commits
125
126	## Self-Review
127
128	After writing the complete plan, look at the spec with fresh eyes and

People who liked this also viewed

6 picks

Type

writing-plans

336stars57forks

View on GitHub

How to install writing-plans?

jamditis/claude-skills-journalism/writing-plans

$npx -y skills add jamditis/claude-skills-journalism --skill writing-plans

Installs into the current project.

Summary

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

Files · 1

View on GitHub

SKILL.md

1	<!--
2	Adapted from obra/superpowers writing-plans skill (v5.0.7), MIT-licensed,
3	copyright 2025 Jesse Vincent. Modifications copyright 2026 Joe Amditis.
4	v0.1.0 added a default-on research phase; v0.2.0 reverted that change
5	and made writing-plans a pure consumer of the brainstorming spec
6	(research belongs at the entry-point stage where work originates).
7	See CREDITS.md.
8	-->
9
10	# Writing Plans
11
12	## Overview
13
14	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.
15
16	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.
17
18	Announce at start: "I'm using the superjawn:writing-plans skill to create the implementation plan."
19
20	Context: This should be run in a dedicated worktree (set up via superjawn:using-git-worktrees).
21
22	Save plans to: `docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md`
23	- (User preferences for plan location override this default)
24
25	## Scope Check
26
27	If 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.
28
29	## File Structure
30
31	Before 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.
32
33	- Design units with clear boundaries and well-defined interfaces. Each file should have one clear responsibility.
34	- 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.
35	- Files that change together should live together. Split by responsibility, not by technical layer.
36	- 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.
37
38	This structure informs the task decomposition. Each task should produce self-contained changes that make sense independently.
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 superjawn:subagent-driven-development (recommended) or superjawn: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	---
65	```
66
67	## Task Structure
68
69	````markdown
70	### Task N: [Component Name]
71
72	Files:
73	- Create: `exact/path/to/file.py`
74	- Modify: `exact/path/to/existing.py:123-145`
75	- Test: `tests/exact/path/to/test.py`
76
77	- [ ] Step 1: Write the failing test
78
79	```python
80	def test_specific_behavior():
81	result = function(input)
82	assert result == expected
83	```
84
85	- [ ] Step 2: Run test to verify it fails
86
87	Run: `pytest tests/path/test.py::test_name -v`
88	Expected: FAIL with "function not defined"
89
90	- [ ] Step 3: Write minimal implementation
91
92	```python
93	def function(input):
94	return expected
95	```
96
97	- [ ] Step 4: Run test to verify it passes
98
99	Run: `pytest tests/path/test.py::test_name -v`
100	Expected: PASS
101
102	- [ ] Step 5: Commit
103
104	```bash
105	git add tests/path/test.py src/path/file.py
106	git commit -m "feat: add specific feature"
107	```
108	````
109
110	## No Placeholders
111
112	Every step must contain the actual content an engineer needs. These are plan failures — never write them:
113	- "TBD", "TODO", "implement later", "fill in details"
114	- "Add appropriate error handling" / "add validation" / "handle edge cases"
115	- "Write tests for the above" (without actual test code)
116	- "Similar to Task N" (repeat the code — the engineer may be reading tasks out of order)
117	- Steps that describe what to do without showing how (code blocks required for code steps)
118	- References to types, functions, or methods not defined in any task
119
120	## Remember
121	- Exact file paths always
122	- Complete code in every step — if a step changes code, show the code
123	- Exact commands with expected output
124	- DRY, YAGNI, TDD, frequent commits
125
126	## Self-Review
127
128	After writing the complete plan, look at the spec with fresh eyes and

People who liked this also viewed

6 picks

Type