ralphinit

Name: ralphinit
Author: sterlingcrispin

201stars18forks

How to install ralphinit?

sterlingcrispin/claude_slash_commands/ralphinit

$npx -y skills add sterlingcrispin/claude_slash_commands --skill ralphinit

Installs into the current project.

Summary

Start a ralph style looping session

Files · 1

View on GitHub

SKILL.md

1	# Initialize Project Documentation from System Plan
2
3	You are initializing a new project for agent-driven development. The user has provided a `current_SYSTEM-PLAN.md` file in the current working directory that describes the system architecture and goals.
4
5	## Your Task
6
7	Read `current_SYSTEM-PLAN.md` and create two companion documents:
8
9	1. current_PRD.md - A comprehensive Product Requirements Document
10	2. current_PROGRESS.md - A progress tracking journal
11
12	These three `current_*` files will serve as the foundation for an automated agent that works in a continuous development loop, picking up tasks and making progress incrementally.
13
14	---
15
16	## Step 1: Read the System Plan
17
18	First, read `current_SYSTEM-PLAN.md` in the current directory to understand:
19	- Project goals and context
20	- Architecture and components
21	- Design decisions
22	- Development stages/phases
23	- Success criteria
24	- Any constraints or scope limitations
25
26	---
27
28	## Step 2: Create current_PRD.md
29
30	Write a comprehensive PRD with testable requirements extracted from the system plan. Structure it as:
31
32	```markdown
33	# [Project Name] - Product Requirements Document
34
35	Last Updated: [today's date]
36
37	---
38
39	## Requirements
40
41	```json
42	[
43	{
44	"category": "functional\|integration\|architecture\|performance\|usability\|maintainability\|milestone\|constraint",
45	"description": "Clear, testable requirement statement",
46	"steps": [
47	"Step 1 to verify this requirement",
48	"Step 2...",
49	"Step 3...",
50	"Step 4...",
51	"Step 5..."
52	],
53	"passes": false
54	},
55	...
56	]
57	```
58
59	## Summary Statistics
60
61	\| Category \| Count \|
62	\|----------\|-------\|
63	\| Functional \| X \|
64	\| Integration \| X \|
65	\| ... \| ... \|
66	\| Total \| X \|
67
68	## Development Stages Mapping
69
70	Map requirements to development stages from the system plan.
71
72	## Open Questions
73
74	List any ambiguities or decisions that need user input.
75	```
76
77	### PRD Guidelines:
78
79	- Extract ALL testable requirements from the system plan - be thorough
80	- Each requirement must have 4-6 concrete verification steps
81	- Start all requirements with `"passes": false`
82	- Use categories: `functional`, `integration`, `architecture`, `performance`, `usability`, `maintainability`, `milestone`, `constraint`
83	- Functional requirements should cover every component mentioned in the architecture
84	- Include milestone requirements that map to the plan's success criteria
85	- Aim for 40-100 requirements depending on project complexity
86	- Requirements should be specific enough that pass/fail is unambiguous
87
88	---
89
90	## Step 3: Create current_PROGRESS.md
91
92	Write a progress journal structured for continuous agent development:
93
94	```markdown
95	# [Project Name] Progress Journal
96
97	Purpose: Track progress on implementation. Useful for context continuity between sessions.
98
99	Last Updated: [today's date]
100
101	---
102
103	## Current Status: [STAGE NAME] NOT STARTED
104
105	Brief description of where we are.
106
107	---
108
109	## Project Context Quick Reference
110
111	### What We Have
112	- Key existing assets (data, models, infrastructure)
113
114	### Key Files
115	- List important files and their purposes
116
117	### Core Design Decisions (from plan)
118	1. Decision 1
119	2. Decision 2
120	...
121
122	---
123
124	## Development Stages Checklist
125
126	### Stage 1: [Name]
127	Goal: [from system plan]
128
129	- [ ] Task 1
130	- [ ] Task 2
131	- [ ] Task 3
132
133	Validation: [how to know this stage is complete]
134
135	---
136
137	### Stage 2: [Name]
138	...
139
140	---
141
142	## Session Log
143
144	### [Date] - Session 1
145	Work Done:
146	- (empty - will be filled as work progresses)
147
148	Next Session Should:
149	- Start with first task from Stage 1
150
151	---
152
153	## Architecture Quick Reference
154
155	[Include a simplified architecture diagram or component list from the system plan]
156
157	---
158
159	## Key Interfaces (for quick reference)
160
161	[Extract key interfaces/APIs from the system plan that the agent will need to implement]
162
163	---
164
165	## Notes & Decisions Log
166
167	Add notes here as implementation decisions are made
168
169	---
170
171	## Open Questions
172
173	[Copy from system plan or identify new ones]
174	```
175
176	### Progress Guidelines:
177
178	- Structure should make it easy for an agent to:
179	- Quickly understand current state
180	- Find the next task to work on
181	- Record what was done
182	- Track which PRD requirements have been satisfied
183	- Include enough architecture context that the agent doesn't need to re-read the full system plan every session
184	- Checklist items should map to PRD requirements where possible
185	- Leave session log empty - it will be filled as work progresses
186
187	---
188
189	## Step 4: Verify and Report
190
191	After creating both files:
192	1. Confirm both files were written successfully
193	2. Report the total number of requirements in the PRD
194	3. Report the number of development stages identified
195	4. List any open questions or ambiguities that need user clarification
196
197	---
198
199	## Important Notes
200
201	- The system plan is the source of truth - don't invent requirements not implied by the plan
202	- Be comprehensive - the agent will rely on these documents to know what to build
203	-

People who liked this also viewed

6 picks

Type

find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 20262.6M27k
grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026633k182k
vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026573k29k
improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026522k182k
setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026454k182k
triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026424k182k

ralphinit

201stars18forks

View on GitHub

How to install ralphinit?

sterlingcrispin/claude_slash_commands/ralphinit

$npx -y skills add sterlingcrispin/claude_slash_commands --skill ralphinit

Installs into the current project.

Summary

Start a ralph style looping session

Files · 1

View on GitHub

SKILL.md

1	# Initialize Project Documentation from System Plan
2
3	You are initializing a new project for agent-driven development. The user has provided a `current_SYSTEM-PLAN.md` file in the current working directory that describes the system architecture and goals.
4
5	## Your Task
6
7	Read `current_SYSTEM-PLAN.md` and create two companion documents:
8
9	1. current_PRD.md - A comprehensive Product Requirements Document
10	2. current_PROGRESS.md - A progress tracking journal
11
12	These three `current_*` files will serve as the foundation for an automated agent that works in a continuous development loop, picking up tasks and making progress incrementally.
13
14	---
15
16	## Step 1: Read the System Plan
17
18	First, read `current_SYSTEM-PLAN.md` in the current directory to understand:
19	- Project goals and context
20	- Architecture and components
21	- Design decisions
22	- Development stages/phases
23	- Success criteria
24	- Any constraints or scope limitations
25
26	---
27
28	## Step 2: Create current_PRD.md
29
30	Write a comprehensive PRD with testable requirements extracted from the system plan. Structure it as:
31
32	```markdown
33	# [Project Name] - Product Requirements Document
34
35	Last Updated: [today's date]
36
37	---
38
39	## Requirements
40
41	```json
42	[
43	{
44	"category": "functional\|integration\|architecture\|performance\|usability\|maintainability\|milestone\|constraint",
45	"description": "Clear, testable requirement statement",
46	"steps": [
47	"Step 1 to verify this requirement",
48	"Step 2...",
49	"Step 3...",
50	"Step 4...",
51	"Step 5..."
52	],
53	"passes": false
54	},
55	...
56	]
57	```
58
59	## Summary Statistics
60
61	\| Category \| Count \|
62	\|----------\|-------\|
63	\| Functional \| X \|
64	\| Integration \| X \|
65	\| ... \| ... \|
66	\| Total \| X \|
67
68	## Development Stages Mapping
69
70	Map requirements to development stages from the system plan.
71
72	## Open Questions
73
74	List any ambiguities or decisions that need user input.
75	```
76
77	### PRD Guidelines:
78
79	- Extract ALL testable requirements from the system plan - be thorough
80	- Each requirement must have 4-6 concrete verification steps
81	- Start all requirements with `"passes": false`
82	- Use categories: `functional`, `integration`, `architecture`, `performance`, `usability`, `maintainability`, `milestone`, `constraint`
83	- Functional requirements should cover every component mentioned in the architecture
84	- Include milestone requirements that map to the plan's success criteria
85	- Aim for 40-100 requirements depending on project complexity
86	- Requirements should be specific enough that pass/fail is unambiguous
87
88	---
89
90	## Step 3: Create current_PROGRESS.md
91
92	Write a progress journal structured for continuous agent development:
93
94	```markdown
95	# [Project Name] Progress Journal
96
97	Purpose: Track progress on implementation. Useful for context continuity between sessions.
98
99	Last Updated: [today's date]
100
101	---
102
103	## Current Status: [STAGE NAME] NOT STARTED
104
105	Brief description of where we are.
106
107	---
108
109	## Project Context Quick Reference
110
111	### What We Have
112	- Key existing assets (data, models, infrastructure)
113
114	### Key Files
115	- List important files and their purposes
116
117	### Core Design Decisions (from plan)
118	1. Decision 1
119	2. Decision 2
120	...
121
122	---
123
124	## Development Stages Checklist
125
126	### Stage 1: [Name]
127	Goal: [from system plan]
128
129	- [ ] Task 1
130	- [ ] Task 2
131	- [ ] Task 3
132
133	Validation: [how to know this stage is complete]
134
135	---
136
137	### Stage 2: [Name]
138	...
139
140	---
141
142	## Session Log
143
144	### [Date] - Session 1
145	Work Done:
146	- (empty - will be filled as work progresses)
147
148	Next Session Should:
149	- Start with first task from Stage 1
150
151	---
152
153	## Architecture Quick Reference
154
155	[Include a simplified architecture diagram or component list from the system plan]
156
157	---
158
159	## Key Interfaces (for quick reference)
160
161	[Extract key interfaces/APIs from the system plan that the agent will need to implement]
162
163	---
164
165	## Notes & Decisions Log
166
167	Add notes here as implementation decisions are made
168
169	---
170
171	## Open Questions
172
173	[Copy from system plan or identify new ones]
174	```
175
176	### Progress Guidelines:
177
178	- Structure should make it easy for an agent to:
179	- Quickly understand current state
180	- Find the next task to work on
181	- Record what was done
182	- Track which PRD requirements have been satisfied
183	- Include enough architecture context that the agent doesn't need to re-read the full system plan every session
184	- Checklist items should map to PRD requirements where possible
185	- Leave session log empty - it will be filled as work progresses
186
187	---
188
189	## Step 4: Verify and Report
190
191	After creating both files:
192	1. Confirm both files were written successfully
193	2. Report the total number of requirements in the PRD
194	3. Report the number of development stages identified
195	4. List any open questions or ambiguities that need user clarification
196
197	---
198
199	## Important Notes
200
201	- The system plan is the source of truth - don't invent requirements not implied by the plan
202	- Be comprehensive - the agent will rely on these documents to know what to build
203	-

People who liked this also viewed

6 picks

Type