superplan

Name: superplan
Author: asteroid-belt

48stars2forks

How to install superplan?

asteroid-belt/skulto/superplan

$npx -y skills add asteroid-belt/skulto --skill superplan

Installs into the current project.

Summary

Use when starting significant features, epics, or complex tasks. Creates multi-phase implementation plans with parallelizable phases, poker estimates, TDD-first acceptance criteria, and quality gates. Detects tech stack from CLAUDE.md/AGENTS.md (bypassing internet research if com

Files · 1

View on GitHub

SKILL.md

1	# Superplan: Comprehensive Feature Planning
2
3	## Overview
4
5	Superplan creates detailed, executable implementation plans that enable parallel agent execution. Each plan includes everything needed to implement a feature: requirements, architecture, code changes, tests, and acceptance criteria.
6
7	## When to Use Superplan
8
9	- Starting a new feature or epic
10	- Complex tasks requiring multiple phases
11	- Tasks that could benefit from parallel execution by multiple agents
12	- When you need comprehensive documentation of implementation decisions
13	- When the team needs to understand the full scope before committing
14
15	## Core Workflow
16
17	```
18	┌─────────────────────────────────────────────────────────────────────┐
19	│ SUPERPLAN WORKFLOW │
20	├─────────────────────────────────────────────────────────────────────┤
21	│ 1. INTAKE → Gather story/requirements from user │
22	│ 2. DETECT → Check CLAUDE.md/AGENTS.md first, then scan │
23	│ (BYPASS codebase scan if docs complete) │
24	│ 3. INTERVIEW → Ask clarifying questions │
25	│ 4. RESEARCH → Look up best practices for DETECTED STACK │
26	│ (BYPASS if CLAUDE.md/AGENTS.md was complete) │
27	│ 5. EXPLORE → Understand existing codebase patterns │
28	│ (ALWAYS runs - never bypassed) │
29	│ 6. REFACTOR ASSESS → Evaluate if refactoring should precede work │
30	│ 7. ARCHITECT → Design solution with diagrams │
31	│ 8. PHASE → Break into parallelizable phases + ESTIMATES │
32	│ 9. DETAIL → Specify code deltas per phase │
33	│ 10. TEST → Define failing tests per phase (TDD) │
34	│ 11. DOCUMENT → Write plan to docs/<feature>-plan.md │
35	└─────────────────────────────────────────────────────────────────────┘
36	```
37
38	---
39
40	## CRITICAL: Parallel Execution with Sub-Agents
41
42	YOU MUST USE SUB-AGENTS OR PARALLEL TASKS for every parallelizable operation:
43
44	\| Operation \| How to Execute \|
45	\|-----------\|---------------\|
46	\| Independent file reads \| Launch multiple Read tasks in single message \|
47	\| Code searches \| Use Task tool with multiple Explore agents in parallel \|
48	\| Parallel phases (1A, 1B, 1C) \| Execute using parallel sub-agents \|
49	\| Independent test suites \| Run unit/integration/e2e concurrently \|
50
51	Example: "Launch 3 sub-agents in parallel to implement Phases 1A, 1B, and 1C"
52
53	IMPORTANT: Each sub-agent MUST return its conventional commit message upon completion. The main agent MUST output all commit messages to the user. See [Phase Completion: Conventional Commit Message](#phase-completion-conventional-commit-message---required-per-phase).
54
55	---
56
57	## Poker Planning Estimates
58
59	All tasks and phases MUST include Fibonacci estimates: 1, 2, 3, 5, 8, 13, 21
60
61	\| Size \| Meaning \| Example \|
62	\|------\|---------\|---------\|
63	\| 1 \| Trivial \| Config value, typo fix \|
64	\| 2 \| Small \| Single file, simple function \|
65	\| 3 \| Medium \| Multi-file, new component \|
66	\| 5 \| Large \| Feature module, API endpoint \|
67	\| 8 \| X-Large \| Complex feature with dependencies \|
68	\| 13 \| Epic chunk \| Major subsystem change \|
69	\| 21 \| Too big \| Split into smaller tasks \|
70
71	---
72
73	## Phase 1: INTAKE - Gather Requirements
74
75	### What You're Doing
76	Collecting the feature requirements from the user through story input.
77
78	### Actions
79
80	1. Ask the user to provide their story/requirements using one of these methods:
81	- Copy/paste the story text directly
82	- Provide a link to a ticket/story (Jira, Linear, GitHub Issue, etc.)
83	- Use an MCP tool to fetch the story if available
84	- Describe the feature verbally
85
86	2. Capture the raw input exactly as provided
87
88	3. Identify the story type:
89	- User Story (`As a <role>, I want <capability>, so that <benefit>`)
90	- Technical Task (implementation-focused)
91	- Bug Fix (problem/solution)
92	- Epic (large feature with sub-stories)
93
94	### Output
95	Document: Source, Type, Raw Requirements, Initial Understanding (1-2 sentences).
96
97	---
98
99	## Phase 2: DETECT - Technology Stack Analysis
100
101	### What You're Doing
102	Identifying the technology, programming language, and major frameworks to inform best practices research and quality gate setup.
103
104	### Detection Flow
105
106	```
107	┌─────────────────────────────────────────────────────────────────────────────┐
108	│ DETECT PHASE FLOW

People who liked this also viewed

6 picks

Type

superplan

48stars2forks

View on GitHub

How to install superplan?

asteroid-belt/skulto/superplan

$npx -y skills add asteroid-belt/skulto --skill superplan

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Superplan: Comprehensive Feature Planning
2
3	## Overview
4
5	Superplan creates detailed, executable implementation plans that enable parallel agent execution. Each plan includes everything needed to implement a feature: requirements, architecture, code changes, tests, and acceptance criteria.
6
7	## When to Use Superplan
8
9	- Starting a new feature or epic
10	- Complex tasks requiring multiple phases
11	- Tasks that could benefit from parallel execution by multiple agents
12	- When you need comprehensive documentation of implementation decisions
13	- When the team needs to understand the full scope before committing
14
15	## Core Workflow
16
17	```
18	┌─────────────────────────────────────────────────────────────────────┐
19	│ SUPERPLAN WORKFLOW │
20	├─────────────────────────────────────────────────────────────────────┤
21	│ 1. INTAKE → Gather story/requirements from user │
22	│ 2. DETECT → Check CLAUDE.md/AGENTS.md first, then scan │
23	│ (BYPASS codebase scan if docs complete) │
24	│ 3. INTERVIEW → Ask clarifying questions │
25	│ 4. RESEARCH → Look up best practices for DETECTED STACK │
26	│ (BYPASS if CLAUDE.md/AGENTS.md was complete) │
27	│ 5. EXPLORE → Understand existing codebase patterns │
28	│ (ALWAYS runs - never bypassed) │
29	│ 6. REFACTOR ASSESS → Evaluate if refactoring should precede work │
30	│ 7. ARCHITECT → Design solution with diagrams │
31	│ 8. PHASE → Break into parallelizable phases + ESTIMATES │
32	│ 9. DETAIL → Specify code deltas per phase │
33	│ 10. TEST → Define failing tests per phase (TDD) │
34	│ 11. DOCUMENT → Write plan to docs/<feature>-plan.md │
35	└─────────────────────────────────────────────────────────────────────┘
36	```
37
38	---
39
40	## CRITICAL: Parallel Execution with Sub-Agents
41
42	YOU MUST USE SUB-AGENTS OR PARALLEL TASKS for every parallelizable operation:
43
44	\| Operation \| How to Execute \|
45	\|-----------\|---------------\|
46	\| Independent file reads \| Launch multiple Read tasks in single message \|
47	\| Code searches \| Use Task tool with multiple Explore agents in parallel \|
48	\| Parallel phases (1A, 1B, 1C) \| Execute using parallel sub-agents \|
49	\| Independent test suites \| Run unit/integration/e2e concurrently \|
50
51	Example: "Launch 3 sub-agents in parallel to implement Phases 1A, 1B, and 1C"
52
53	IMPORTANT: Each sub-agent MUST return its conventional commit message upon completion. The main agent MUST output all commit messages to the user. See [Phase Completion: Conventional Commit Message](#phase-completion-conventional-commit-message---required-per-phase).
54
55	---
56
57	## Poker Planning Estimates
58
59	All tasks and phases MUST include Fibonacci estimates: 1, 2, 3, 5, 8, 13, 21
60
61	\| Size \| Meaning \| Example \|
62	\|------\|---------\|---------\|
63	\| 1 \| Trivial \| Config value, typo fix \|
64	\| 2 \| Small \| Single file, simple function \|
65	\| 3 \| Medium \| Multi-file, new component \|
66	\| 5 \| Large \| Feature module, API endpoint \|
67	\| 8 \| X-Large \| Complex feature with dependencies \|
68	\| 13 \| Epic chunk \| Major subsystem change \|
69	\| 21 \| Too big \| Split into smaller tasks \|
70
71	---
72
73	## Phase 1: INTAKE - Gather Requirements
74
75	### What You're Doing
76	Collecting the feature requirements from the user through story input.
77
78	### Actions
79
80	1. Ask the user to provide their story/requirements using one of these methods:
81	- Copy/paste the story text directly
82	- Provide a link to a ticket/story (Jira, Linear, GitHub Issue, etc.)
83	- Use an MCP tool to fetch the story if available
84	- Describe the feature verbally
85
86	2. Capture the raw input exactly as provided
87
88	3. Identify the story type:
89	- User Story (`As a <role>, I want <capability>, so that <benefit>`)
90	- Technical Task (implementation-focused)
91	- Bug Fix (problem/solution)
92	- Epic (large feature with sub-stories)
93
94	### Output
95	Document: Source, Type, Raw Requirements, Initial Understanding (1-2 sentences).
96
97	---
98
99	## Phase 2: DETECT - Technology Stack Analysis
100
101	### What You're Doing
102	Identifying the technology, programming language, and major frameworks to inform best practices research and quality gate setup.
103
104	### Detection Flow
105
106	```
107	┌─────────────────────────────────────────────────────────────────────────────┐
108	│ DETECT PHASE FLOW

People who liked this also viewed

6 picks

Type