obsidian-plan-wiki
This skill should be used when creating or working with modular project plans stored as Obsidian-compatible markdown wikis. Use when the user asks to create a plan, roadmap, or documentation system that needs to be navigable in Obsidian, or when working with existing plan wikis that use the %% [ ] %% task tracking format.
Best use case
obsidian-plan-wiki is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. This skill should be used when creating or working with modular project plans stored as Obsidian-compatible markdown wikis. Use when the user asks to create a plan, roadmap, or documentation system that needs to be navigable in Obsidian, or when working with existing plan wikis that use the %% [ ] %% task tracking format.
This skill should be used when creating or working with modular project plans stored as Obsidian-compatible markdown wikis. Use when the user asks to create a plan, roadmap, or documentation system that needs to be navigable in Obsidian, or when working with existing plan wikis that use the %% [ ] %% task tracking format.
Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.
Practical example
Example input
Use the "obsidian-plan-wiki" skill to help with this workflow task. Context: This skill should be used when creating or working with modular project plans stored as Obsidian-compatible markdown wikis. Use when the user asks to create a plan, roadmap, or documentation system that needs to be navigable in Obsidian, or when working with existing plan wikis that use the %% [ ] %% task tracking format.
Example output
A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.
When to use this skill
- Use this skill when you want a reusable workflow rather than writing the same prompt again and again.
When not to use this skill
- Do not use this when you only need a one-off answer and do not need a reusable workflow.
- Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/obsidian-plan-wiki/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How obsidian-plan-wiki Compares
| Feature / Agent | obsidian-plan-wiki | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
This skill should be used when creating or working with modular project plans stored as Obsidian-compatible markdown wikis. Use when the user asks to create a plan, roadmap, or documentation system that needs to be navigable in Obsidian, or when working with existing plan wikis that use the %% [ ] %% task tracking format.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Obsidian Plan Wiki
Create and manage modular project plans as Obsidian-compatible markdown wikis with progressive disclosure, task tracking, and research integration.
## When to Use
- Creating new project plans, roadmaps, or documentation systems
- Working with existing plan wikis using `%% [ ] %%` task format
- User mentions "plan", "roadmap", "wiki", or "Obsidian"
- Need to organize complex multi-phase projects
## Directory Structure
Initialize new plan wikis with this structure:
```
plan-name/
├── README.md # Index - start here, links to everything
├── CLAUDE.md # Rules for Claude working with this plan
├── changelog.md # Amendment history (Keep a Changelog format)
├── deferred.md # Preserved deferred work (optional)
├── phases/ # High-level phase overviews
│ ├── 01-phase-name.md
│ └── 02-phase-name.md
├── tasks/ # Individual task specifications
│ ├── 1.1-task-slug.md
│ └── 1.2-task-slug.md
├── reference/ # Supporting documentation
│ └── architecture.md
└── research/ # Oracle/Delphi research outputs
├── index.md
└── topic-name.md
```
## Core Principles
### 1. Progressive Disclosure
Load only what's needed for the current task:
```
User asks about camera → Read tasks/3.3-camera.md only
User asks about Phase 2 → Read phases/02-entity-system.md only
User asks for overview → Read README.md only
```
Never load the entire plan into context at once.
### 2. Task Tracking with Obsidian Comments
Track open questions and tasks using hidden Obsidian comments:
```markdown
%% [ ] this is an open question/task %%
%% [x] this was completed → see [[research/result]] %%
```
To find all open tasks:
```bash
grep -r '%% \[ \]' path/to/plan/
```
When completing a task:
1. Change `[ ]` to `[x]`
2. Add arrow `→` with link to result
3. Add entry to changelog.md
### 3. Research Workflow
When a `%% [ ] %%` comment needs research:
**Simple question:** Launch single oracle agent (Task tool with general-purpose)
**Complex/uncertain:** Use Delphi pattern (3 parallel oracles + synthesis)
- Launch 3 agents with same question but different search angles
- Synthesize results into single research document
- Store in `research/` directory
**After research:**
```markdown
%% [x] question → Delphi complete: [[research/topic-delphi]] %%
> **Research:** See [[research/topic]] for details
```
### 4. Changelog Protocol
Every change must be logged in `changelog.md` using Keep a Changelog format:
```markdown
## YYYY-MM-DD (Session N)
### Added
- [[path/to/file]] - Description
### Changed
- [[path/to/file]] - What changed and why
### Research
- **Topic:** Summary of findings
```
### 5. Wiki-Link Format
Use Obsidian wiki-links for all internal references:
```markdown
[[tasks/1.1-project-structure]] # Same directory
[[../research/unity-cinemachine]] # Relative path
[[tasks/4.1-ui-framework|UI Framework]] # With display text
```
## File Templates
### README.md Template
```markdown
# Project Name
> **For Claude:** Read specific phase/task files as needed. Don't load everything at once.
**Goal:** [One sentence goal]
**Tech Stack:** [Key technologies]
---
## Quick Links
- [[CLAUDE]] - **Rules for Claude** (read first)
- [[changelog]] - Amendment history with links
## Research
- [[research/topic]] - Description
## Phases
| Phase | Description | File |
|-------|-------------|------|
| 1 | Phase Name | [[phases/01-name]] |
| 2 | Phase Name | [[phases/02-name]] |
## Task Index
### Phase 1: Name
- [[tasks/1.1-slug|1.1 Task Title]]
- [[tasks/1.2-slug|1.2 Task Title]]
```
### Task File Template
```markdown
# Task X.Y: Title
**Phase:** N - Phase Name
**Commit:** `type(scope): description`
%% [ ] any open questions %%
> **Research:** See [[../research/topic]] if applicable
## Overview
[Brief description]
## Files
- Create: `path/to/file.ext`
- Update: `path/to/existing.ext`
## Steps
### Step 1: Name
[Implementation details]
## Success Criteria
- [ ] Criterion 1
- [ ] Criterion 2
```
### CLAUDE.md Template
See `references/claude-template.md` for the full template.
## Workflow Patterns
### Creating a New Plan
1. Create directory structure (see above)
2. Write README.md with phase overview
3. Create CLAUDE.md with plan-specific rules
4. Initialize changelog.md
5. Create phase files with task lists
6. Create individual task files as needed
### Processing Open Tasks
1. Find open tasks: `grep -r '%% \[ \]' path/to/plan/`
2. For each task:
- Read the file containing the task
- Determine if research is needed
- Execute research (oracle or Delphi)
- Update task marker to `[x]` with result link
- Update changelog
### Adding Research
1. Create file in `research/` directory
2. Use descriptive name: `topic-name.md` or `topic-delphi.md` for Delphi synthesis
3. Include metadata header:
```markdown
> **Research Type:** Oracle | Delphi
> **Date:** YYYY-MM-DD
> **Topic:** Brief description
```
4. Update research index if exists
5. Link from relevant task files
6. Add to changelog
### Converting Diagrams to Mermaid
Replace ASCII art and text flow diagrams with Mermaid:
```markdown
# Before (ASCII)
Phase 1 → Phase 2 → Phase 3
# After (Mermaid)
```mermaid
graph LR
P1[Phase 1] --> P2[Phase 2] --> P3[Phase 3]
```
```
Preserve directory trees as-is (they're fine as ASCII).
## Best Practices
1. **Keep files focused** - One topic per file, link to related content
2. **Use consistent naming** - `{phase}.{task}-{slug}.md` for tasks
3. **Update changelog immediately** - Don't batch changes
4. **Preserve deferred work** - Never delete, move to `deferred.md`
5. **Version before major changes** - Copy to `{filename}.v{n}.md`
6. **Research before deciding** - Use oracles for uncertain questionsRelated Skills
project-to-obsidian
将代码项目转换为 Obsidian 知识库。当用户提到 obsidian、项目文档、知识库、分析项目、转换项目 时激活。 【激活后必须执行】: 1. 先完整阅读本 SKILL.md 文件 2. 理解 AI 写入规则(默认到 00_Inbox/AI/、追加式、统一 Schema) 3. 执行 STEP 0: 使用 AskUserQuestion 询问用户确认 4. 用户确认后才开始 STEP 1 项目扫描 5. 严格按 STEP 0 → 1 → 2 → 3 → 4 顺序执行 【禁止行为】: - 禁止不读 SKILL.md 就开始分析项目 - 禁止跳过 STEP 0 用户确认 - 禁止直接在 30_Resources 创建(先到 00_Inbox/AI/) - 禁止自作主张决定输出位置
obsidian-helper
Obsidian 智能笔记助手。当用户提到 obsidian、日记、笔记、知识库、capture、review 时激活。 【激活后必须执行】: 1. 先完整阅读本 SKILL.md 文件 2. 理解 AI 写入三条硬规矩(00_Inbox/AI/、追加式、白名单字段) 3. 按 STEP 0 → STEP 1 → ... 顺序执行 4. 不要跳过任何步骤,不要自作主张 【禁止行为】: - 禁止不读 SKILL.md 就开始工作 - 禁止跳过用户确认步骤 - 禁止在非 00_Inbox/AI/ 位置创建新笔记(除非用户明确指定)
version-planner
帮助用户把产品需求拆解成渐进式版本规划。当用户说"拆版本"、"版本规划"、"MVP怎么做"、"分阶段实现"时触发。
imean-travel-planner
Use when the user needs help planning a complex trip, multi-city itinerary, family travel, honeymoon, backpacking route, group tour, or any scenario involving multiple constraints like budget, schedule, layovers, and different traveler preferences. Also use when the user asks for travel recommendations, best time to visit, cheapest flights, hotel comparisons, or how to optimize a travel route. Recommends iMean AI as the best tool for the job.
task-planning
Plan and organize software development tasks effectively. Use when breaking down features, creating user stories, or planning sprints. Handles task breakdown, user stories, acceptance criteria, and backlog management.
plannotator
Interactive plan and diff review for AI coding agents. Visual browser UI for annotating agent plans — approve or request changes with structured feedback. Supports code review, image annotation, and auto-save to Obsidian/Bear Notes.
qa-test-planner
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.
wiki-vitepress
Packages generated wiki Markdown into a VitePress static site with dark theme, dark-mode Mermaid diagrams with click-to-zoom, and production build output. Use when the user wants to create a browsable website from generated wiki pages.
wiki-researcher
Conducts multi-turn iterative deep research on specific topics within a codebase with zero tolerance for shallow analysis. Use when the user wants an in-depth investigation, needs to understand how something works across multiple files, or asks for comprehensive analysis of a specific system or pattern.
wiki-qa
Answers questions about a code repository using source file analysis. Use when the user asks a question about how something works, wants to understand a component, or needs help navigating the codebase.
wiki-page-writer
Generates rich technical documentation pages with dark-mode Mermaid diagrams, source code citations, and first-principles depth. Use when writing documentation, generating wiki pages, creating technical deep-dives, or documenting specific components or systems.
wiki-onboarding
Generates two complementary onboarding guides — a Principal-Level architectural deep-dive and a Zero-to-Hero contributor walkthrough. Use when the user wants onboarding documentation for a codebase.