Helps maintain the project roadmap - a living documentation system that tracks what's planned, what shipped, and what was rejected.
/plugin marketplace add cameronsjo/claude-marketplace/plugin install essentials@cameronsjoThis skill inherits all available tools. When active, it can use any tool Claude has access to.
commands/roadmap.add.mdcommands/roadmap.suggest.mdHelps maintain the project roadmap - a living documentation system that tracks what's planned, what shipped, and what was rejected.
The roadmap is documentation that grows from planning. It bridges incoming work and completed features, providing institutional memory for humans and agents.
docs/roadmap/
├── README.md # Entry point - explains the system
├── ideas.md # Prioritized backlog (p0-p4)
├── research.md # Topics under investigation
├── completed/ # Shipped features - THE DOCS
│ └── {feature}.md
└── rejected/ # Decided against - WHY NOT
└── {feature}.md
research.md ──→ ideas.md ──→ (branch/PR) ──→ completed/{feature}.md
↓
rejected/{feature}.md
Git blame provides all date tracking.
| Item | Priority | Effort | Details |
|------|----------|--------|---------|
| Feature name | p1 | medium | Brief description |
Sorted by priority then item name.
| Item | Priority | Details |
|------|----------|---------|
| Topic | p1 | What needs investigation |
No effort - can't estimate what you don't understand.
# Feature Name
> One-line summary
## Status
- **Priority**: p1
- **Effort**: medium
- **Shipped**: version or date context
## Problem
What problem does this solve?
## Solution
How it works.
## Usage
How to use it.
## Related
- Links to other features
# Feature Name
> Rejected - brief reason
## Request
What users asked for.
## Decision
**Won't implement.**
## Reasoning
Why not.
## Alternatives
What to do instead.
| Value | Alias | Meaning |
|---|---|---|
p0 | Critical - drop everything | |
p1 | high | Core functionality, security |
p2 | medium | Nice to have |
p3 | low | Edge case, cosmetic |
p4 | Backlog, opportunistic |
| Value | Meaning |
|---|---|
small | < 1 day |
medium | 1-3 days |
large | > 3 days |
| Command | Purpose |
|---|---|
/roadmap | Review status, suggest next steps |
/roadmap.add <item> | Add to ideas or research |
/roadmap.suggest <item> | Return JSON (for subagents) |
/roadmap.spec <item> | Create detail file |
/roadmap.archive <item> | Move to completed/ or rejected/ |
/roadmap.dependencies <item> | Show blockers and unlocks |
/roadmap.metrics | Stats and distribution |
When feature ships:
completed/{feature}.md with full documentationWhen deciding against something:
rejected/{feature}.md with reasoningcompleted/ to understand existing functionalityrejected/ before suggesting previously-declined featuresUser: "Add caching to p2" → Add to ideas.md at p2 priority
User: "Research how auth should work" → Add to research.md
User: "Ship the plugin versioning feature" → Create completed/plugin-versioning.md, remove from ideas.md
User: "We're not doing cloud sync" → Create rejected/cloud-sync.md with reasoning
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.