Roadmap Management logo

Roadmap Management

OrganizationPopular
a5c-ai
roadmap-management

Roadmap parsing, analysis, and mutation operations for ROADMAP.md. Handles phase and milestone lifecycle including add, insert (decimal), remove, complete, and requirements coverage analysis.

Overview

Publishera5c-ai
Repositorybabysitter
Skill nameroadmap-management
Stars
1.8K
Forks
112
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by a5c-ai on GitHub. Read the source before you install it.

Installation

Install the Roadmap Management AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/a5c-ai/babysitter/tree/main/library/methodologies/gsd/skills/roadmap-management
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/a5c-ai/babysitter.git /tmp/babysitter
mkdir -p .claude/skills
cp -r /tmp/babysitter/library/methodologies/gsd/skills/roadmap-management .claude/skills/roadmap-management
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Roadmap Management in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Roadmap Management on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Roadmap Management is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

  • Milestones (versioned deliverables, e.g., v1.0, v2.0)
  • Phases within each milestone (numbered execution units)
  • Requirements mapped to phases (100% coverage guarantee)
  • Phase dependencies and ordering
  • Phase status tracking (planned/in-progress/completed/verified)

This skill combines the original lib/roadmap.cjs and lib/phase.cjs modules. It handles all roadmap mutations: adding phases, inserting decimal phases for urgent work, removing phases with renumbering, and marking phases complete.

Capabilities

1. Parse Roadmap

Parse ROADMAP.md into structured data:

markdown
# Roadmap

## Milestone v1.0: MVP Launch

### Phase 70: Project Setup
- **Status**: completed
- **Requirements**: R1 (project scaffolding), R2 (dev environment)
- **Deliverables**: Package.json, tsconfig, eslint config, CI pipeline

### Phase 71: Database Layer
- **Status**: completed
- **Requirements**: R3 (data model), R4 (migrations)
- **Deliverables**: Schema definitions, migration scripts, seed data

### Phase 72: Authentication
- **Status**: in-progress
- **Requirements**: R5 (user auth), R6 (OAuth2)
- **Deliverables**: Login flow, token management, middleware

### Phase 73: API Endpoints
- **Status**: planned
- **Requirements**: R7 (REST API), R8 (validation)
- **Deliverables**: CRUD endpoints, input validation, error handling

## Milestone v2.0: Enhanced Features
...

Parsed result:

json
{
  "milestones": [
    {
      "version": "v1.0",
      "title": "MVP Launch",
      "phases": [
        { "number": 70, "title": "Project Setup", "status": "completed", "requirements": ["R1", "R2"] },
        { "number": 71, "title": "Database Layer", "status": "completed", "requirements": ["R3", "R4"] },
        { "number": 72, "title": "Authentication", "status": "in-progress", "requirements": ["R5", "R6"] },
        { "number": 73, "title": "API Endpoints", "status": "planned", "requirements": ["R7", "R8"] }
      ]
    }
  ]
}

2. Add Integer Phase

Append a new phase to the end of the current milestone:

add_phase(
  milestone: "v1.0",
  title: "Admin Dashboard",
  requirements: ["R12", "R13"],
  deliverables: "Admin UI, user management, analytics"
)
-> Phase 74: Admin Dashboard (appended after Phase 73)

3. Insert Decimal Phase

Insert a phase between existing phases for urgent work:

insert_phase(
  after: 72,
  title: "Fix Auth Token Refresh",
  requirements: ["R5.1"],
  deliverables: "Token refresh logic, session persistence"
)
-> Phase 72.1: Fix Auth Token Refresh (inserted between 72 and 73)

Decimal phases:

  • 72.1 is between 72 and 73
  • 72.2 is between 72.1 and 73
  • Multiple decimals can exist between any two integer phases

4. Remove Phase and Renumber

Remove a future phase and renumber subsequent phases:

remove_phase(73)
-> Phase 73 removed
-> Phase 74 renumbered to Phase 73
-> All references updated

Only future (planned) phases can be removed. Completed and in-progress phases cannot be removed.

5. Mark Phase Complete

Update phase status in the roadmap:

complete_phase(72)
-> Phase 72 status: completed
-> If all phases in milestone completed -> milestone ready for audit

Status transitions:

  • planned -> in-progress (when planning begins)
  • in-progress -> completed (when execution finishes)
  • completed -> verified (when verification passes)

6. Requirements Coverage Analysis

Verify 100% requirement coverage across phases:

coverage_analysis()
-> Total requirements: 13
-> Mapped to phases: 13
-> Unmapped: 0
-> Coverage: 100%

-> R1: Phase 70 (completed)
-> R2: Phase 70 (completed)
-> R5: Phase 72 (in-progress)
-> R5.1: Phase 72.1 (planned)
...

7. Phase Dependency Resolution

Determine execution order based on dependencies:

dependency_graph()
-> Phase 70: no dependencies (can start immediately)
-> Phase 71: depends on Phase 70
-> Phase 72: depends on Phase 71
-> Phase 72.1: depends on Phase 72
-> Phase 73: depends on Phase 71 (not 72, can parallelize)

8. Milestone Scope Determination

Determine which phases belong to a milestone:

milestone_scope("v1.0")
-> Phases: [70, 71, 72, 72.1, 73]
-> Total: 5 phases
-> Completed: 2
-> In Progress: 1
-> Planned: 2
-> Progress: 40%

9. Phase Status Queries

Query phases by status:

phases_by_status("completed") -> [70, 71]
phases_by_status("in-progress") -> [72]
phases_by_status("planned") -> [72.1, 73]
next_phase() -> 72.1 (first planned phase after current)

Tool Use Instructions

Parsing Roadmap

  1. Use Read to load .planning/ROADMAP.md
  2. Parse markdown headings to identify milestones (## level) and phases (### level)
  3. Extract status, requirements, and deliverables from bullet points under each phase
  4. Return structured milestone/phase hierarchy

Adding a Phase

  1. Parse current roadmap to find last phase number in target milestone
  2. Generate new phase number (last + 1)
  3. Format phase section following existing pattern
  4. Use Edit to insert before the next milestone heading or end of file

Inserting a Decimal Phase

  1. Parse roadmap to find the target phase and next phase
  2. Calculate decimal number (e.g., 72.1 if inserting after 72)
  3. Format phase section
  4. Use Edit to insert between the two phases

Requirements Coverage

  1. Parse ROADMAP.md for all phase requirement mappings
  2. Use Read to load .planning/REQUIREMENTS.md for full requirement list
  3. Compare mapped requirements against full list
  4. Report coverage percentage and any gaps

Process Integration

  • new-project.js - Create initial ROADMAP.md with milestone and phase structure
  • progress.js - Read roadmap for progress display and next-action routing
  • complete-milestone.js - Determine milestone scope, verify all phases complete
  • audit-milestone.js - Read phase scope for audit, requirements coverage check
  • plan-phase.js - Read phase requirements and deliverables for planning context
  • add-phase command - Add integer phase via this skill
  • insert-phase command - Insert decimal phase via this skill
  • remove-phase command - Remove phase via this skill

Output Format

json
{
  "operation": "parse|add|insert|remove|complete|coverage|dependencies|scope|query",
  "status": "success|error",
  "roadmap": {
    "milestoneCount": 2,
    "totalPhases": 8,
    "currentMilestone": "v1.0"
  },
  "phase": {
    "number": 72,
    "title": "Authentication",
    "status": "completed",
    "requirements": ["R5", "R6"]
  },
  "coverage": {
    "total": 13,
    "mapped": 13,
    "percentage": 100,
    "gaps": []
  }
}

Configuration

SettingDefaultDescription
roadmapFile.planning/ROADMAP.mdPath to ROADMAP.md
requirementsFile.planning/REQUIREMENTS.mdPath for coverage analysis
startingPhaseNumber70First phase number for new projects
allowDecimalPhasestrueEnable decimal phase insertion
autoStatusTransitiontrueAuto-update phase status on events

Error Handling

ErrorCauseResolution
ROADMAP.md not foundPlanning directory not initializedRun new-project first
Phase not foundReferenced phase does not existCheck phase number, list available phases
Cannot remove active phaseTrying to remove in-progress/completed phaseOnly planned phases can be removed
Duplicate phase numberPhase number already existsUse next available number or decimal
Coverage gap detectedRequirements not mapped to any phaseAdd phase or update existing phase to cover requirement
Circular dependencyPhase depends on itself or cycle existsReview dependency graph, break cycle

Constraints

  • ROADMAP.md must remain human-readable markdown at all times
  • Phase numbers must be positive (integer or decimal with one decimal place)
  • Requirements coverage must be 100% before milestone can be audited
  • Phase removal triggers automatic renumbering of subsequent phases
  • Status transitions are one-directional (cannot go from completed back to planned)
  • Decimal phases are temporary (should be consolidated into integer phases at milestone completion)
  • All roadmap mutations must be committed via git-integration skill

Frequently asked questions

What does the Roadmap Management AI skill do?

Roadmap parsing, analysis, and mutation operations for ROADMAP.md. Handles phase and milestone lifecycle including add, insert (decimal), remove, complete, and requirements coverage analysis.

Why use Roadmap Management on TypingMind?

Because you install it once and use it with any model. Roadmap Management is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Roadmap Management in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/a5c-ai/babysitter/tree/main/library/methodologies/gsd/skills/roadmap-management. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Roadmap Management?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Roadmap Management?

As many as you like. As long as a model supports skills, you can use Roadmap Management with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Roadmap Management AI skill free?

Yes. It is published on GitHub by a5c-ai under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇