Install
$ agentstack add skill-creoaurea-devlab-agentic-skills-roadmap ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Roadmap
Flat-file, git-versioned roadmap management. One YAML file is the source of truth. No external tools needed — agents and humans read the same file.
Hierarchy
Initiative (strategic theme, e.g., "Platform Launch")
└── Project (deliverable, e.g., "Auth System")
└── Milestone (checkpoints with exit criteria)
└── Epic (feature group)
└── Task (atomic work item, ≤1 day)
Each level has an id, title, status, and owner. Tasks also have estimate and priority.
Quick Start
Create a .project/roadmap.yaml at the project root:
roadmap:
title: "My Project Roadmap"
updated: 2026-03-18
initiatives:
- id: INIT-001
title: "MVP Launch"
status: in-progress
projects:
- id: PROJ-001
title: "Core API"
owner: "@team-backend"
milestones:
- id: MS-001
title: "API v1 Complete"
target_date: 2026-04-15
exit_criteria:
- "All CRUD endpoints passing integration tests"
- "Auth middleware deployed"
epics:
- id: EPIC-001
title: "User Management"
tasks:
- id: T-001
title: "User registration endpoint"
status: done
estimate: 0.5d
- id: T-002
title: "User profile CRUD"
status: in-progress
estimate: 1d
priority: high
Status Values
planned → in-progress → done
→ blocked (requires note)
→ cut (descoped, requires reason)
Prioritization
Use WSJF (Weighted Shortest Job First) for backlog ordering:
WSJF = (business_value + time_criticality + risk_reduction) / job_size
| Factor | Scale | |--------|-------| | businessvalue | 1-5 | | timecriticality | 1-5 | | riskreduction | 1-5 | | jobsize | 1-5 (1 = XS, 5 = XL) |
Higher WSJF → do first.
Progress Computation
milestone_progress = done_tasks / total_tasks
project_progress = avg(milestone_progress for each milestone)
initiative_progress = avg(project_progress for each project)
Count only done tasks. blocked and cut tasks are excluded from the denominator if they have exclude_from_progress: true.
Agent Workflow for Updates
When asked to update the roadmap:
- Read
.project/roadmap.yaml - Identify which tasks/milestones changed
- Update
statusandupdatedfields - Recompute progress for affected milestones/projects
- If a milestone's exit criteria are all met → mark it
done - Write the updated YAML back
When asked for status:
- Read the roadmap
- Compute progress at each level
- Report: what's done, what's in progress, what's blocked, what's next
Sprint Planning
For sprint-based teams, add a sprints section:
sprints:
- id: SPRINT-01
title: "Sprint 1"
start: 2026-03-18
end: 2026-03-29
goal: "Complete user registration flow"
tasks: [T-001, T-002, T-003]
velocity_planned: 8
velocity_actual: null # filled at sprint end
Integration Points
- Issue trackers — export tasks as GitHub Issues / Linear tickets
- CI/CD — milestone exit criteria map to CI pipeline gates
- Skills system — the
implementskill reads the roadmap to understand what to build next
For the full YAML schema definition with all fields and validation rules, read references/schemas.md.
Anti-Patterns
- Roadmap without exit criteria — milestones become meaningless checkboxes
- Tasks larger than 1 day — break them down; large tasks hide complexity
- No owner on projects — unowned work doesn't get done
- Updating the tool but not the file — the YAML file is the source of truth, always
- Planning everything upfront — plan one sprint ahead in detail, the rest in broad strokes
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: creoaurea-devlab
- Source: creoaurea-devlab/agentic-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.