danieldekay/ai-ops/project-planning
- community
Checking that the SKILL.md file is still in the repository.
Strategic project planning system for creating and maintaining planning artifacts. Use when creating or updating vision, roadmap, epics, backlog, project status dashboards, or milestone reviews. Use when breaking down large goals into actionable work. Use when triaging scope (L1 spec / L2 task-batch / L3 quick-fix). Templates live in this skill's templates/ directory. NOT for spec-kit artifacts (spec.md, plan.md, tasks.md) — those belong to speckit agents.
Install
npx vskill@latest install danieldekay/ai-ops/project-planningSKILL.md
Project Planning Skill
Strategic planning system that produces living planning documents. Covers everything ABOVE the spec level: vision, roadmap, epics, backlog, status dashboards, and milestone reviews.
When To Use This Skill
- Creating a new project's planning structure from scratch
- Writing or updating a vision, roadmap, epic, backlog, or status dashboard
- Running a milestone review or checkpoint
- Triaging work into L1 (spec) / L2 (task-batch) / L3 (quick-fix)
- Extracting deferred items from specs into a centralized backlog
When NOT To Use This Skill
- Writing spec.md, plan.md, tasks.md → use speckit agents
- Implementing code → use spec-implementer or direct coding
- Reviewing code → use Code Review Agent
The Planning Hierarchy
Every piece of work enters the hierarchy and gets triaged by size before execution.
Artifact Catalog
| Artifact | Template | When To Create | Update Frequency | |
|---|---|---|---|---|
| Planning Session | templates/planning-session.md | Every planner session | Once (immutable snapshot) | |
| Vision | templates/vision.md | Once per project | Rarely (strategy shifts) | |
| Roadmap | templates/roadmap.md | Once per project | When priorities change | |
| Epic | templates/epic.md | Per capability group (5–15 specs) | When epic scope changes | |
| Project Status | templates/project-status.md | Once per project | After any spec work | |
| Backlog | templates/backlog.md | Once per project | When completing or discovering items | |
| Milestone Review | templates/milestone-review.md | At each milestone boundary | Once (snapshot) |
Using Templates
- Read the template from
templates/<name>.md - Replace all
{{PLACEHOLDER}}values with project-specific content - Write to the target location (see File Locations below)
- Remove any template sections that don't apply
Planning Session Artifacts (Mandatory)
Every planner session MUST produce a dated session artifact at:
Examples:
plan/sessions/2026-03-02-situation-assessment.mdplan/sessions/2026-03-02-epic-05-breakdown.mdplan/sessions/2026-03-02-backlog-extraction.md
This creates a searchable history of planning decisions even when the main artifacts (ROADMAP, BACKLOG) are updated in-place.
Work Item Triage (L1 / L2 / L3)
See references/triage-rules.md for the complete decision tree.
Quick version:
- L1 Spec: New domain entities, cross-layer changes, 3+ user stories →
speckit.specify - L2 Task-Batch: Clear scope, no new domain concepts, 1–3 sessions → entry in backlog
- L3 Quick-Fix: Single file, <30 min, near-zero risk → just do it
When uncertain, default to L2. You can promote to L1 if complexity emerges. L1 → L2 is rare and indicates overscoping.
Backlog Management
Extracting Deferred Items
To build or refresh a backlog:
- Scan all
specs/*/future-improvements.mdfiles - Scan
plan/MVP-CHECKLIST.mdfor open blockers - Check each spec for incomplete phases or user stories
- Consolidate into
plan/BACKLOG.mdusing the backlog template - Assign IDs:
BLK-NNN(blocker),RDY-NNN(ready),SCP-NNN(needs scoping),DEF-NNN(deferred) - Assign effort level: L1, L2, or L3
Prioritization Framework
- Blockers — anything preventing other work
- Current branch — finish before starting new
- Critical path — items on the path to launch
- Multipliers — features that unlock many others
- Quick wins — high value, low effort
- Nice-to-haves — someday/maybe
Creating New Epics
Epics group 5–15 related specs into a coherent capability. Use templates/epic.md.
Rules:
- Every spec MUST belong to exactly one epic
- Epic names describe a capability, not a feature (e.g., "Entity Expansion" not "Add People")
- Include dependency links to other epics
- Track completion as aggregate of contained spec statuses
Milestone Reviews
At milestone boundaries, create a review using templates/milestone-review.md:
- What was planned vs. delivered
- What slipped and why
- Backlog items discovered during the milestone
- Scope changes for the next milestone
- Updated risk assessment
File Locations
Planning artifacts live in plan/:
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/project-planning/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/danieldekay/ai-ops/project-planning)