- Home
- Skills
- Ratacat
- Claude Skills
- Technical Planning
technical-planning_skill
- Python
24
GitHub Stars
1
Bundled Files
2 months ago
Catalog Refreshed
4 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill ratacat/claude-skills --skill technical-planning- SKILL.md11.0 KB
Overview
This skill plans technical projects using a risk-first development approach, milestone structuring, and explicit managed deferral. I designed it to help teams define outcome-focused milestones, prioritize high-impact unknowns, and defer noncritical decisions until the last responsible moment. It emphasizes measurable success criteria and continuous validation.
How this skill works
The skill inspects project requirements and identifies technical risks, then produces a four-phase planning framework: Requirements & Risk Analysis, Milestone Planning, Implementation Strategy, and Execution Framework. It recommends sequencing milestones to resolve critical unknowns first, creating working proofs-of-concept, and documenting deferred items with target milestones. The output includes milestone goals, core tasks (outcome-focused), success criteria, risk mitigations, and a deferral registry.
When to use it
- Planning a new software project or greenfield architecture
- Defining milestones and delivery cycles for complex features
- Breaking down a large initiative into manageable, testable iterations
- Prioritizing work when technical feasibility is uncertain
- Aligning teams on what to defer vs. what to prove early
Best practices
- Focus task definitions on outcomes and constraints, not implementation steps
- Address highest-impact unknowns in Milestone 1 with proofs-of-concept
- Document deferred items, reasons, and target milestones for review
- Reserve 20–30% of sprint time for exploration and learning
- Measure success with predefined metrics and continuous validation
Example use cases
- Create a milestone plan that validates an external API integration before full implementation
- Structure a 12-week project into three 4-week cycles that each deliver working functionality
- Prioritize addressing performance bottlenecks with an early benchmark and prototype
- Plan feature rollouts where UI polish and optimizations are deferred until after user validation
- Onboard a team by defining clear success criteria and a risk register for initial milestones
FAQ
Decide early on user problems, success metrics, hard constraints, and critical integrations; defer algorithm, code organization, library choices, and polish until implementation reveals the best options.
How do I track deferred items?
Maintain a deferral registry listing each item, rationale, category (debt/polish/edge case), and the target milestone for re-evaluation or completion.
How long should milestones be?
Use 4–8 week cycles based on project complexity; ensure each milestone delivers testable, working functionality and resolves at least one high-risk unknown.