design-solution

Converge from multiple options to a single recommended approach.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "design-solution" with this command: npx skills add kasperjunge/agent-resources/kasperjunge-agent-resources-design-solution

Design Solution

Converge from multiple options to a single recommended approach.

Position in Workflow

Step 3 of development workflow:

  • /research

  • Understand problem and constraints

  • /brainstorm-solutions

  • Explore solution space

  • /design-solution

  • Converge on a single solution (THIS)

  • Plan, code, review, ship

Core Principle

Decide deliberately. Evaluate trade-offs, align to constraints, and pick the best fit.

Input

Default: Use the options from the current conversation.

If argument provided:

  • File path: Read the file for brainstorming output

  • GitHub issue number/URL: Fetch with scripts/gh_issue_phase.sh get-issue $ARG

Workflow

  1. Reconfirm Context
  • Restate the problem, constraints, and success criteria.

  • Identify any missing information that blocks a decision.

  1. Evaluate Options

For each option, assess:

  • Pros: Benefits and what it enables

  • Cons: Risks and complexity

  • Codebase fit: Alignment with existing patterns

  • Effort: Low/Medium/High

  • Reversibility: Easy/Moderate/Hard to change later

  1. Decide
  • Rank options against success criteria.

  • Select a recommended option.

  • State conditions that would change the decision.

  1. Capture Open Questions

List unknowns that must be resolved before planning.

Output Format

Solution Decision

Context Summary

[Brief restatement of problem and key constraints]

Decision Criteria

[What matters most: performance, time, simplicity, extensibility, etc.]


Option Evaluation

Option 1: [Name] - Recommended

[Description]

Pros:

  • ...

Cons:

  • ...

Codebase fit: [How it aligns with existing patterns] Effort: [Low/Medium/High] Reversibility: [Easy/Moderate/Hard]

Option 2: [Name]

[Same structure]

Option 3: [Name]

[Same structure]


Recommendation

[Why the recommended option wins, and when you would choose differently]

Open Questions

[Anything that could change the recommendation]

Next Step

Ready to plan implementation. Enter Plan Mode or run /plan.

GitHub Issue Tracking

If a GitHub issue was provided or is available from prior phases:

Post design decision as a phase comment and set the label:

echo "$DESIGN_SUMMARY" | scripts/gh_issue_phase.sh post-phase $ISSUE design scripts/gh_issue_phase.sh set-label $ISSUE phase:design

Pass the issue number to the next skill (e.g., /make-plan #42 ).

Common Mistakes

Mistake Fix

Skipping decision criteria State criteria before evaluating

Over-weighting novelty Prefer codebase fit and simplicity

Ignoring reversibility Consider how hard it is to change later

Decision without evidence Call out unknowns explicitly

What NOT to Do

  • Do NOT re-brainstorm options

  • Do NOT proceed to planning without a chosen option

  • Do NOT hide assumptions or uncertainties

  • Do NOT ignore codebase constraints

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

brainstorm-solutions

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

refactor-for-determinism

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

commit-work

No summary provided by upstream source.

Repository SourceNeeds Review