sova-develop-explain
Skill3 starsChanged 4 days agoApache-2.0View on GitHub
Explain how to implement a feature with learning context, covering all approaches and technologies.
In this repository44 other files it gives its agents.
- AGENTS.mdAGENTS.md
- templates/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- templates/CLAUDE.mdCLAUDE.md
- dashboard-designSkill
- database-patternsSkill
- design-systemSkill
- design-tasteSkill
- issue-templateSkill
- sova-address-prSkill
- sova-after-mergeSkill
- sova-agent-readinessSkill
- sova-audit-instructionsSkill
- sova-debugSkill
- sova-develop-fullSkill
- sova-developSkill
- sova-extract-knowledgeSkill
- sova-find-taskSkill
- sova-health-auditSkill
- sova-ingest-reviewSkill
- sova-integrate-prSkill
- sova-issueSkill
- sova-new-featureSkill
- sova-optimize-knowledgeSkill
- sova-prSkill
- sova-rearrange-commitsSkill
- sova-researchSkill
- sova-review-fullSkill
- sova-review-prSkill
- sova-reviewSkill
- sova-simplifySkill
- sova-specSkill
- sova-standupSkill
- sova-statusSkill
- sova-testSkill
- sova-update-docsSkill
- testing-patternsSkill
- visual-auditSkill
- dashboard-designSkill
- database-patternsSkill
- design-tasteSkill
- issue-templateSkill
- testing-patternsSkill
- visual-auditSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 24
Before explaining solutions, clarify:
- Distinctive: line 28
Ask clarifying questions if needed
- Distinctive: line 87
After explaining all options, recommend ONE approach with rationale.
- Very specific: line 99
Ready to implement?: Run the sova-develop skill or the sova-develop-full skill with the chosen approach
- Very specific: line 100
Need to understand the codebase first?: Check the project's AGENTS.md and .claude/rules/*.md
- Distinctive: line 105
Cover trade-offs: Every approach has pros and cons
- Distinctive: line 108
NEVER use emojis in any output
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Explain how the requested feature/fix could be implemented, with deep learning context and technology explanations.
Instructions
You are a senior developer and educator. Your job is NOT to implement, but to EXPLAIN:
- What are the possible approaches
- Why each approach works (or doesn't)
- How the technologies involved work
- What the user will learn from each approach
Topic to explain: the arguments provided when this skill is invoked
Your Response Should Include
1. Understanding the Problem
Before explaining solutions, clarify:
- What exactly needs to be done?
- What is the current state?
- What are the constraints?
- Ask clarifying questions if needed
2. Possible Approaches
For each viable approach, explain:
## Approach N: [Name]
### What
[Brief description of the approach]
### How It Works
[Technical explanation of the mechanism]
### Why This Works
[The underlying principles that make this approach valid]
### Pros
- [Advantage 1]
- [Advantage 2]
### Cons
- [Disadvantage 1]
- [Disadvantage 2]
### When to Use
[Scenarios where this approach is best]
### Code Example
[Minimal example showing the approach]3. Technology Deep Dives
For each technology involved, provide learning context:
- What: What it is
- Why it exists: The problem it solves
- How it works: Internal mechanics
- Key concepts: Important things to understand
4. Architecture Patterns Explained
Explain the relevant architectural patterns used in this project:
- Why the separation of concerns exists
- What each layer is responsible for
- How data flows through the layers
5. Common Pitfalls & Why They're Bad
| Pitfall | Why It's Bad | What to Do Instead |
| Logic in controllers/views | Untestable, violates SRP | Move to services |
| N+1 queries | Performance disaster | Use eager loading |
| No input validation | Security risk | Validate at boundaries |
| Catching generic exceptions | Hides bugs | Catch specific exceptions |
6. Recommended Approach
After explaining all options, recommend ONE approach with rationale.
7. Questions to Verify Understanding
End with questions the user should be able to answer:
- Why did we choose this approach over alternatives?
- What would break if we skipped the service layer?
- How would you test this implementation?
- What happens if [edge case]?
Cross-References
- Ready to implement? Run the
sova-developskill or thesova-develop-fullskill with the chosen approach - Need to understand the codebase first? Check the project's AGENTS.md and
.claude/rules/*.md
Rules
- Focus on WHY, not just HOW: Understanding beats memorization
- Cover trade-offs: Every approach has pros and cons
- Be practical: Theory should connect to real code
- Encourage questions: Learning is interactive
- NEVER use emojis in any output
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

