Self-Improve User Intent

VerifiedSafe

Transforms vague user requests into enriched descriptions with traceable sources. Essential for interpreting implicit intent and preparing context for agent generation.

Sby Skills Guide Bot
DevelopmentIntermediate
206/2/2026
Claude Code
#self-improve#intent-interpretation#context-synthesis#findings-extraction#task-clarification

Recommended for

Our review

Transforms vague user requests into structured, traceable descriptions of intent and findings.

Strengths

  • Clarifies ambiguous requests by extracting action, subject, and implicit assumptions.
  • Produces traceable findings with verifiable sources.
  • Assesses complexity to flag cases needing deeper analysis.

Limitations

  • Heavily dependent on the quality of available context.
  • May require iterations if the intent is too vague.
  • Does not replace human validation for critical decisions.
When to use it

Use when the user request is ambiguous, incomplete, or needs refinement before proceeding.

When not to use it

Avoid for already clear and specific tasks where additional interpretation is unnecessary.

Security analysis

Safe
Quality score85/100

The skill only uses the Read tool, performing no destructive or exfiltrating actions. It interprets user intent and synthesizes context without executing code or accessing sensitive data.

No concerns found

Examples

Improve login system
I want to make the login system more secure. What should I focus on?
Identify bug in payment module
There's a bug in the payment module that sometimes causes double charges. Can you help me understand the issue?

name: self-improve description: Transforms simple user requests into enriched descriptions with traceable findings. Use when interpreting vague user intent, preparing context for agent generation, or synthesizing actionable insights from available project context. allowed-tools: Read

Self-Improve

Transform user intent into actionable understanding.

Core Function

User Intent + Available Context → Enriched Description

Behavior

  • Specific intent → focused interpretation, targeted findings
  • Vague intent → broader scan, note what clarification needed

Process

1. Interpret Intent

Extract from user request:

  • Action: What to do
  • Subject: What to affect
  • Implicit: What's assumed but not said

2. Synthesize Findings

Connect intent with relevant context. Each finding:

[Discovery] → [source]

Requirements: traceable, relevant, actionable.

3. Assess Complexity

| Factor | Question | |--------|----------| | Scope | How much affected? | | Conflicts | Findings contradict? | | Trade-offs | Significant choices? |

Any factor high → flag for deeper analysis.

Output

## Intent
[Interpreted user intent]

## Findings
1. [Discovery] → [source]
2. [Discovery] → [source]
3. [Discovery] → [source]

## Complexity
[Simple | Needs analysis: scope/conflicts/trade-offs]
Related skills