Self-Improve Intent

VerifiedSafe

Enriches vague user requests by extracting intent, connecting with relevant context, and producing traceable findings. Helps when interpreting unclear instructions or preparing context for automated agents.

Sby Skills Guide Bot
ProductivityIntermediate
706/2/2026
Claude Code
#intent-interpretation#context-analysis#actionable-insights#traceable-findings

Recommended for

Our review

This skill transforms simple user requests into enriched descriptions with traceable findings by interpreting intent.

Strengths

  • Clarifies vague user requests
  • Produces traceable and actionable findings
  • Assesses complexity and flags issues
  • Connects user intent with project context

Limitations

  • Depends on quality of available project context
  • May misinterpret highly ambiguous requests
  • Limited by agent's semantic understanding
When to use it

Use when a user request is vague or incomplete and needs to be translated into an actionable, traceable plan.

When not to use it

Do not use when the request is already precise and no further clarification is needed, as it could add unnecessary overhead.

Security analysis

Safe
Quality score88/100

The skill only uses the Read tool, which is read-only and safe. It does not execute any code, nor does it access external resources. There are no destructive or exfiltrating actions.

No concerns found

Examples

Vague performance request
My application is too slow, help me fix it.
Unclear feature request
I want to add a new feature to my app.
Ambiguous debugging
There's a bug in my code, what should I do?

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