PR

prompt-optimizer

Converts loose user prompts into formal, concise task briefs.

Install

mkdir -p .claude/skills/prompt-optimizer-0langa && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18011" && unzip -o skill.zip -d .claude/skills/prompt-optimizer-0langa && rm skill.zip

Installs to .claude/skills/prompt-optimizer-0langa

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Use this skill only when the incoming prompt contains `optimize prompt first` (case-insensitive).
97 chars · catalog description✓ has a “when” trigger
Beginner

Key capabilities

  • Normalize user requests by removing filler and resolving shorthand
  • Extract explicit deliverables from raw user input
  • Lock technical and safety constraints for execution
  • Infer minimal assumptions to fill small gaps using repository context
  • Produce an internal execution brief with objective, scope, tasks, checks, risks, and mitigations
  • Show an optimized prompt section in the output

How it works

The skill processes raw user input by normalizing it, locking constraints, and inferring assumptions to generate an internal execution brief. It then presents an optimized prompt to the user.

Inputs & outputs

You give it
Raw user input containing 'optimize prompt first'
You get back
Execution-ready internal brief and an optimized prompt

When to use prompt-optimizer

  • Refine ambiguous tasks
  • Define project constraints before coding
  • Create structured execution plans

About this skill

Skill: Prompt Optimizer

Use this skill only when the incoming prompt contains optimize prompt first (case-insensitive).

Goal

Convert raw user input into an execution-ready internal brief that improves precision and delivery speed while preserving intent.

Workflow

  1. Normalize the request.
  • Remove filler.
  • Resolve obvious shorthand.
  • Extract explicit deliverables.
  1. Lock constraints.
  • Technical stack and architecture limits.
  • Safety limits (non-destructive operations, validation requirements).
  • Output expectations (code changes, tests, docs, summary).
  1. Infer minimal assumptions.
  • Fill small gaps using repository context.
  • Keep assumptions narrow and reversible.
  1. Produce internal execution brief.
  • Objective (one sentence)
  • Scope in / out
  • Concrete tasks
  • Acceptance checks
  • Risks and mitigations
  1. Execute from brief.
  • Start implementation immediately unless high-risk ambiguity exists.
  1. Show optimized prompt.
  • Include a visible Optimized Prompt section in output.
  • Keep it concise and faithful to original intent and requested scope.

Guardrails

  • Never change user intent.
  • Never add major requirements not requested.
  • Never block on questions when a safe assumption is possible.
  • Ask for clarification only when choices have non-obvious consequences.

When not to use it

  • When the incoming prompt does not contain 'optimize prompt first'
  • When the user intent needs to be changed
  • When major requirements not requested need to be added

Limitations

  • Never change user intent
  • Never add major requirements not requested
  • Ask for clarification only when choices have non-obvious consequences

How it compares

This workflow systematically refines user input into a structured brief and optimized prompt, providing a clear plan for execution, unlike directly attempting to fulfill an ambiguous request.

Compared to similar skills

prompt-optimizer side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
prompt-optimizer (this skill)03moNo flagsBeginner
prompt-optimizer435moNo flagsBeginner
prompt-optimize138moNo flagsAdvanced
ai-cost-optimizer94moCautionIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

prompt-optimizer

solatis

Optimize system prompts for Claude Code agents using proven prompt engineering patterns. Use when users request prompt improvement, optimization, or refinement for agent workflows, tool instructions, or system behaviors.

43147

prompt-optimize

YYH211

Expert prompt engineering skill that transforms Claude into "Alpha-Prompt" - a master prompt engineer who collaboratively crafts high-quality prompts through flexible dialogue. Activates when user asks to "optimize prompt", "improve system instruction", "enhance AI instruction", or mentions prompt engineering tasks.

13113

ai-cost-optimizer

ScientiaCapital

Save 40-70% on AI costs with intelligent multi-LLM routing. Automatically selects the optimal model based on task complexity across 40+ models from 8 providers.

990

prompt-library

davila7

Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks.

1169

context-compression

muratcankoylan

This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.

1350

prompt-lookup

f

Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.

738

Search skills

Search the agent skills registry