Use this skill when the user wants to optimize, modify, or improve the system prompt of an AI agent. This includes requests like 'optimize the prompt', 'make the AI more focused on X', 'change the system prompt', 'improve the agent behavior', or 'modify how the AI responds'.
NewMaintained
Automatic
◆AI Engineer pack
Last verified 8/18/2026
What it changes
3 of 22 test cases passed with the skill.
Pass-rate lift
—
Tokens
+115%
Agent turns
0%
Response time
-8%
Model gemini-3.6-flashMeasured 8/18/2026v13 of 22 cases passed with skill · 3 comparable
Tokens, turns and time describe resource use, not a dollar price.
Lift withheld: 3 comparable cases; this report requires 8.
What's inside
The instructions your model reads when the skill loads.
SKILL.md83 linessingle file
Prompt Optimization Skill
This skill allows you to view and modify the system prompts of the current AI agent (Team).
Available Tools
get_team_prompt() — Get the current prompt and source mapping for the team
submit_prompt_changes(changes) — Send optimized prompts to the user for review
Workflow
Step 1: Get Current Prompts
Call get_team_prompt(). It returns:
team_id: The team's database ID
assembled_prompt: The full assembled prompt
sources: Array of prompt sources, each with:
type: "ghost" (base prompt) or "member" (team member prompt)
id: Resource ID (Ghost ID or Team ID)
name: Display name (Ghost name or Bot name)
field: Field name (e.g., "systemPrompt" or "prompt")
content: The actual prompt text
index: Member index (only for "member" type)
Step 2: Analyze and Rewrite
Based on the user's request, determine which source(s) need modification:
If the user wants to change the agent's core behavior → modify the ghost source
If the user wants to change a specific team member's role → modify the member source
You may modify multiple sources if needed
Rules:
Only modify the sources that are relevant to the user's request
Preserve the overall structure and intent of unrelated parts
Write complete, production-quality prompts (not just appending text)
If the original prompt is in Chinese, write the modification in Chinese
If the original prompt is in English, write the modification in English