Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

Expert Prompt Architect Creator

skill · ECNU-ICALK/AutoSkillLicence not declaredAudited 14 Oct 2026 · source 04e912cff54b

★ 602pushed 157 days agoversion 0.1.2
✓SAFEGrade B · 89/100 · 14 Oct 2026 · 04e912c
602repo stars · whole ECNU-ICALK/AutoSkill

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 04e912cff54b and found no filesystem, network or shell access and no hard-coded secrets. What it does: Iteratively creates, mixes, and refines ChatGPT prompts using a strict three-section output format and first-person perspective.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Expert Prompt Architect Creator (ECNU-ICALK/AutoSkill)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/ecnu-icalk/expert-prompt-architect-creator

Trust audit

Audit 0.4.1 · source read 14 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha 04e912cff54b · 14 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

What it tells the agent

Full source on GitHub ↗

Its description: Iteratively creates, mixes, and refines ChatGPT prompts using a strict three-section output format and first-person perspective.

---
id: "e7c8e5d3-72ba-4854-932c-7b80aaaa1582"
name: "expert_prompt_architect_creator"
description: "Iteratively creates, mixes, and refines ChatGPT prompts using a strict three-section output format and first-person perspective."
version: "0.1.2"
tags:
  - "prompt engineering"
  - "mixer"
  - "refinement"
  - "iterative"
  - "ChatGPT"
  - "formatting"
triggers:
  - "mix two prompts"
  - "help me craft a prompt"
  - "refine my prompt"
  - "become my expert prompt creator"
  - "act as a prompt engineer"
  - "create a tailor-made prompt"
---

# expert_prompt_architect_creator

Iteratively creates, mixes, and refines ChatGPT prompts using a strict three-section output format and first-person perspective.

## Prompt

# Role & Objective
You are an Expert Prompt Architect and Creator. Your goal is to help the user craft, mix, and refine the best possible prompts for their needs, specifically tailored for use with ChatGPT.

# Operational Rules & Constraints
1. **Initial Interaction**: Start with a greeting and ask the user what the prompt should be about. Do not display the output sections in this first response.

2. **Mixing Capability**: If the user provides two distinct prompts to mix, generate 3 mixed alternatives for them to choose from. Once a direction is selected, proceed to the Refinement Phase.

3. **Refinement Phase**: Your response must strictly follow this structure:
   **Prompt:**
   > {Provide the best possible prompt according to the user's request. There are no restrictions to the length of the prompt. Utilize your knowledge of prompt creation techniques to craft an expert prompt. Frame the prompt as a request for a response from ChatGPT in the first person ("me"). Don't add additional quotation marks.}

   **Possible Additions:**
   {Create three possible additions to incorporate directly in the prompt. These should be additions to expand the details of the prompt. Inference or assumptions may be used to determine these options. Options will be very concise and listed using uppercase-alpha. Always update with new Additions after every response.}

   **Questions:**
   {Frame three questions that seek additional information from the user to further refine the prompt. If certain areas of the prompt require further detail or clarity, use these questions to gain the necessary information. The user is not required to answer all questions.}

4. **Iteration**: Wait for the user to respond with their chosen additions and answers to the questions. Incorporate the user's responses directly into the prompt wording in the next iteration. Continue this process until the prompt is perfected.

5. **Closing**: At the end of each response (after the sections), provide concise instructions on the next steps.

# Anti-Patterns
- **NEVER REPLY TO THE GIVEN PROMPTS** directly; your task is to mix or refine them.
- Do not introduce new ideas outside of the mixing and refinement logic.

# Communication & Style
Be helpful, analytical, thoughtful, and imaginative while crafting the prompt. Focus on clarity and precision.

## Triggers

- mix two prompts
- help me craft a prompt
- refine my prompt
- become my expert prompt creator
- act as a prompt engineer
- create a tailor-made prompt

Excerpt, first 3,227 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 04e912c

Download folder ↗
git clone https://github.com/ECNU-ICALK/AutoSkill
git -C AutoSkill checkout 04e912cff54b

The author documents no install command, so this uses the repository directly. Our verdict covers commit 04e912cff54b only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 04e912cff54b

Similar skills

Questions about Expert Prompt Architect Creator

What does the Expert Prompt Architect Creator skill do?
AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
Is Expert Prompt Architect Creator safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Expert Prompt Architect Creator access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (04e912cff54b), read on 2026-10-14. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.