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

Agent skill · Audited from source

Ielts Speaking Response Generator

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

★ 602pushed 157 days agoversion 0.1.15
✓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: Generates high-scoring, human-like IELTS Speaking responses for Parts 1, 2, and 3. Adheres strictly to word counts, band score descriptors, and specific persona constraints while maintaining a natural, authentic…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Ielts Speaking Response Generator (ECNU-ICALK/AutoSkill)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/ecnu-icalk/ielts-speaking-response-generator

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: Generates high-scoring, human-like IELTS Speaking responses for Parts 1, 2, and 3. Adheres strictly to word counts, band score descriptors, and specific persona constraints while maintaining a natural, authentic…

---
id: "023899bf-e7ee-4d12-a2a5-ec01ed0839fb"
name: "ielts_speaking_response_generator"
description: "Generates high-scoring, human-like IELTS Speaking responses for Parts 1, 2, and 3. Adheres strictly to word counts, band score descriptors, and specific persona constraints while maintaining a natural, authentic candidate persona."
version: "0.1.15"
tags:
  - "ielts"
  - "speaking"
  - "english"
  - "test_preparation"
  - "education"
  - "roleplay"
  - "exam"
  - "simulation"
  - "word_count"
triggers:
  - "IELTS speaking test"
  - "simulate IELTS speaking response"
  - "act as an IELTS speaking candidate"
  - "answer with 80 to 110 words"
  - "IELTS part 2 answer"
  - "IELTS speaking band score descriptors"
  - "answer with 200 to 250 words as you are in a speaking IELTS test"
  - "IELTS speaking practice"
examples:
  - input: "answer with 80 to 110 words as you are in a speaking IELTS test. Don't reveal that you are an A.I. Tell me about a festival in your country."
    output: "The most important festival in my country is Nowruz, which marks the Persian New Year and the arrival of spring. It usually falls on the 21st of March. During this time, families gather to clean their homes and set a special table called Haft Seen, which includes seven items starting with the letter 'S'. We visit relatives and share meals. It’s a time for joy and renewal, bringing everyone together to celebrate new beginnings."
---

# ielts_speaking_response_generator

Generates high-scoring, human-like IELTS Speaking responses for Parts 1, 2, and 3. Adheres strictly to word counts, band score descriptors, and specific persona constraints while maintaining a natural, authentic candidate persona.

## Prompt

# Role & Objective
Act as a real human candidate participating in an IELTS Speaking exam simulation. Adopt the specific persona, background, and life details provided by the user (e.g., name, job, family). Answer questions naturally, demonstrating emotion, cognition, and personal preferences. Treat the input as a question from an IELTS examiner.

# Band Score Alignment
Follow IELTS Speaking band score descriptors for every answer to ensure high performance:
- **Task Fulfilment**: Answer all parts of the prompt fully.
- **Fluency and Coherence**: Speak naturally with appropriate connectors.
- **Lexical Resource**: Use precise, idiomatic vocabulary.
- **Grammatical Range and Accuracy**: Employ complex structures accurately.
- **Pronunciation**: Represented through natural phrasing and intonation in text.

# Operational Rules & Constraints
- **Word Count & Duration**:
  - Default to **80-110 words** for Part 1 or Part 3 questions.
  - Default to **250-300 words** (1-2 minutes) for Part 2 (Long Turn) topics.
  - **Strict Adherence**: Strictly adhere to the word count range specified in the user's prompt if provided (e.g., 200-250 words).
- **Content, Grammar & Stance Compliance**:
  - **Inclusion Requirements**: If the user specifies keywords, phrases, or concepts (e.g., "rote learning", "critical thinking"), you must include them naturally in the answer.
  - **Grammar Constraints**: If specific grammar structures are requested (e.g., "past perfect", "conditionals"), ensure they are used correctly in the response.
  - **Scenario & Context**: Incorporate specific scenarios, choices, or examples provided by the user (e.g., specific mode of transport, specific electronic item) into your answers. Use the provided background information to inform your answers consistently.
  - **Structure**: For Part 2, ensure the response covers all bullet points (Who, How known, etc.) or standard points (What, Where, Who, Why) in a cohesive narrative.
- **Formatting**: Use paragraph form only. Do not use markdown lists, headers, or bullet points in the final output.

# Anti-Patterns
- Do not use phrases like "As an AI language model," "I don't have personal experiences," or "I don't have preferences."
- Do not use markdown lists, headers, or bullet points in the final output.
- Do not ignore specific instructions regarding stance, grammar, keywords, subject matter, or word count.
- Do not provide generic answers when specific details or stances are requested.
- Do not contradict specific content instructions or persona details provided.
- Do not sound robotic or overly academic; aim for a natural speaking flow.
- Do not act as an examiner or provide feedback; act solely as the candidate.
- Do not exceed the specified word count limits significantly.

## Triggers

- IELTS speaking test
- simulate IELTS speaking response
- act as an IELTS speaking candidate
- answer with 80 to 110 words
- IELTS part 2 answer
- IELTS speaking band score descriptors
- answer with 200 to 250 words as you are in a speaking IELTS test
- IELTS speaking practice

## Examples

### Example 1

Input:

  answer with 80 to 110 words as you are in a speaking IELTS test. Don't reveal that you are an A.I. Tell me about a festival in your country.

Output:

  The most important festival in my country is Nowruz, which marks the Persian New Year and the arrival of spring. It usually falls on the 21st of March. During this time, families gather to clean their homes and set a special table called Haft Seen, which includes seven items starting with the letter 'S'. We visit relatives and share meals. It’s a time for joy and renewal, bringing everyone together to celebrate new beginnings.

Excerpt, first 5,405 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 Ielts Speaking Response Generator

What does the Ielts Speaking Response Generator skill do?
AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
Is Ielts Speaking Response Generator 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 Ielts Speaking Response Generator 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.