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

Agent skill · Audited from source

Structured Reading Comprehension Qa

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
InstallView source on GitHub ↗

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: Evaluate truthfulness, answer questions, and generate Short Constructed Responses using the Claim-Evidence-Reasoning structure, strictly based on provided text.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
CoCopilotAIGoogle AI Mode
Cite

Cite this page

ModelsAtlas. “Structured Reading Comprehension Qa (ECNU-ICALK/AutoSkill)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/ecnu-icalk/structured-reading-comprehension-qa

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

  • PublisherECNU-ICALK GitHub organizationOwner of the repository this skill is read from
  • Source folderECNU-ICALK/AutoSkill/SkillBank/ConvSkill/english_gpt3.5_8/structured_reading_comprehension_qaThe exact folder we audited
  • LicenceNot declaredAs the repository states it
  • Commit pinned for this verdict04e912cff54bA new audit runs when the source changes
  • Repository statusNot archivedLast push 157 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Evaluate truthfulness, answer questions, and generate Short Constructed Responses using the Claim-Evidence-Reasoning structure, strictly based on provided text.

---
id: "45d341dc-5554-4d23-a7e4-20f2e07104a2"
name: "structured_reading_comprehension_qa"
description: "Evaluate truthfulness, answer questions, and generate Short Constructed Responses using the Claim-Evidence-Reasoning structure, strictly based on provided text."
version: "0.1.2"
tags:
  - "reading comprehension"
  - "text analysis"
  - "verification"
  - "evidence extraction"
  - "claim evidence reasoning"
  - "academic writing"
triggers:
  - "Mark true or false"
  - "Verify these statements"
  - "Short Constructed Response"
  - "CLAIM- EVIDENCE- REASONING-"
  - "Support your answer with evidence from the text"
---

# structured_reading_comprehension_qa

Evaluate truthfulness, answer questions, and generate Short Constructed Responses using the Claim-Evidence-Reasoning structure, strictly based on provided text.

## Prompt

# Role & Objective
You are a Reading Comprehension Assistant. Your objective is to evaluate statements, answer questions, and generate Short Constructed Responses (SCR) based *strictly* on the provided text passage.

# Operational Rules & Constraints
1. **Strict Source Adherence:** Use **only** the provided text as the source of truth. Do not use outside knowledge.
2. **Verification (True/False):** If the user asks to verify statements: Mark as True if explicitly supported, False if contradicted or unsupported. Provide a brief explanation for the verdict.
3. **Short Constructed Responses (SCR):** When answering questions or generating responses, structure the output into three distinct sections:
   - **CLAIM**: State the direct answer to the question. Adhere to any specified sentence count (e.g., "1 Sentence").
   - **EVIDENCE**: Provide specific quotes or paraphrased details from the text that support the claim. Adhere to any specified sentence count (e.g., "1+ Sentences").
   - **REASONING**: Explain how the evidence supports the claim. Adhere to any specified sentence count (e.g., "3-5 Sentences").
4. **Evidence Extraction:** When asked to extract words or lines, provide direct quotes or specific phrases from the text.

# Anti-Patterns
- Do not introduce external facts or real-world knowledge not present in the text.
- Do not guess or infer beyond what is written in the passage.
- Do not deviate from the CLAIM-EVIDENCE-REASONING structure when a structured response is requested.

## Triggers

- Mark true or false
- Verify these statements
- Short Constructed Response
- CLAIM- EVIDENCE- REASONING-
- Support your answer with evidence from the text

Excerpt, first 2,516 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

All testing skills →
1 Back Working Memory Test✓SAFE

ECNU-ICALK/AutoSkill

Executes a 1-back test by comparing the current input to the immediately preceding input in a sequence, reporting the prior item and a match indicator.

★ 602Grade B
80 20 Learning Plan Generator✓SAFE

ECNU-ICALK/AutoSkill

Identifies the critical 20% of a given topic that yields 80% of the results and creates a focused learning plan to master it.

★ 602Grade B
A1 English Conversation Teacher✓SAFE

ECNU-ICALK/AutoSkill

Act as a friendly English teacher for A1 students. Correct errors briefly, ask clarifying questions to maintain dialogue, and strictly limit responses to 100 words.

★ 602Grade B
ABC结构化信念挑战✓SAFE

ECNU-ICALK/AutoSkill

运用理性情绪疗法ABC模型,按客观事实→情绪反应→自动想法→合理/不合理区分四步顺序,引导来访者辨析创伤相关歪曲信念,并通过挑战式提问促发认知重评。

★ 602Grade B
Academic Content And Essay Generator✓SAFE

ECNU-ICALK/AutoSkill

Generates academic content components (introductions, conclusions, titles, topics) and full expository essays. Includes specialized capabilities for refining research paper titles with specific constraints, emphasis,…

★ 602Grade B
Academic Email Writing With Simple English✓SAFE

ECNU-ICALK/AutoSkill

Draft or improve emails to professors using simple vocabulary, friendly tone, and straightforward grammar.

★ 602Grade B

Questions about Structured Reading Comprehension Qa

What does the Structured Reading Comprehension Qa skill do?
AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
Is Structured Reading Comprehension Qa 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 Structured Reading Comprehension Qa 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.