ielts-task1-review

ielts-task1-review is a skill for Codex from AaronL725/ielts-writing-review-skills. It costs 112 tokens per session (2,535 once invoked), scanned A, original, MIT.

A review workflow for IELTS Academic Writing Task 1 answers, which describe charts, tables, maps, or processes. It follows one teacher's marking style and produces a structured review.

In plain words
What is it for?
It is for analyzing the visual prompt, checking a student's answer against IELTS scoring criteria, suggesting improvements, and optionally preparing a reviewed Word document.
Why use it?
It prevents language corrections from hiding misunderstandings of the visual question, which can lower the score even when the English is accurate.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/aaronliang/Desktop/IELTS_Task1_Reviewed_YYYYMMDD_HHMM.docx.

Good fit It is for analyzing the visual prompt, checking a student's answer against IELTS scoring criteria, suggesting improvements, and optionally preparing a reviewed Word document.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ielts-task1-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/aaronl725/ielts-writing-review-skills/ielts-task1-review/github.svg)](https://agentmods.dev/skills/aaronl725/ielts-writing-review-skills/ielts-task1-review)
Your own site
<a href="https://agentmods.dev/skills/aaronl725/ielts-writing-review-skills/ielts-task1-review"><img src="https://agentmods.dev/badge/skills/aaronl725/ielts-writing-review-skills/ielts-task1-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ielts-task1-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/aaronl725/ielts-writing-review-skills/ielts-task1-review"><img src="https://agentmods.dev/badge/skills/aaronl725/ielts-writing-review-skills/ielts-task1-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,535 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00112 $0.02535
Opus 5 $0.00056 $0.01267
Sonnet 5 $0.00022 $0.00507
Haiku 4.5 $0.00011 $0.00253

Measured 12d ago against content hash 2d5438cffbdd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ielts-task1-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 7 executable files (scripts/create_and_validate_task1_review.py, scripts/create_task1_review_docx.py, scripts/extract_docx_images.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/ielts-task1-review/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IELTS Task 1 Review

Core Rule

Analyze the visual prompt before correcting the student's writing. For Task 1, accurate chart/table/map/process understanding is part of Task Achievement, so do not polish language before identifying the main features.

Use these references in order:

  1. Read references/visual_analysis_protocol.md to inspect the visual.
  2. Read references/teacher_style.md for Task 1 teacher-style marking.
  3. Read references/ielts_task1_band_descriptors.md before scoring.
  4. Use references/teacher_samples_index.md to find relevant samples, then read full samples from references/teacher_samples/ when useful.
  5. Use references/review_format.md for DOCX layout and cleanup rules.

Workflow

  1. Identify the prompt, embedded image, and student answer.
    • For .docx, extract embedded images with scripts/extract_docx_images.py.
    • Inspect the extracted image directly before reviewing. This is mandatory: never score or rewrite a Task 1 answer from the text alone.
    • For .docx, also run scripts/extract_task1_input.py so the review plan can distinguish prompt text from student answer paragraphs.
    • For pasted text, require an image attachment or image path.
  2. Build an internal visual facts note.
    • Identify visual type, units, categories, time periods, axes, legends, stages, and key values.
    • Identify overview-level features before local details.
    • Keep this note internal unless the user explicitly asks to see it.
  3. Check the student's Task Achievement.
    • Mark inaccurate chart type, wrong units, missing overview, wrong key feature selection, inaccurate values, or irrelevant details in comments.
  4. Select the closest teacher samples by visual type before writing comments.
    • First classify the new task as bar chart, line graph, table, pie chart, map, process, or mixed visual.
    • Use references/teacher_samples_index.md to find similar sample files, then inspect one or two matching full samples.
    • Prefer same visual type and same main challenge, such as trend comparison, proportions, maps, process sequencing, or mixed table/chart reporting.
  5. Split the answer into review units.
    • Use sentence-level units for grammar, articles, plural forms, data phrasing, collocation, and formal wording.
    • Use paragraph-level units for overview errors, poor grouping, data misreading, map/process sequencing, or missing comparisons.
  6. Add teacher-style comments.
    • Use short English comments anchored to specific words or phrases.
    • Use comments like Specify type: bar chart, mention proportions, slightly repetitive, formal, Use comma, This is stated in overview.
  7. Add italic rewrites after relevant units.
    • Rewrites must be concise, formal, data-accurate, and at a stable Band 7.5 standard.
    • Keep rewrites learnable and close to the student's intended meaning; do not turn local fixes into over-complex Band 9 wording.
  8. Score the student's original answer strictly using official Task 1 descriptors.
    • Score Task Achievement, Coherence & Cohesion, Lexical Resource, Grammatical Range & Accuracy, and estimated overall band.
    • For this teacher-style educational review, criterion scores and the estimated overall score may use whole or half bands, such as 6, 6.5, or 7. Use .5 when the original answer sits between adjacent whole-band descriptor anchors; do not force criterion scores to integers.
  9. Give concise Band 7.5 / 8.0-oriented feedback.
    • Mention blockers preventing stable Band 7.5 first.
    • Then mention the most useful move toward 8.0.
  10. Write a 150-200 word model answer at a stable Band 8.0 standard.
  • Use exactly four paragraphs:
    1. Introduction: paraphrase the task prompt.
    2. Overview: begin with Overall and summarize the main features.
    3. Body paragraph 1: report the first logical group of details.
    4. Body paragraph 2: report the second logical group of details.
  • Leave one blank line between model answer paragraphs in the output DOCX.
  • Align it with the visual and official criteria.
  • Correct any inaccurate visual interpretation.
  • It must be strong enough for Band 8.0: skilful key feature selection, clear overview, logical grouping, precise data language, natural comparisons, well-managed cohesion, and mostly error-free grammar.
  • Keep it realistic and teacher-like, not an over-complex Band 9 answer.
  1. Generate a reviewed .docx by default.
  • For input MyAnswer.docx, output MyAnswer(reviewed).docx in the same folder unless the user specifies another path.
  • For DOCX input, create the reviewed file by copying the original DOCX first.
  • Write comments directly into the copied original answer paragraphs; do not create a second copy of the student's answer for comments.
  • Insert italic rewrites immediately after the matched original answer paragraph.
  • Keep the original prompt and embedded visual in place; do not repeat the task prompt or image.
  • For pasted text, output to /Users/aaronliang/Desktop/IELTS_Task1_Reviewed_YYYYMMDD_HHMM.docx.
  • Use Times New Roman for all added review text and comments.
  • Use Cyber Esme as the Word comment author.
  • Do not include a visible Visual Facts section unless the user asks for it or --include-visual-facts is intentionally used.
  • Do not add big visible section headings such as Task, Reviewed Answer, Score, or Model Answer.
  • Preserve the original word/document.xml root namespace declarations and mc:Ignorable; do not leave undeclared prefixes such as w14, w15, w16*, or wp14.
  • Insert a page break before the score and feedback page; keep the score lines and To Reach Band 7.5 / 8.0 together; insert another page break before the model answer.
  • Never overwrite the original answer unless explicitly requested.
  1. Clean up temporary byproducts after a successful review.
  • Delete temporary files such as review_plan_*.json, extracted scratch images, and unpacked DOCX folders.
  • scripts/extract_docx_images.py creates a unique /private/tmp/ielts_task1_images_* directory by default; delete that scratch directory after validation.
  • Do not delete source answers, final reviewed DOCX files, or bundled reference files.

Read the full file on GitHub · 161 lines

Files

What ships with it

51 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 161 lines · 112 tokens per session scan A 2d5438cffbdd

Subscribe to this mod's changes

ielts-task1-review is a skill published in the GitHub repository AaronL725/ielts-writing-review-skills (31 stars, last pushed 25d ago), licensed MIT. It adds 112 tokens to every session and 2,535 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

frog-and-toad-studio

A lesson-planning studio for teachers who teach English as a second language to first-grade learners using Arnold Lobel's Frog and Toad stories. For each chapter, it creates a projected keyword map, a one-page student workbook, and a workbook answer key.

CathyErer/frog-and-toad-studio · 279 tokens

frog-and-toad-illustration-style

A style guide and prompt library for generating square watercolor illustrations of Frog and Toad course material. It includes ready-made prompt lists for 20 chapters and supports user-supplied prompt files.

CathyErer/frog-and-toad-studio · 77 tokens

english-coaching

Use when responding to any user message in a Claude Code session running the nativish plugin — for non-native English speakers who want inline grammar and spelling feedback alongside every reply.

denys-petryniak/nativish · 39 tokens

immersion-reader

Build a local H5 English deep-reading lesson from an article URL, YouTube transcript, podcast transcript, or prepared segments.json.

rayw-lab/english-immersion-reader · 30 tokens

oral-english-practice

A Claude Code skill that stores and analyses spoken-English practice completed in the Claude app. The app handles the conversation; this skill keeps reports, scores, mistakes, progress trends, and the next practice focus.

XcutingUnicorn235/Oral-English-Practice · 113 tokens

lecture-builder

A document-building workflow that turns a teacher's knowledge and problem files into printable student and teacher Word documents.

dhcnsa-netizen/lecture-builder · 280 tokens