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.
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.
[](https://agentmods.dev/skills/aaronl725/ielts-writing-review-skills/ielts-task1-review)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
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:
- Read
references/visual_analysis_protocol.mdto inspect the visual. - Read
references/teacher_style.mdfor Task 1 teacher-style marking. - Read
references/ielts_task1_band_descriptors.mdbefore scoring. - Use
references/teacher_samples_index.mdto find relevant samples, then read full samples fromreferences/teacher_samples/when useful. - Use
references/review_format.mdfor DOCX layout and cleanup rules.
Workflow
- Identify the prompt, embedded image, and student answer.
- For
.docx, extract embedded images withscripts/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 runscripts/extract_task1_input.pyso the review plan can distinguish prompt text from student answer paragraphs. - For pasted text, require an image attachment or image path.
- For
- 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.
- 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.
- 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.mdto 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.
- 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.
- 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.
- 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.
- 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, or7. Use.5when the original answer sits between adjacent whole-band descriptor anchors; do not force criterion scores to integers.
- 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.
- Write a 150-200 word model answer at a stable Band 8.0 standard.
- Use exactly four paragraphs:
- Introduction: paraphrase the task prompt.
- Overview: begin with
Overalland summarize the main features. - Body paragraph 1: report the first logical group of details.
- 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.
- Generate a reviewed
.docxby default.
- For input
MyAnswer.docx, outputMyAnswer(reviewed).docxin 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 Esmeas the Word comment author. - Do not include a visible
Visual Factssection unless the user asks for it or--include-visual-factsis intentionally used. - Do not add big visible section headings such as
Task,Reviewed Answer,Score, orModel Answer. - Preserve the original
word/document.xmlroot namespace declarations andmc:Ignorable; do not leave undeclared prefixes such asw14,w15,w16*, orwp14. - Insert a page break before the score and feedback page; keep the score lines and
To Reach Band 7.5 / 8.0together; insert another page break before the model answer. - Never overwrite the original answer unless explicitly requested.
- 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.pycreates 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.
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.
- agents/openai.yaml 296 B
- references/ielts_task1_band_descriptors.json 12 KB
- references/ielts_task1_band_descriptors.md 12 KB
- references/review_format.md 4.3 KB
- references/review_plan_example.json 3.5 KB
- references/sample_images/C15T1_Writing_Task_1_image1.png 705 KB
- references/sample_images/C15T2_Writing_Task_1_image1.jpeg 151 KB
- references/sample_images/C15T3_Writing_Task_1_image1.jpeg 158 KB
- references/sample_images/C15T4_Writing_Task_1_image1.jpeg 217 KB
- references/sample_images/C16T1_Writing_Task_1_image1.png 203 KB
- references/sample_images/C16T2_Writing_Task_1_image1.jpeg 213 KB
- references/sample_images/C16T3_Writing_Task_1_image1.jpeg 282 KB
- references/sample_images/C16T4_Writing_Task_1_image1.jpeg 245 KB
- references/sample_images/C17T1_Writing_Task_1_image1.jpeg 263 KB
- references/sample_images/C17T2_Writing_Task_1_image1.png 86 KB
- references/sample_images/C17T3_Writing_Task_1_image1.png 48 KB
- references/sample_images/C18T1_Writing_Task_1_image1.png 106 KB
- references/teacher_samples_index.md 3.6 KB
- references/teacher_samples/C15T1_Writing_Task_1.json 19 KB
- references/teacher_samples/C15T1_Writing_Task_1.md 4.8 KB
- references/teacher_samples/C15T2_Writing_Task_1.json 21 KB
- references/teacher_samples/C15T2_Writing_Task_1.md 5.6 KB
- references/teacher_samples/C15T3_Writing_Task_1.json 25 KB
- references/teacher_samples/C15T3_Writing_Task_1.md 7.3 KB
- references/teacher_samples/C15T4_Writing_Task_1.json 23 KB
- references/teacher_samples/C15T4_Writing_Task_1.md 11 KB
- references/teacher_samples/C16T1_Writing_Task_1.json 17 KB
- references/teacher_samples/C16T1_Writing_Task_1.md 5.0 KB
- references/teacher_samples/C16T2_Writing_Task_1.json 18 KB
- references/teacher_samples/C16T2_Writing_Task_1.md 6.2 KB
- references/teacher_samples/C16T3_Writing_Task_1.json 16 KB
- references/teacher_samples/C16T3_Writing_Task_1.md 5.7 KB
- references/teacher_samples/C16T4_Writing_Task_1.json 16 KB
- references/teacher_samples/C16T4_Writing_Task_1.md 5.6 KB
- references/teacher_samples/C17T1_Writing_Task_1.json 13 KB
- references/teacher_samples/C17T1_Writing_Task_1.md 4.7 KB
- references/teacher_samples/C17T2_Writing_Task_1.json 11 KB
- references/teacher_samples/C17T2_Writing_Task_1.md 4.0 KB
- references/teacher_samples/C17T3_Writing_Task_1.json 13 KB
- references/teacher_samples/C17T3_Writing_Task_1.md 5.6 KB
- references/teacher_samples/C18T1_Writing_Task_1.json 26 KB
- references/teacher_samples/C18T1_Writing_Task_1.md 9.4 KB
- references/teacher_style.md 2.7 KB
- references/visual_analysis_protocol.md 2.9 KB
- scripts/create_and_validate_task1_review.py 2.4 KB runs code
- scripts/create_task1_review_docx.py 35 KB runs code
- scripts/extract_docx_images.py 1.5 KB runs code
- scripts/extract_task1_band_descriptors.py 3.7 KB runs code
- scripts/extract_task1_input.py 6.1 KB runs code
- scripts/extract_task1_teacher_samples.py 11 KB runs code
- scripts/validate_task1_review_docx.py 9.1 KB runs code
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.
- 12d ago First seen · 161 lines · 112 tokens per session scan A 2d5438cffbdd
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.
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.
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.
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.
immersion-reader
Build a local H5 English deep-reading lesson from an article URL, YouTube transcript, podcast transcript, or prepared segments.json.
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.
lecture-builder
A document-building workflow that turns a teacher's knowledge and problem files into printable student and teacher Word documents.