H5P Item Bank Writer: Fill in the Blanks, Drag the Words, and Mark the Words in Paste-Ready Syntax

Prompt

Act as an assessment item writer who builds H5P activities for language and content teachers. You write items in the exact text syntax the H5P editors expect, so the teacher can paste them without reformatting, and you check every item for a single defensible answer.

Inputs:
- Target vocabulary or grammar point with level (for example CEFR A2 past simple irregular verbs): [LearningTarget]
- Word list or source text the items must use: [WordList]
- Learner profile (age band, first language, known trouble spots): [Learners]
- H5P content types wanted and item count per type: [ContentTypes]
- Host platform (H5P.com, WordPress plugin, Moodle, Canvas via LTI) if known: [Host]
- Spelling variants to accept (British and American, contractions): [Variants]
- Output format: [Format]

Generate:
1. Item plan. A short table: content type, item count, which WordList entries each item tests, and the skill (recall, recognition, form).
2. Fill in the Blanks text blocks. Mark each blank as *answer*. Put accepted alternatives inside the same asterisks separated by a slash (*colour/color*) using Variants. Add a tip after a colon only where a learner could reasonably be stuck (*went:past of go*). One blank per sentence unless the plan says otherwise.
3. Drag the Words text. Mark each draggable with *word*. Add one or two distractors in a note for the teacher, because Drag the Words builds its pool only from the marked words.
4. Mark the Words text. Write a short paragraph and mark the correct target words with asterisks; make sure no unmarked word in the paragraph also fits the task instruction.
5. Behavior settings per content type: Case sensitive, Accept minor spelling errors, Require all fields to be answered before the solution can be viewed, Enable Retry, Enable Show solution, and Automatically check answers. Recommend a value for each and why, given Learners.
6. Item review sheet. For each item: answer key, ambiguity check (could another word fit?), and the Learners trouble spot it targets.

Constraints:
- Use only words from WordList as answers.
- Never put an asterisk anywhere except around answers; explain how to write a literal asterisk only if WordList contains one.
- Sentences must be natural and level appropriate; no trick items.
- No em dashes.

Instructions

Replace every [bracket] with your details before running. Works on ChatGPT, Claude, and Gemini.

Generated Output

This image was generated using the prompt above.

H5P Item Bank Writer: Fill in the Blanks, Drag the Words, and Mark the Words in Paste-Ready Syntax - Result

Examples

Example Input

LearningTarget: CEFR A2 past simple irregular verbs
WordList: went, saw, bought, took, ate, wrote, came, found
Learners: adults, Spanish L1, often write 'goed' and 'buyed', confuse 'saw' and 'seen'
ContentTypes: Fill in the Blanks 6 items, Drag the Words 1 paragraph with 5 gaps, Mark the Words 1 paragraph
Host: Moodle with the core H5P activity
Variants: none needed for these verbs
Format: plan, paste blocks, settings, review sheet

Example Output

1. Item plan
| Type | Items | Words tested | Skill |
| Fill in the Blanks | 6 | went, saw, bought, took, ate, wrote | form recall |
| Drag the Words | 5 gaps | came, found, went, bought, saw | recognition in context |
| Mark the Words | 1 paragraph | all 8 | recognition |

2. Fill in the Blanks (paste into the Text blocks field)
Yesterday I *went:past of go* to the market after work.
We *saw* a great film at the cinema on Saturday.
My sister *bought:past of buy* a new coat last week.
He *took* the bus to the airport this morning.
They *ate* paella at a small restaurant by the sea.
I *wrote* a long email to my manager on Friday.

Tips appear only on went and bought because Learners overgeneralize to goed and buyed.

3. Drag the Words (paste into the Text field)
Last summer my cousin *came* to visit us. On the first day we *went* to the old town, and she *bought* a hat. In a small shop we *found* some old postcards. In the evening we *saw* fireworks over the river.

Teacher note: the draggable pool will contain only these five words. If you want distractors, add a sixth sentence that uses a near form, or keep 'seen' and 'goed' for a separate error-correction task, since H5P does not add unused words to the pool on its own.

4. Mark the Words (task: Click every verb in the past simple)
On Monday Ana *took* the early train. She *ate* breakfast at the station and *wrote* a message to her friend. At work she *found* her keys under a desk. Now she is tired, but she is happy.

Ambiguity check: 'is' appears twice in present tense, which is intentional as a non-target. No other past form appears unmarked.

5. Settings
Fill in the Blanks: Case sensitive off (a capital letter is not the skill). Accept minor spelling errors off, because 'buyed' versus 'bought' is exactly the form being tested. Require all fields answered before solution: on. Enable Retry: on. Enable Show solution: on. Automatically check answers after input: off, so learners commit before feedback.
Drag the Words: Enable Retry on, Show solution on, instant feedback off.
Mark the Words: Enable Retry on, Show solution on.
In Moodle, set the H5P activity grade method to highest attempt if Retry stays on.

6. Review sheet
| Item | Key | Could another word fit? | Trouble spot |
| FitB 1 | went | no; 'walked' is not in WordList but would fit, so the tip anchors 'go' | goed |
| FitB 2 | saw | no | saw vs seen |
| FitB 3 | bought | no | buyed |
| FitB 4 | took | 'caught' would fit; acceptable since only WordList answers are keyed, consider adding caught/took | none |
| FitB 5 | ate | 'had' would fit; add *ate/had* if you allow it | none |
| FitB 6 | wrote | 'sent' would fit; add *wrote/sent* or rewrite with 'wrote by hand' | none |
| DtW | came, went, bought, found, saw | each gap has one best fit from the pool | saw vs seen |
| MtW | took, ate, wrote, found | none unmarked | none |