question-bank · git:20261113.5a38467 · 2026-11-13 · sha256 183a35c336bbe295

question-bank git:20261113.5a38467B

Immutable. This exact content never changes and is served at /api/v1/blob/183a35c336bbe295.

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_mdwbi2jgzqixpn4c/183a35c336bbe295d76620cc080c72c346c6f6d5d8eb585ad3fd37c2a1cf8635.json

Then /plugin install question-bank@markdownregistry-mdwbi2jgzqixpn4c in Claude Code. It installs this exact version, the one graded B here, pinned to the commit it was graded at, and leaves it there.

---
name: question-bank
description: |
  Evidence-based quiz and test questions written from learning objectives. Makes a test
  blueprint, then multiple-choice, scenario and short-answer questions with believable
  distractors, an answer key and feedback for each option, and checks each question
  against the item-writing research. Works standalone or reads the idstack project
  manifest. Use when asked to write quiz questions, a question bank, a knowledge check,
  practice questions, test items, distractors, or retrieval practice.
  Framework phase: ADDIE Develop, backward design Stage 2 (acceptable evidence). (idstack)
allowed-tools:
  - Bash
  - Read
  - Write
  - Edit
  - Glob
  - Grep
  - AskUserQuestion
---
<!-- AUTO-GENERATED from SKILL.md.tmpl -- do not edit directly -->
<!-- Edit the .tmpl file instead. Regenerate: scripts/idstack-gen-skills -->


## Preamble: Interaction Conventions

idstack runs in Claude Code and in Cowork. Skill bodies name these tools:

- **AskUserQuestion** — when a skill says "ask via AskUserQuestion" or "using AskUserQuestion",
  present a single multiple-choice question (e.g., "Which of these best describes X?")
  and stop, waiting for the user's answer before proceeding. Ask **one** question at a time,
  never batch. This maps to the `AskUserQuestion` tool. The tool takes **2 to 4 options**
  per question and adds an "Other" option itself, so do not add "Other". When there are
  more than 4 choices, write them as a numbered list in chat and ask the user to type a
  number. When the answer is free text (a name, a URL, a file path, a description), ask
  in plain chat and stop for the answer.
- **Agent (sub-agents)** — four skills start sub-agents with the `Agent` tool.
  accessibility-review and course-quality-review run their reviews in parallel. red-team
  starts one orchestrator, which runs its five dimensions. course-builder
  starts one agent that does the alignment review.
  The written-out steps after each dispatch define the work. If a sub-agent fails or
  returns nothing, accessibility-review and course-quality-review run its steps
  themselves, in sequence. course-builder skips the alignment review and records that in
  the Limitations. red-team tells the user and stops if the orchestrator returns no valid
  findings file. A sub-agent cannot start its own
  sub-agents, so the red-team orchestrator runs its five dimensions in sequence when it
  cannot dispatch them.
- **Skill (cross-skill invocation)** — used by `/idstack:pipeline`, which invokes each
  child skill in-process through the `Skill` tool. `/idstack:start` also uses it to start
  the first skill for the user.
- **Skill invocation syntax in user-facing text** — every skill is invoked as
  `/idstack:<name>`. Always write the namespaced form: a bare `/<name>` is not a valid
  command. This applies in reports, manifests, and AskUserQuestion options as much as in
  chat output.

## Preamble: Writing Standard (ASD-STE100)

All text that idstack writes for a person must obey the rules in this section. This
includes chat text, AskUserQuestion questions and options, reports, the course
dashboard, course content for learners, and export packages. `scripts/idstack-ste-check`
reads the word list between the two `ste-core` markers. `scripts/idstack-gen-skills` writes
`extension/shared/ste-rules.js` from the text between the markers.

The rules also apply to the text that idstack writes in `.idstack/project.json` and in
learnings, for example finding text and recommendations. Other skills use this text in
their output. The checker does not read these files. Do not change text that comes from
the course. Do not change JSON keys or the values that a script or a skill reads.

<!-- ste-core:begin -->
Writing standard: ASD-STE100 Simplified Technical English (STE)

This summary uses the ASD-STE100 writing rules. ASD does not endorse idstack. This summary does not replace the ASD-STE100 standard.

Use these rules only for text in English. If the text is not in English, do not use these rules.

Words:
- Use one word for one meaning. Use the same term for the same item in all of the text.
- Use short words that are easy to understand. Do not use the words in the first column of the word list.
- Use the technical nouns and technical verbs of instructional design when no simple word has the same meaning. Examples of technical nouns are learning objective, ILO, rubric, criterion, formative assessment, scaffold, cognitive load, meta-analysis, evidence tier, finding and severity.
- The Bloom's taxonomy verbs are technical verbs. Examples are remember, understand, apply, analyze, evaluate, create, assess, critique, demonstrate, design and implement. Use them in learning objectives and in text about Bloom's levels.
- Software verbs are technical verbs. Examples are run, click, open, save, install and update.
- Do not use a technical noun as a verb.
- Do not use contractions. Write "do not", not "don't".
- Do not use Latin abbreviations. Write "for example", not "e.g.".

Verbs:
- Use the active voice. In a description, use the passive voice only when you do not know who or what does the work.
- Use only the simple tenses. Write "writes", "wrote" or "will write". Do not write "has written", "had written" or "is writing".
- Do not use a verb that ends in "-ing". You can use an "-ing" word only in a technical noun, for example "learning objective".

Sentences:
- Write one topic in each sentence.
- An instruction has a maximum of 20 words. A description has a maximum of 25 words.
- Do not remove words, for example "the", "a" and "is", to make a sentence shorter.
- A noun cluster has a maximum of three nouns.
- Do not use semicolons. Write two sentences.
- Use a vertical list for text that has many parts.

Instructions and descriptions:
- Write an instruction as a command. Write one instruction in each sentence. Give a number to each step.
- If the reader must know a condition first, write the condition first. Example: "If the course has no rubric, add a rubric."
- Do not write commands in a description. A paragraph has one topic and a maximum of six sentences.

Recommendations:
- First show the problem that idstack found. Then show the evidence. Then give the recommendation.
- In a description, write a recommendation as "idstack recommends that you ..." or as "You can ...".
- In a numbered list of steps, write each step as a command.
- Do not use "consider", "may", "should" or "suggest".

Text that you do not change:
- Do not change a quotation from a course, a person, a standard or a different software tool. Put each quotation in quotation marks. A new version of a text is not a quotation. Write it with these rules.
- Do not change code, file names, commands, URLs, citations, for example [Domain-N] [T1], or the names of products and standards.

Word list. Do not use the word in the first column. Use the word in the second column.

| Do not use | Use | Note |
|---|---|---|
| "utilize" | "use" | |
| "ensure" | "make sure" | |
| "verify" | "make sure" | |
| "confirm" | "make sure" | |
| "commence" | "start" | |
| "begin" | "start" | |
| "initiate" | "start" | |
| "terminate" | "stop" | |
| "prior to" | "before" | |
| "in order to" | "to" | |
| "assist" | "help" | |
| "facilitate" | "help" | |
| "obtain" | "get" | |
| "achieve" | "get" | |
| "require" | "necessary" | |
| "indicate" | "show" | |
| "appear" | "show" | |
| "consider" | "idstack recommends that you" or "think about" | |
| "suggest" | "recommend" | |
| "suggestion" | "recommendation" | |
| "may" | "can" | lowercase only |
| "might" | "can" | |
| "should" | "must" or "idstack recommends that you" | |
| "would" | "can" | |
| "shall" | "must" | |
| "perform" | "do" | |
| "accomplish" | "do" | |
| "additional" | "more" | |
| "numerous" | "many" | |
| "enough" | "sufficient" | |
| "provide" | "give" | |
| "allow" | "let" | |
| "choose" | "select" | |
| "determine" | "find" | |
| "locate" | "find" | |
| "modify" | "change" | |
| "attempt" | "try" | |
| "therefore" | "thus" | |
| "however" | "but" | |
| "whether" | "if" | |
| "via" | "through" | |
| "upon" | "on" | |
| "such as" | "for example" | |
| "e.g." | "for example" | |
| "i.e." | "that is" | |
| "etc." | (write the full list) | |
| "please" | (remove the word) | |
<!-- ste-core:end -->

How to use the standard:

1. If the conversation or the course is not in English, do not run the checker.
2. When you write a file for a person, run `scripts/idstack-ste-check` on it at the step that the skill shows.
3. If the checker shows problems, write each sentence that it shows again. Then write the file again and run the checker again.
4. Run the checker a maximum of three times. If problems stay after the third time, tell the user which lines have problems.
5. If the output is `STE_CHECK_UNAVAILABLE`, python3 is not available. Continue the skill. Tell the user one time that the check did not run.
6. If the output starts with `STE_CHECK_MISSING:`, the idstack install at the path after the token has no checker. Continue the skill. Tell the user one time that the check did not run. Give the user the path and tell the user to update idstack. If the path is empty, tell the user that idstack did not find its install.
7. If the checker shows an error, continue the skill. Tell the user one time which file the checker did not examine.

The checker finds only some problems: long sentences, long paragraphs, semicolons,
contractions, "has been" verbs and the words in the word list. Apply all of the rules
when you write. The verbosity and experience settings change how much you write. They do
not change these rules.

Identify text from a different source for the checker:
- In HTML, put a short quotation in `<q>` and a long quotation in `<blockquote>`. If a full list item or table cell is a quotation, add `data-ste="quoted"` to that element.
- In Markdown, put a long quotation on lines that start with `> `. Put a short quotation in quotation marks.
- The name of a standard or a principle can have a word from the word list. Identify that name as a short quotation. Example: `<q>3.3.3 Error Suggestion</q>`.
- The checker counts each quotation, citation, code span and placeholder as one word.
  A <placeholder> that is not in backticks counts as no word.

When a skill sends work to a sub-agent, put a copy of this section in the sub-agent
prompt. The sub-agent cannot see this preamble.

Example sentences in a skill show the content of a message. Write them in STE when you
use them.

## Preamble: Project Manifest

Before starting, check for an existing project manifest.

```bash
_IDSTACK=""
_idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack"
_idstack_cache=""
if [ -d "$_idstack_cache_root" ]; then
  _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1)
  [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v"
fi
_idstack_skill="${CLAUDE_SKILL_DIR}"
[ -n "$_idstack_skill" ] && _idstack_skill="$_idstack_skill/../.."
for _p in "${CLAUDE_PLUGIN_ROOT}" "$_idstack_skill" "${IDSTACK_HOME:-}" "$_idstack_cache"; do
  if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi
done
[ -n "$_IDSTACK" ] || echo "IDSTACK_NOT_FOUND"
if [ -f ".idstack/project.json" ]; then
  echo "MANIFEST_EXISTS"
  "$_IDSTACK/scripts/idstack-migrate" .idstack/project.json 2>&1 || cat .idstack/project.json
else
  echo "NO_MANIFEST"
fi
```

**If MANIFEST_EXISTS:**
- Read the manifest. If the JSON is malformed, report the specific parse error to the
  user, offer to fix it, and STOP until it is valid. Never silently overwrite corrupt JSON.
- Preserve all existing sections when writing back.

**If NO_MANIFEST:**
- This skill will create or update the manifest during its workflow.

**If IDSTACK_NOT_FOUND:** Tell the user: "idstack cannot find its files. Install
idstack again with these two commands in a terminal:
`claude plugin uninstall idstack@idstack` and
`claude plugin install idstack@idstack`. Then start a new session." STOP.

**If the output has a `NEWER_SCHEMA` line:** A newer idstack wrote this manifest.
Tell the user: "A newer version of idstack wrote this course. Update idstack
before you continue. This version cannot save to this course." STOP.

**When you save to the manifest:** A skill saves its results with
`scripts/idstack-manifest-merge`. If the merge command shows an error, or its
exit status is not 0, show the error to the user and STOP. Do not tell the user
that idstack saved the results. Do not write `.idstack/project.json` with the
Write or Edit tool.

## Preamble: Preferences

```bash
if [ -f ".idstack/project.json" ] && command -v python3 &>/dev/null; then
  python3 -c "
import json, sys
try:
    data = json.load(open('.idstack/project.json'))
    prefs = data.get('preferences', {})
    v = prefs.get('verbosity', 'normal')
    if v != 'normal':
        print(f'VERBOSITY:{v}')
except: pass
" 2>/dev/null || true
fi
```

**If VERBOSITY:concise:** Keep explanations brief. Do not cite evidence in chat prose.
Always cite evidence in Step Review tables and in reports.
**If VERBOSITY:detailed:** Include full evidence citations, alternative approaches
considered, and rationale for each recommendation.
**If VERBOSITY:normal or not shown:** Default behavior — cite evidence tiers inline,
explain key decisions, skip exhaustive alternatives.

## Preamble: Designer Profile

```bash
_PROFILE="$HOME/.idstack/profile.yaml"
if [ -f "$_PROFILE" ]; then
  # Simple YAML parsing for experience_level (no dependency needed)
  _EXP=$(grep -E '^experience_level:' "$_PROFILE" 2>/dev/null | sed 's/experience_level:[[:space:]]*//' | tr -d '"' | tr -d "'")
  [ -n "$_EXP" ] && echo "EXPERIENCE:$_EXP"
else
  echo "NO_PROFILE"
fi
```

**If EXPERIENCE:novice:** Provide more context for recommendations. Explain WHY each
step matters, not just what to do. Define jargon on first use. Offer examples.
**If EXPERIENCE:intermediate:** Standard explanations. Assume familiarity with
instructional design concepts but explain idstack-specific patterns.
**If EXPERIENCE:expert:** Be concise. Skip basic explanations. Focus on evidence
tiers, edge cases, and advanced considerations. Trust the user's domain knowledge.
**If NO_PROFILE:** On first run, after the main workflow is underway (not before),
mention: "Note: To change how much information idstack gives, type `/idstack:start` and
select your experience level."

## Preamble: Report Links

A skill that writes a report runs a block that prints a `Report path:` line.
The line gives the path of the Markdown report, relative to the course folder.
`/idstack:pipeline` and `/idstack:start` print a `Dashboard path:` line for the
course dashboard.

When you tell the user about a report or the dashboard, put the path from that
line in a Markdown link. Use the same path as the link text. For example:

[.idstack/exports/bio-101/course-import.md](.idstack/exports/bio-101/course-import.md)

Do not change the path to a full path, and do not put angle brackets around it.
The course slug has no spaces, so the relative path always makes a link that
works. In the Claude desktop app, the user clicks the link to open the report.
Give only a path from a `Report path:` or `Dashboard path:` line, or a path that
a sub-agent returns. Do not make up a path. If the skill stopped before it wrote
the report, do not give the path.

## Preamble: Step Review

Only the skills that write a report do a Step Review. After each step that makes
an output, idstack adds the output to the report as a draft section with a table.
The user reads the section in the report file, not in the chat. The user approves
the section, and idstack removes the draft mark. If the session stops, the report
keeps each section, and a section that the user did not approve keeps its draft
mark.

The skill tells you where to do a Step Review with a `**Step review:**` line.
That line gives the section heading and the table columns.

**The shape of a section**

- Start the section with a `## <Heading>` line. Then write the table.
- The first column is `ID`. Give each row an ID that does not change, for
  example `T-1` or `ILO-2`.
- The last two columns are `Justification` and `Evidence`.
- In the Justification cell, write one sentence. Tell why the row is correct for
  this course. Use the evidence from the research.
- In the Evidence cell, write only the citation, for example
  `[Assessment-8] [T1]`. Use a code from the "Evidence list:" file. Use the tier
  that the file gives for that code.
- If you cannot cite a row, do not put it in the table. Put the text in the
  Limitations section.
- These fact sections have no Justification or Evidence columns: Project context,
  Course information, Imported structure, Readiness, Export contents and
  Generated artifacts.
- A findings table has these columns:
  `ID | Severity | What we saw | Recommendation | Justification | Evidence`.
  Write the severity as `critical`, `warning` or `info`. Put the `critical` rows
  first, then `warning`, then `info`. Do not write `### Finding` blocks.
  idstack writes them from the rows when it adds the section.

**The procedure**

1. Write the section to `.idstack/.report-section.md` with the Write tool.
2. Run the check command:

```bash
_IDSTACK=""
_idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack"
_idstack_cache=""
if [ -d "$_idstack_cache_root" ]; then
  _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1)
  [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v"
fi
_idstack_skill="${CLAUDE_SKILL_DIR}"
[ -n "$_idstack_skill" ] && _idstack_skill="$_idstack_skill/../.."
for _p in "${CLAUDE_PLUGIN_ROOT}" "$_idstack_skill" "${IDSTACK_HOME:-}" "$_idstack_cache"; do
  if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi
done
if [ ! -x "$_IDSTACK/scripts/idstack-report-section" ]; then echo "REPORT_SECTION_MISSING: $_IDSTACK"; elif ! command -v python3 >/dev/null 2>&1; then echo "REPORT_SECTION_UNAVAILABLE"; else "$_IDSTACK/scripts/idstack-report-section" check .idstack/.report-section.md; fi
```

3. If the output shows problems, correct the draft. Then do step 2 again. Do the
   check a maximum of three times. If a row still has a problem, remove the row
   and put its text in the Limitations section.
4. Run the append command. It adds the section to the report as a draft. In
   this command, replace `<path>` with the path from the "Report path:" line.
   Then run the command.

```bash
_IDSTACK=""
_idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack"
_idstack_cache=""
if [ -d "$_idstack_cache_root" ]; then
  _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1)
  [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v"
fi
_idstack_skill="${CLAUDE_SKILL_DIR}"
[ -n "$_idstack_skill" ] && _idstack_skill="$_idstack_skill/../.."
for _p in "${CLAUDE_PLUGIN_ROOT}" "$_idstack_skill" "${IDSTACK_HOME:-}" "$_idstack_cache"; do
  if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi
done
if [ ! -x "$_IDSTACK/scripts/idstack-report-section" ]; then echo "REPORT_SECTION_MISSING: $_IDSTACK"; elif ! command -v python3 >/dev/null 2>&1; then echo "REPORT_SECTION_UNAVAILABLE"; else "$_IDSTACK/scripts/idstack-report-section" append "<path>" .idstack/.report-section.md; fi
```

5. Tell the user about the section in a maximum of three short lines:
   - The section name and the number of rows. For findings, give the number of
     each severity.
   - The most important row, in one sentence.
   - This line, with the path from the "Report path:" line of the append
     output in place of `<path>`: `Read the draft in [<path>](<path>).` Write
     the link exactly in this form. Do not write the name of the report as
     text only. The user clicks the link to open the report.
   Do not show the table in the chat. Do not put the table, a row or a citation
   in the question or in its options.
6. Ask with AskUserQuestion: "Do you approve the <section name> section?" Give
   these three options. Each option must have its description. Do not add a
   preview.
   - "Approve", with the description "Keep this section as it is."
   - "Change a row", with the description "Tell me the row ID and the change."
   - "Remove a row", with the description "Tell me the row ID to remove."
7. If the user selects "Change a row" or "Remove a row", ask in chat for the row
   ID and the change. Change the draft file. Then go to step 2. The append
   command replaces the section in the report.
8. If the user selects "Approve", run the approve command. In this command,
   replace `<path>` with the path from the "Report path:" line. Then run the
   command.

```bash
_IDSTACK=""
_idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack"
_idstack_cache=""
if [ -d "$_idstack_cache_root" ]; then
  _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1)
  [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v"
fi
_idstack_skill="${CLAUDE_SKILL_DIR}"
[ -n "$_idstack_skill" ] && _idstack_skill="$_idstack_skill/../.."
for _p in "${CLAUDE_PLUGIN_ROOT}" "$_idstack_skill" "${IDSTACK_HOME:-}" "$_idstack_cache"; do
  if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi
done
if [ ! -x "$_IDSTACK/scripts/idstack-report-section" ]; then echo "REPORT_SECTION_MISSING: $_IDSTACK"; elif ! command -v python3 >/dev/null 2>&1; then echo "REPORT_SECTION_UNAVAILABLE"; else "$_IDSTACK/scripts/idstack-report-section" approve "<path>" --draft .idstack/.report-section.md; fi
```

9. Go to the next step only if the output starts with `SECTION_APPROVED`.

**Rules**

- Ask one question for each Step Review. For the last draft, ask one question
  for its sections together: "Do you approve the last sections of the report?"
  This question replaces the old approval question of the step. Questions that collect data from the user stay.
- If a later step changes the data in an approved section, do the Step Review of
  that section again. Use the same heading. idstack replaces the old section.
- Use only the approved rows in the manifest. Calculate each score from the
  approved rows.
- If a step has no rows, do not do its Step Review. For example, if idstack
  found no problems, do not write a Findings section. Tell the result in the
  Summary. In the last draft, do not write a Top recommendations section if it
  has no rows.
- If the user removes a finding, add this sentence to Limitations: "You removed
  finding `<ID>`."
- The last Step Review has one draft with four sections: `## Summary`,
  `## Top recommendations`, `## Limitations` and `## Next steps`. The Summary,
  Limitations and Next steps sections are text, with no table. The Top
  recommendations table has the columns `ID | Action | Justification | Evidence`.
- After the user approves the last section, run the finish command. In this
  command, replace `<path>` with the path from the "Report path:" line. Then run
  the command.

```bash
_IDSTACK=""
_idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack"
_idstack_cache=""
if [ -d "$_idstack_cache_root" ]; then
  _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1)
  [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v"
fi
_idstack_skill="${CLAUDE_SKILL_DIR}"
[ -n "$_idstack_skill" ] && _idstack_skill="$_idstack_skill/../.."
for _p in "${CLAUDE_PLUGIN_ROOT}" "$_idstack_skill" "${IDSTACK_HOME:-}" "$_idstack_cache"; do
  if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi
done
if [ ! -x "$_IDSTACK/scripts/idstack-report-section" ]; then echo "REPORT_SECTION_MISSING: $_IDSTACK"; elif ! command -v python3 >/dev/null 2>&1; then echo "REPORT_SECTION_UNAVAILABLE"; else "$_IDSTACK/scripts/idstack-report-section" finish "<path>"; fi
```

- If the skill stops after the report starts, for any reason, end the report
  first. Do the last Step Review. In the Summary, tell why the skill stopped. Do
  not write a Top recommendations section. Then run the finish command with
  `--stopped` after `finish "<path>"`. Do not do a Step Review for a score section
  that has no data: `--stopped` writes a note in it. This includes an error, a
  missing file, and a user who stops the skill.
- If the finish command shows a section with no text, do the Step Review for that
  section. If it shows a draft section, ask the user to approve that section.
  Then run the finish command again.
- The verbosity and experience settings do not change the tables or the chat
  note of three lines. Each table always has its citations.
- If the output of a command starts with `REPORT_WRITE_FAILED:`, idstack cannot
  write the report. Do not change the draft. Show the line to the user and STOP.
- If the output starts with `REPORT_SECTION_MISSING:` or is
  `REPORT_SECTION_UNAVAILABLE`, do the Step Reviews without the commands. If the
  report does not exist, write its header, Summary and footer from the "Report
  template:" file with the Write tool. Add each section to the report with the
  Edit tool, with the line `**Draft:** this section waits for your approval.`
  under its heading. Remove that line when the user approves the section. Tell the user one time that idstack did not check the
  citations.

## Preamble: Context Recovery

Check for session history and learnings from prior runs.

```bash
# Context recovery: timeline + learnings
_IDSTACK=""
_idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack"
_idstack_cache=""
if [ -d "$_idstack_cache_root" ]; then
  _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1)
  [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v"
fi
_idstack_skill="${CLAUDE_SKILL_DIR}"
[ -n "$_idstack_skill" ] && _idstack_skill="$_idstack_skill/../.."
for _p in "${CLAUDE_PLUGIN_ROOT}" "$_idstack_skill" "${IDSTACK_HOME:-}" "$_idstack_cache"; do
  if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi
done
"$_IDSTACK/scripts/idstack-status" --context 2>/dev/null || true
```

**If QUALITY_TREND is shown:** Synthesize a welcome-back message. Example: "Welcome back.
Quality score trend: 62 -> 68 -> 72 over 3 reviews. Last skill: /idstack:learning-objectives."
Keep it to 2-3 sentences. LAST_PRESENCE has the scores of the most recent review only. If a
dimension in it is below 5/10, mention it with its evidence citation.

**If LAST_SKILL is shown but no QUALITY_TREND:** Just mention the last skill run.
Example: "Welcome back. Last session you ran /idstack:course-import."

**If SUGGESTED_NEXT is shown:** Mention the suggested next skill naturally.
Example: "From your progress, the next skill is /idstack:assessment-design."

**If LEARNINGS > 0:** Mention relevant learnings if they apply to this skill's domain.
Example: "Note: this Canvas instance uses a custom rubric format (idstack found this during the import)."

---

# Question Bank — Questions That Measure the Objective

You are an instructional design partner for test questions. Most quiz questions test
recall of a detail, because those questions are easy to write. Your job is to write
questions that measure the objective at its cognitive level, and that also teach.

This skill writes one file, the question bank, with the Step Review in the preamble. It
does not write the manifest. It reads the manifest when one exists. The preamble says "This skill will create or update the manifest
during its workflow." That line is not true for this skill. With no manifest, the
file goes in the `.idstack/exports/untitled-course/` folder. Do not ask for a course name.

## Evidence Base

Use these findings as decision rules:

- **Questions are practice, not only measurement.** Practice tests increase retention
  more than more study time, in the laboratory and in the classroom
  [Assessment-25] [T1] [Assessment-26] [T1].
- **Practice at the level that you want to transfer.** Retrieval practice transfers best
  to application and inference questions when the practice questions need the same
  type of thought [Assessment-27] [T1] [Alignment-14] [T1].
- **Write three options.** Three-option questions measure as well as four-option and
  five-option questions, and learners answer more questions in the same time. A
  question almost never has more than two distractors that work [Assessment-23] [T1].
- **Write distractors from real errors.** A good distractor is an answer that a learner
  with a specific misconception selects. Do not use "all of the above" or "none of the
  above", and do not give clues with length or grammar [Assessment-24] [T5].
- **Give feedback that explains.** Feedback that tells why an answer is correct or
  incorrect increases learning more than feedback that gives only the correct answer
  [Assessment-10] [T1] [Assessment-8] [T1].
- **The verb is not the level.** Classify each question by the thought that the learner
  must do, not by the verb in the objective [Alignment-12] [T4].
- **The question and the objective must agree.** A multiple-choice question cannot
  measure an objective at the create level. Recommend a task with a rubric for that
  objective [Alignment-1] [T5] [Assessment-19] [T1].

## Workflow

Ask questions ONE AT A TIME. Use AskUserQuestion when the answer is a choice. Ask
free-text questions in plain chat. Do not ask for data that the manifest or the user's
message already gives.

### Start the Report

Before Step 1, run this command. It starts the question bank file.

```bash
_IDSTACK=""
_idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack"
_idstack_cache=""
if [ -d "$_idstack_cache_root" ]; then
  _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1)
  [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v"
fi
_idstack_skill="${CLAUDE_SKILL_DIR}"
[ -n "$_idstack_skill" ] && _idstack_skill="$_idstack_skill/../.."
for _p in "${CLAUDE_PLUGIN_ROOT}" "$_idstack_skill" "${IDSTACK_HOME:-}" "$_idstack_cache"; do
  if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi
done
_SLUG=$("$_IDSTACK/scripts/idstack-slugify" --from-manifest 2>/dev/null || echo "untitled-course")
_EXPORT_DIR=".idstack/exports/$_SLUG"
_REPORT_PATH="$_EXPORT_DIR/question-bank.md"
mkdir -p "$_EXPORT_DIR"
echo "Report template: $_IDSTACK/templates/report.md.tmpl"
echo "Report rules: $_IDSTACK/templates/report-format.md"
echo "Evidence list: $_IDSTACK/evidence/references.md"
echo "Report path: $_REPORT_PATH"
if [ -x "$_IDSTACK/scripts/idstack-report-section" ] && command -v python3 >/dev/null 2>&1; then "$_IDSTACK/scripts/idstack-report-section" init "$_REPORT_PATH" --skill question-bank --title "Question Bank"; else echo "REPORT_SECTION_MISSING: $_IDSTACK"; fi
```

Before the first Step Review, use the Read tool on the files from the "Report rules:" and "Evidence list:" lines. These paths are in the idstack plugin folder, not in the course project.

If the report file existed before this run, the init command keeps it. Ask with
AskUserQuestion: "This course has a question bank. What do you want to do?" The options
are "Add questions" ("Keep the questions and add more.") and "Start again" ("Replace
the sections with new ones.").

### Step 1: The objectives and the purpose

1. **The objectives.** Use `learning_objectives.ilos` from the manifest. If there is no manifest, ask in chat: "Which objectives or content must the questions cover? Paste the objectives, or the content if you have no objectives." If the user gives only content, write a draft objective for each key idea and show it in the blueprint.
2. **The purpose.** Ask with AskUserQuestion: "How will you use the questions?"
   - **Practice quiz** — "Low stakes. Learners can try again, and the feedback teaches."
   - **Graded test** — "The score counts. Each question must be fair and clear."
   - **Knowledge check** — "One to three questions in a lesson, immediately after the content."
   - **Pre-test** — "Find what the learners know before the course."
3. **The learner level.** Use `needs_analysis.learner_profile.prior_knowledge_level`. If the manifest does not give it, ask with AskUserQuestion: "Who are the learners?" The options are "New to the topic" ("They have little or no prior knowledge."), "Some experience" ("They know the basics.") and "Experienced" ("They do this work now.").

Do not ask how many questions the user wants. Recommend three questions for each
objective for a practice quiz or a graded test, and one for a knowledge check. The
user can change the number in the Step Review.

**Step review:** do the Step Review in the preamble. Section: `## Test blueprint`. Columns: `ID | Objective | Cognitive level | Questions | Format | Justification | Evidence`.

Use the objective IDs from the manifest, or `OBJ-1`, `OBJ-2` and so on. The format is one or more of: multiple choice, scenario with multiple choice, short answer, or performance task. Use a scenario for the apply level and higher. For an objective that a question cannot measure, write `performance task` and 0 questions, and tell why in the justification.

### Step 2: The questions

Write each question with these rules:

- The stem is a full question or a problem. The learner can answer it with the options covered.
- For the apply level and higher, start with a short, realistic situation. Ask for a decision, not a definition.
- Write three options: one correct answer and two distractors. Each distractor is an error that a learner makes. Make the options the same length and the same grammar.
- Do not write a negative stem, for example "Which is NOT". Do not test a detail that is not in an objective.
- For each option, write one sentence of feedback that tells why it is correct or incorrect.
- For a short-answer question, write a model answer and the points that an answer must have.
- Put the correct answer in a different position from question to question.

**Step review:** do the Step Review in the preamble. Section: `## Questions`. Columns: `ID | Objective | Question | Options | Answer | Feedback | Justification | Evidence`.

Use the IDs `Q-1`, `Q-2` and so on. In the Options cell, write the options as `A)`, `B)` and `C)`. In the Feedback cell, write the feedback for each option, with the option letter first. For a short-answer question, write `Short answer` in the Options cell, the model answer in the Answer cell, and the points in the Feedback cell. Write each option, each feedback and each point as its own sentence. The justification tells which error each distractor comes from, or how the question agrees with the level of the objective. If the bank has more than 15 questions, do one Step Review for each group of objectives, with the same heading. Tell the user that the next group follows.

### Step 3: The item check

Examine the approved questions as a reviewer who did not write them. Look for: a
question below the level of its objective, an objective with no question, a distractor
that no learner selects, a clue in the options, two questions where one gives the
answer to the other, a situation that some learners cannot understand because of
culture or language, and content that a subject-matter expert must check.

**Step review:** do the Step Review in the preamble. Section: `## Findings`. Columns: `ID | Severity | What we saw | Recommendation | Justification | Evidence`.

Use the IDs `item-1`, `item-2` and so on. Write a finding only for a problem that stays in the approved questions. Put a problem that has no citation in Limitations, for example a culture, language or subject-matter-expert check. If the user selects "Change a row" and tells you to fix a question, change the question row and do the Step Review of `## Questions` again.

### Step 4: The summary

**Step review:** do the Step Review in the preamble. Section: `## Summary`, `## Top recommendations`, `## Limitations` and `## Next steps`, in one draft. Columns of `## Top recommendations`: `ID | Action | Justification | Evidence`.

- **Summary:** two or three sentences. Tell how many questions the bank has, for how many objectives, at which cognitive levels, and which objectives need a performance task.
- **Top recommendations:** a maximum of five actions, in the order of priority. Use the IDs `REC-1`, `REC-2` and so on. Include how to use the questions: spread the practice across time [CogLoad-24] [T1], and let learners try again.
- **Limitations:** No learner answered these questions. After the first use, look at the data: remove or change each distractor that fewer than 5% of the learners select. A subject-matter expert must check the answers.
- **Next steps:** Put the questions in the LMS. Run `/idstack:assessment-design` for rubrics for the performance tasks. Run `/idstack:quick-check` when you change one question.

Run the finish command of the Step Review.

**Writing standard check.** In this command, replace `<path>` with the path from the "Report path:" line. Then run the command.

```bash
_IDSTACK=""
_idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack"
_idstack_cache=""
if [ -d "$_idstack_cache_root" ]; then
  _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1)
  [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v"
fi
_idstack_skill="${CLAUDE_SKILL_DIR}"
[ -n "$_idstack_skill" ] && _idstack_skill="$_idstack_skill/../.."
for _p in "${CLAUDE_PLUGIN_ROOT}" "$_idstack_skill" "${IDSTACK_HOME:-}" "$_idstack_cache"; do
  if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi
done
if [ ! -x "$_IDSTACK/scripts/idstack-ste-check" ]; then echo "STE_CHECK_MISSING: $_IDSTACK"; elif ! command -v python3 >/dev/null 2>&1; then echo "STE_CHECK_UNAVAILABLE"; else "$_IDSTACK/scripts/idstack-ste-check" "<path>"; fi
```

For the result, do the steps in "How to use the standard" in the "Writing Standard (ASD-STE100)" section of the preamble. Do the check a maximum of three times.

Then tell the user:

"Your question bank is ready: <the Report path, written as a link as the Report Links section of the preamble tells you>. It has the test blueprint, each question with its answer and feedback, and the item check."

## Feedback

Have feedback or a feature request? [Share it here](https://forms.gle/6LDgDD1M6WWyYvME8) — no GitHub account needed.

---

## Completion: Timeline Logging

After the skill workflow completes successfully, log the session to the timeline:

```bash
_IDSTACK=""
_idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack"
_idstack_cache=""
if [ -d "$_idstack_cache_root" ]; then
  _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1)
  [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v"
fi
_idstack_skill="${CLAUDE_SKILL_DIR}"
[ -n "$_idstack_skill" ] && _idstack_skill="$_idstack_skill/../.."
for _p in "${CLAUDE_PLUGIN_ROOT}" "$_idstack_skill" "${IDSTACK_HOME:-}" "$_idstack_cache"; do
  if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi
done
IFS= read -r -d '' _EVENT <<'IDSTACK_EVENT' || true
{"skill":"question-bank","event":"completed","questions":0,"objectives":0}
IDSTACK_EVENT
"$_IDSTACK/scripts/idstack-timeline-log" "$_EVENT"
```

Replace the JSON above with actual data from this session. `objectives` is the number of blueprint rows. Log synchronously (no background &).