Hax Ubd Unit Audit

What it does

When your agent uses it

• The user says review this unit for understanding
• Is my course backward-designed
• Audit my HAX site against UbD
• Are my assessments aligned

Example prompts

• “review this unit for understanding”
• “is my course backward-designed”
• “audit my HAX site against UbD”
• “/hax-ubd-unit-audit”

Requirements

• Node.js

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Ingest structure. Locate the unit in the HAX project
2. 2Run the 12 UbD design-standards checks (../hax-ubd-backward-design/references/design-standards.md) across the unit
3. 3Map each finding to a real HAX remediation component. Use the consolidated map (../hax-ubd-backward-design/references/ubd-element-map.md)…
4. 4Determine the overall rating: Aligned | Partial | Activity-oriented | Coverage-bound (the twin sins are named diagnoses, not vague grades).
5. 5Emit the report (format below), then an "Implementation handoff" block pointing at the skill/CLI that applies each fix.

What it can do on your machine

Read from SKILL.md and the folder at commit 3542096. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • npx

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hax Ubd Unit Audit loads about 2.9k tokens when it runs. Until then it costs about 118 tokens; SKILL.md has 867 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~118

When it runs · the whole SKILL.md, loaded when a task matches

~2.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from haxtheweb/haxcms-php at commit 3542096, republished under its MIT licence (© haxtheweb). 867 words, ~2,866 tokens.

name

hax-ubd-unit-audit

description

READ-ONLY diagnostic: review an existing HAX site/unit against Understanding by Design standards and emit a report with actionable HAX remediation. Use when the user says "review this unit for understanding", "is my course backward-designed", "audit my HAX site against UbD", "are my assessments aligned", or "does this unit have big ideas" — even if they don't say "UbD". Diagnoses only; hands off to the stage skills and hax-claudehax for remediation.

version

1.0.0

license

MIT

metadata.author

PRAW

metadata.tags

instructional-design, understanding-by-design, ubd, audit, alignment, hax, diagnostic

metadata.requirements

A HAX site path (site.json + pages/*.html), optionally a files/ubd/*.manifest.json. Emits a report; does NOT edit pages or site.json.

### 📊 UbD Design Diagnostics
* **Backward-Design Rating:** [Aligned / Partial / Activity-oriented / Coverage-bound]
* **Primary Defect:** [the worst offender — one sentence]

### 🔍 Findings & HAX Remediation

* **{node / page / unit-level}**
  * **UbD Standard Violated:** [standard # + name]
  * **Issue:** [e.g., Goals present but no enduring understandings — only topic nouns]
  * **UbD Rationale:** [why this defeats understanding — cite the twin sin or alignment failure]
  * **HAX Remediation:** [real component + concrete placement, e.g. "Add a `stop-note` at the top of pages/<slug>.html carrying the essential question; add `oer-schema` learningOutcome propositions."]

* **{node / page / unit-level}**
  * ...

### 🛠 Implementation handoff
* [one-line action per fix → skill/CLI, e.g. "Rebuild Stage 2 from Stage 1 via `hax-ubd-stage2`."]

### 📊 UbD Design Diagnostics
* **Backward-Design Rating:** Activity-oriented
* **Primary Defect:** No enduring understandings or essential questions; the only
  evidence is a selected-response quiz that cannot reveal understanding.

### 🔍 Findings & HAX Remediation

* **Unit-level (site.json node "westward-expansion")**
  * **UbD Standard Violated:** #1 Big-idea focus; #2 Enduring understandings; #3 Essential questions
  * **Issue:** No big ideas, understandings, or EQs anywhere in the unit. Pages are
    activity + content only.
  * **UbD Rationale:** Activity-oriented design (twin sin #1) — "hands-on without
    being minds-on." Without explicit priorities, students cannot answer "what's
    the point?" and learning is by osmosis.
  * **HAX Remediation:** Run `hax-ubd-stage1` to derive big ideas + understandings
    + EQs from the topic. Then add a `stop-note` carrying the topical EQ to the top
    of each child page, and `oer-schema` `learningOutcome` propositions to page
    metadata.

* **Page "westward-quiz" (multiple-choice only)**
  * **UbD Standard Violated:** #6 GRASPS task; #7 facet breadth; #8 validity
  * **Issue:** The only evidence is a `multiple-choice` quiz. No performance task.
  * **UbD Rationale:** Selected response is "insufficient and sometimes misleading"
    for understanding. It can show recall, not transfer. Fails validity self-test
    Q2 (parroting) and Q1 (guessing).
  * **HAX Remediation:** Add ≥1 GRASPS performance task page via `hax-ubd-stage2`
    (authentic context via `video-player`/`image-compare-slider`; product via
    `simple-fields`; rubric via `editable-table`). Keep the quiz as OE for K/S only.

* **Page "westward-vocab" (word search)**
  * **UbD Standard Violated:** #12 triangulation
  * **Issue:** Word search is an orphan activity — equips for no Stage 2 performance.
  * **UbD Rationale:** Activity not derived from goals/evidence — the activity-oriented sin.
  * **HAX Remediation:** Drop or repurpose as an Explore/Equip (`flash-card` for
    vocab retrieval) that explicitly equips for the GRASPS task.

### 🛠 Implementation handoff
* Unit-level: run `hax-ubd-stage1` then `hax-ubd-stage2` to rebuild goals + evidence.
* Quiz page: add a GRASPS task page via `hax-ubd-stage2`; keep quiz as OE only.
* Vocab page: replace with `flash-card` Explore/Equip, or drop.
* Apply DDD tokens via `hax-design-system`; insert via `hax-claudehax` / `hax-site-building`.

© haxtheweb, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .well-known/agent-skills/hax-ubd-unit-audit of haxtheweb/haxcms-php.

Open the folder on GitHubat commit 3542096