Hax Ubd Stage2

What it does

When your agent uses it

• The user says what evidence do I need
• Design a performance task
• Build a GRASPS task
• What assessments prove understanding

Example prompts

• “what evidence do I need”
• “design a performance task”
• “build a GRASPS task”
• “/hax-ubd-stage2”

Workflow steps

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

1. 1Map the scrapbook across the assessment continuum (UbD Fig 7.4/7.5): performance tasks (T) + academic prompts + quiz/test items + informal…
2. 2Frame ≥1 core GRASPS task (UbD Fig 7.7 prompts): Goal, Role, Audience, Situation, Performance/Product, Standards. The task must be…
3. 3Problem vs. exercise check (UbD Fig 7.6): confirm ≥1 task is a genuine problem — no cues about how to frame/solve it, multiple approaches…
4. 4Six-facet rubric blueprint (UbD Fig 7.9): for each targeted understanding, pick the facet(s) that yield the strongest evidence and build…
5. 5Validity self-test (../hax-ubd-backward-design/references/validity-self-test.md): run the 7 questions on every proposed assessment…
6. 6Reliability check: ensure multiple measures over time (progress-donut / simple-progress / promise-progress + grade-book), not one…

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

  No scripts in the folder and no shell commands in SKILL.md.

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

• Network

  No URLs in SKILL.md.

  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 Stage2 loads about 2.3k tokens when it runs. Until then it costs about 117 tokens; SKILL.md has 855 words of instructions outside code blocks.

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

~117

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

~2.3k

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). 855 words, ~2,257 tokens.

name

hax-ubd-stage2

description

UbD Stage 2 — think like an assessor: build a scrapbook of acceptable evidence, frame ≥1 GRASPS performance task, map the six facets to rubric criteria, enforce problem-not-exercise, and run the 7-question validity self-test. Use when the user says "what evidence do I need", "design a performance task", "build a GRASPS task", "what assessments prove understanding", or "is this assessment valid". Encodes UbD Ch. 7–8. The most distinctive UbD skill.

version

1.0.0

license

MIT

metadata.author

PRAW

metadata.tags

instructional-design, understanding-by-design, ubd, stage2, assessment, grasps, six-facets, validity, hax

metadata.requirements

manifest.stage1 MUST be populated (Stage 2 is derived from goals). Writes manifest.stage2 + assessment pages + editable-table rubrics.

# Stage 2 — Acceptable Evidence: {unit}
## Evidence scrapbook
- T (performance): {GRASPS summary} → page {slug}; facets: {...}; problem-not-exercise: yes; targets: {U}
- OE (academic prompts): {...} → stop-note + simple-fields
- OE (quiz/test): {...} → {components}
- OE (informal checks): {...} → {components}
## GRASPS task {id}
G: {...} | R: {...} | A: {...} | S: {...} | P: {...} | S (standards): {...}
## Rubric (facet-mapped)
| Criterion | Facet | Level 4 | Level 1 |
## Validity self-test
{7 questions → answers; defects + redesign}
## Reliability
{longitudinal evidence plan: components + cadence}
## HAX handoff
{page + component list per evidence item}

© 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-stage2 of haxtheweb/haxcms-php.

Open the folder on GitHubat commit 3542096