Agent skill

Hax Ubd Stage3

by haxtheweb in haxtheweb/haxcms-php

UbD Stage 3 — plan learning experiences via WHERETO, derived from Stages 1+2.

MITAuto-check passedEducation

Install Hax Ubd Stage3

skills CLI
$ npx skills add haxtheweb/haxcms-php --skill hax-ubd-stage3 -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install haxtheweb/haxcms-php hax-ubd-stage3 --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/haxtheweb/haxcms-php.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.well-known/agent-skills/hax-ubd-stage3 .claude/skills/hax-ubd-stage3 && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
hax-ubd-stage3
GitHub stars
130
Token cost
~1.9k tokens
SKILL.md length
707 words
Files
1
Skills in repo
18
Repo updated
First seen
Licence
MIT

At a glance

UbD Stage 3 — plan learning experiences via WHERETO, derived from Stages 1+2.

  • Works in 6 steps: Resist the comfortable-activity reflex.… → Sequence via WHERETO (UbD Fig 9.1),… → Uncoverage over coverage. Use… → …
  • The user says sequence this unit
  • SKILL.md covers When to Use, Scope, Inputs and Methodology, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Hax Ubd Stage3 is an agent skill from haxtheweb/haxcms-php. UbD Stage 3 — plan learning experiences via WHERETO, derived from Stages 1+2. Enforce uncoverage over coverage and build feedback/revision cycles. Use when the user says "sequence this unit", "plan the learning activities", "WHERETO my unit", "how do I teach for understanding", or "organize these pages". Encodes UbD Ch. 9–10. Stage 3 points AT Stage 2 evidence; it never invents new endpoints.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Education, covering Lesson planning. The repository describes itself as: HAX + CMS to manage your microsite universe with PHP backend. The licence is MIT.

When your agent uses it

  • The user says sequence this unit
  • Plan the learning activities
  • WHERETO my unit
  • How do I teach for understanding

Example prompts

  • “sequence this unit”
  • “plan the learning activities”
  • “WHERETO my unit”
  • “/hax-ubd-stage3”

Workflow steps

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

  1. Resist the comfortable-activity reflex. For every proposed activity, ask: does it equip learners for a Stage 2 performance, or serve a…
  2. Sequence via WHERETO (UbD Fig 9.1), mapping each letter to HAX (table below). The two E's are distinct: Explore/Equip (build knowledge +…
  3. Uncoverage over coverage. Use progressive disclosure (a11y-collapse with heading-button, a11y-tabs) for depth. Never page-march a…
  4. Feedback + revision cycles. Insert self-check / stop-note loops (Rethink/Revise) between Explore and Exhibit. Understanding develops…
  5. Exhibit points to Stage 2. The Exhibit is the GRASPS task from manifest.stage2.performanceTasks[*] — reference its id in…
  6. Organize the site.json child page ordering to match the WHERETO sequence; use map-menu for the unit map. Run page content through…

What it can do on your machine

Read from SKILL.md and the folder at commit 6712afe. 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 Stage3 loads about 1.9k tokens when it runs. Until then it costs about 103 tokens; SKILL.md has 707 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~103
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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 6712afe, republished under its MIT licence (© haxtheweb). 707 words, ~1,893 tokens.

Download SKILL.mdSave it as .claude/skills/hax-ubd-stage3/SKILL.md (or your agent's skills folder).
name
hax-ubd-stage3
description
UbD Stage 3 — plan learning experiences via WHERETO, derived from Stages 1+2. Enforce uncoverage over coverage and build feedback/revision cycles. Use when the user says "sequence this unit", "plan the learning activities", "WHERETO my unit", "how do I teach for understanding", or "organize these pages". Encodes UbD Ch. 9–10. Stage 3 points AT Stage 2 evidence; it never invents new endpoints.
version
1.0.0
license
MIT
metadata.author
PRAW
metadata.tags
instructional-design, understanding-by-design, ubd, stage3, whereto, uncoverage, learning-plan, hax
metadata.requirements
manifest.stage1 AND manifest.stage2 MUST be populated (Stage 3 is derived from goals + evidence). Writes manifest.stage3 + site.json ordering + per-page…

HAX UbD Stage 3 — Planning Learning (WHERETO)

Derive and sequence learning experiences from Stages 1 and 2 via WHERETO, enforcing uncoverage over coverage and building feedback + revision cycles. This is Stage 3 of UbD — the learning plan. It comes last in backward design because every activity must be justified by the goals (Stage 1) and the targeted performances (Stage 2).

The core move: resist the comfortable-activity reflex. Test every proposed activity against Stages 1+2 — does it equip learners for the targeted performances? If not, drop it. "Teaching" (direct instruction) is only one learning activity among many.

When to Use

Trigger conditions:

  • "Sequence this unit" / "plan the learning activities" / "WHERETO my unit"
  • "How do I teach for understanding" / "organize these pages"
  • You are hax-ubd-backward-design and have reached step 5 of its methodology

When NOT to use (with redirect):

  • Page-level cognitive load / chunking → hax-content-chunking-audit (chunking = page scope; WHERETO = unit scope)
  • Cognitive level of an objective → grad-blooms
  • Goals → hax-ubd-stage1; evidence/assessments → hax-ubd-stage2

Scope

Mutating. Writes manifest.stage3 + site.json page ordering + a per-page component plan. Does NOT invent new endpoints — Stage 3 points at Stage 2's evidence (the Exhibit references a real stage2.performanceTasks[*].id).

Inputs

  • manifest.stage1 + manifest.stage2 — both required. Stage 3 is derived; do not sequence without goals + evidence.

Methodology

  1. Resist the comfortable-activity reflex. For every proposed activity, ask: does it equip learners for a Stage 2 performance, or serve a Stage 1 understanding? If neither, drop it. This is where the twin sin of activity-oriented design is avoided.

  2. Sequence via WHERETO (UbD Fig 9.1), mapping each letter to HAX (table below). The two E's are distinct: Explore/Equip (build knowledge + coach skills) vs. Exhibit/Evaluate (the final performance).

  3. Uncoverage over coverage. Use progressive disclosure (a11y-collapse with heading-button, a11y-tabs) for depth. Never page-march a textbook. Coverage = "teaching by mentioning it"; uncoverage = going into depth on the big ideas. (A purposeful survey is legitimate; coverage is not.)

  4. Feedback + revision cycles. Insert self-check / stop-note loops (Rethink/Revise) between Explore and Exhibit. Understanding develops through inquiry + rethinking; build in perform→feedback→revise→perform cycles, as in apprenticeship/coaching.

  5. Exhibit points to Stage 2. The Exhibit is the GRASPS task from manifest.stage2.performanceTasks[*] — reference its id in whereto.exhibit.taskRef. Do NOT create a new endpoint here.

  6. Organize the site.json child page ordering to match the WHERETO sequence; use map-menu for the unit map. Run page content through hax-content-chunking-audit per-page and apply DDD tokens via hax-design-system.

Show full SKILL.md (316 more words)Show less

HAX Component Map (WHERETO)

LetterMeaningComponent(s)
WWhere/Why — show destination + criteriaprogress-donut / simple-progress / promise-progress + page intro
HHook — provocative entryvideo-player, image-compare-slider, media-quote, stop-note (provocative Q)
EExplore/Equip — content + coachingcontent + flash-card, self-check, lrndesign-imagemap
RRethink/Revise — feedback cyclesself-check + stop-note loops, flash-card (retrieval)
EExhibit/Evaluate — the performanceGRASPS page (ref Stage 2) + clean-portfolio-theme / glossy-portfolio-theme + grade-book + editable-table rubric
TTailor — differentiate / choicea11y-tabs, a11y-collapse (set heading-button)
OOrganize — sequence + uncoveragesite.json ordering + map-menu + a11y-collapse (set heading-button)

Full map (all stages): ../hax-ubd-backward-design/references/ubd-element-map.md.

Output Format

# Stage 3 — WHERETO: {unit}
## Sequence
1. {page slug} — W: {components} → shows destination
2. {page slug} — H: {components} → hooks into EQ
3. {page slug} — E (Equip): {components} → equips for: {task id}
4. {page slug} — R: {components} → feedback to: {task id}
5. {page slug} — E (Exhibit): {components} → exhibits: {task id}
6. {page slug} — T: {components} → choice options
## Uncoverage plan
{what goes deep vs. what is surveyed; where a11y-collapse/a11y-tabs disclose depth}
## Feedback cycles
{loop placements: self-check/stop-note between Explore and Exhibit}
## site.json ordering
{child node order = WHERETO order}
## HAX handoff
{per-page component list + DDD token note}

Acceptance criteria

  • Every sequence[*].evidenceRef resolves to a stage2 item (or is explicitly an Explore/Equip with no evidence target).
  • Exactly one Exhibit step; its taskRef resolves to a real stage2.performanceTasks[*].id.
  • ≥1 Rethink/Revise loop between Explore and Exhibit.
  • No activity in the sequence lacks a Stage 1/2 justification (no orphan activities — the anti-activity-oriented-sin invariant).
  • a11y-collapse / a11y-tabs usages set heading-button (PRAW rule).

Gotchas

  • "Teaching" is only one learning activity. Don't default to direct instruction. The focus is planning learnings, not teachings.
  • Don't duplicate Stage 2's evidence as a new "Exhibit." The exhibit is the GRASPS task. If you find yourself inventing a new culminating task, stop — you're in Stage 2 territory; go back.
  • Over-fragmenting hurts. A coherent short argument split into tiny chunks can hurt coherence more than a readable block helps (same caveat as hax-content-chunking-audit). Use progressive disclosure for depth, not to mince cohesive content.
  • Uncoverage ≠ never surveying. A purposeful, transparent overview is legitimate. Coverage (content march with no overarching purpose) is the sin.
  • WHERETO is a checklist, not a rigid order. The letters ensure nothing is forgotten; the actual order serves the learners. But W (where we're going) almost always comes early, and Exhibit comes last.

Dependencies

  • Reads: manifest.stage1 + manifest.stage2 (both required)
  • Hands off to: hax-claudehax / hax-site-building (materialization); hax-content-chunking-audit (per-page); hax-design-system (DDD tokens)

References

  • ../hax-ubd-backward-design/references/manifest-schema.md — stage3 fields
  • ../hax-ubd-backward-design/references/ubd-element-map.md — WHERETO component map
  • ../hax-ubd-backward-design/references/design-standards.md — standards 10–12
  • PRAW RULES.md: ~/Documents/git/haxtheweb/praw/RULES.md
  • Source: Wiggins & McTighe (2005), UbD Ch. 9–10.

© 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-stage3 of haxtheweb/haxcms-php.

Open the folder on GitHubat commit 6712afe

Compare with similar skills

Hax Ubd Stage3 next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Hax Ubd Stage3 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hax Ubd Stage3 this skillhaxtheweb/haxcms-php130—~1.9kAutomated safety check: PassMIT
K-12 Core Literacy Lesson DesignTHU-MAIC/OpenMAIC40k—~2.4kAutomated safety check: PassMIT
Zone of Proximal Development Practice LessonsTHU-MAIC/OpenMAIC40k—~1.1kAutomated safety check: PassMIT
Curriculum PlannerTHU-MAIC/OpenMAIC40k—~2.8kAutomated safety check: PassMIT
Deep Interactive Course DesignTHU-MAIC/OpenMAIC40k—~681Automated safety check: PassMIT
Learndair-ai/dair-academy-plugins6142 repos~1.3kAutomated safety check: PassMIT

Similar skills

  • Designs a Chinese K-12 classroom for one OpenMAIC stage around the core-literacy model, using authentic tasks, performance assessment and observable evidence.

    40k GitHub stars~2.4k tokensUpdated today
    EducationAuto-check passed
  • Designs a review-and-practice lesson around an independent first attempt, targeted feedback, supported practice, a fresh independent check and a next step.

    40k GitHub stars~1.1k tokensUpdated today
    EducationAuto-check passed
  • Curriculum Planner

    THU-MAIC/OpenMAIC

    Plans a multi-classroom series such as a seven-day course, clarifies the brief in rounds, gets sign-off on the full lesson list, then builds each stage in a shared folder.

    40k GitHub stars~2.8k tokensUpdated today
    EducationAuto-check passed
  • Plans online courses so learners manipulate simulations, diagrams, code, games or 3D scenes on most pages, with slides only for the opening and the close.

    40k GitHub stars~681 tokensUpdated today
    EducationAuto-check passed
  • Learn

    dair-ai/dair-academy-plugins

    Help a user learn a topic through adaptive tutoring, lesson planning, practice, retrieval checks, explanations, study guides, or exercises.

    614 GitHub starsUsed in 2 repos~1.3k tokens
    EducationAuto-check passed
  • Turns a concept or lesson material into a Feynman-style classroom where learners explain first, find their smallest gap, rebuild the idea and apply it somewhere new.

    40k GitHub stars~955 tokensUpdated today
    EducationAuto-check passed

More from haxtheweb/haxcms-php

All 18 skills in this repo
  • Ddev

    haxtheweb/haxcms-php

    DDEV local development environment guidance for Docker-based PHP/Node projects.

    130 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed
  • Hax Ubd Backward Design

    haxtheweb/haxcms-php

    Design HAX course units via Understanding by Design (UbD) backward design — start from desired results, derive acceptable evidence, then plan learning experiences.

    130 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed
  • Hax Udl Audit

    haxtheweb/haxcms-php

    READ-ONLY diagnostic: review a HAX site/page against Universal Design for Learning (UDL) 3.0 — multiple means of Engagement, Representation, and Action & Expression — and emit a report with…

    130 GitHub stars~3.7k tokensUpdated yesterday
    Auto-check passed
  • Haxcms Lrs Rater

    haxtheweb/haxcms-php

    Run BookLooky's Looky Rating System (LRS) content rating and minimum-age recommendation on a HAXcms site's aggregated content — either a local site checkout or a live published URL like btopro.com —…

    130 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed
  • Oerschema Integration Finder

    haxtheweb/haxcms-php

    READ-ONLY diagnostic: scan HAX webcomponents, themes, CMS backends (PHP/NodeJS HAXcms), the VitePress plugin, and the Google Apps Script add-on for code surfaces that render or consume pedagogical…

    130 GitHub stars~4.1k tokensUpdated yesterday
    Auto-check passed
  • Hax A11y Audit

    haxtheweb/haxcms-php

    READ-ONLY diagnostic: review authored HAX page/site content against WCAG 2.0 AA (image alt text, heading hierarchy, landmark structure, link text, form labels, color contrast, media…

    130 GitHub stars~5.5k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Hax Ubd Stage3

What does Hax Ubd Stage3 do?

UbD Stage 3 — plan learning experiences via WHERETO, derived from Stages 1+2. Hax Ubd Stage3 is an agent skill from haxtheweb/haxcms-php. UbD Stage 3 — plan learning experiences via WHERETO, derived from Stages 1+2.

When should I use Hax Ubd Stage3?

Hax Ubd Stage3 fits situations like: the user says sequence this unit; plan the learning activities; WHERETO my unit; how do I teach for understanding.

How do I install Hax Ubd Stage3 in Claude Code?

Run `npx skills add haxtheweb/haxcms-php --skill hax-ubd-stage3 -a claude-code`. Or copy the skill folder (.well-known/agent-skills/hax-ubd-stage3 in haxtheweb/haxcms-php) into .claude/skills/hax-ubd-stage3 in your project. Claude Code loads it when a task matches its description.

How do I install Hax Ubd Stage3 in Codex?

Run `npx skills add haxtheweb/haxcms-php --skill hax-ubd-stage3 -a codex`. Or copy the skill folder (.well-known/agent-skills/hax-ubd-stage3 in haxtheweb/haxcms-php) into .agents/skills/hax-ubd-stage3 in your project. Codex loads it when a task matches its description.

Can I use Hax Ubd Stage3 in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add haxtheweb/haxcms-php --skill hax-ubd-stage3 -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hax-ubd-stage3, .gemini/skills/hax-ubd-stage3, .github/skills/hax-ubd-stage3 and .opencode/skills/hax-ubd-stage3 in your project.

What does Hax Ubd Stage3 need to run?

SKILL.md names no scripts, command-line tools or credentials: Hax Ubd Stage3 is instructions for the agent only.

Does Hax Ubd Stage3 access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Hax Ubd Stage3 safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Hax Ubd Stage3 use?

Hax Ubd Stage3 is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hax Ubd Stage3 use?

About 1.9k tokens (SKILL.md is roughly 7.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Hax Ubd Stage3?

Skills that share tags, products or a category with Hax Ubd Stage3: K-12 Core Literacy Lesson Design (THU-MAIC/OpenMAIC, 40k stars), Zone of Proximal Development Practice Lessons (THU-MAIC/OpenMAIC, 40k stars), Curriculum Planner (THU-MAIC/OpenMAIC, 40k stars) and Deep Interactive Course Design (THU-MAIC/OpenMAIC, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hax Ubd Stage3?

haxtheweb (a GitHub organization) maintains it in haxtheweb/haxcms-php, which has 130 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 8, 2026.

Source: haxtheweb/haxcms-php on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.