Body Text And Reading
Use when setting or fixing running text meant to be read continuously — article bodies, documentation, long-form pages, onboarding copy, email. Also use when readers report eye strain, losing their place, re-reading lines, or text that "feels dense", and when choosing body size, line-height, or measure.
Nd Working Memory
Maintain explicit task context across subtasks and persist it in one durable working surface when interruptions, multiple turns, or multiple agents could lose the thread. Re-state active goals when context grows long, track what is in flight, and provide an exact re-entry action.
Nd Velocity Check
Track and surface the ratio of ideas captured vs items shipped. Warn when the capture:ship ratio is high — the ideas-rich/finish-poor pattern made visible.
Responsive Typography
Use when type must adapt across viewports, containers, or devices — fluid sizing with clamp(), breakpoint jumps, text that overflows or shrinks illegibly on mobile, headings that wrap badly, or a scale that works on desktop and collapses on phone. Also use when building a type system intended to be resolution-independent.
Vd Done Is Executed
The always-on governor against over-claimed completion. Never call work done, fixed, passing, working, wired, or complete unless you RAN the actual Done criterion end-to-end and observed the result with your own eyes. Code that would work, a traced code path, a passing adjacent layer, or "looks right" are NOT done. Applies silently to every completion, success, or "it works" claim; dispatches the…
Typography Accessibility
Use whenever type carries information — always co-load this with body text, UI, and editorial typography work. Specifically for contrast, 200% zoom, user text-spacing overrides, Dynamic Type, dyslexia and low-vision needs, screen-reader compatibility, images of text, and any claim that typography is "accessible".
Editorial Web Typography
Use when designing article, long-form, marketing, or art-directed pages — pull quotes, drop caps, captions, bylines, subheads, figures, footnotes, hero compositions. Also use when an article template feels flat and undifferentiated, or when a page needs expressive typographic voice without sacrificing readability.
Nd Task Initiation
When a user faces a blank page, explicitly says they are stuck or avoiding a known task, or does not know where to start, create the smallest concrete first action and, when needed, add one truthful interest, novelty, challenge, feedback, or body-doubling bridge. Never invent urgency or use shame.
Nd Choicereduce
When presenting options or a backlog, show only the top 3. Hidden items are noted but not shown until one choice is completed.
Vd Run The Real Path
When you can run it, run it. Prefer executing the real path — the one-shot command, the actual agent loop, the failing test now passing, the app in front of you — over inspecting the code that would run. "Looks right" and "the code clearly does X" are smells to verify, not conclusions. Use whenever you're about to conclude from reading rather than from running, especially when execution is cheap…
Type Foundations
Use when typographic vocabulary or first principles are needed — what an em actually is, font vs typeface, leading vs line-height, points vs pixels, how CSS units relate, what the em square means. Also use when someone is confidently using a term incorrectly, or when an explanation needs grounding before a decision is made.
Color And Icon Fonts
Use when type needs to be more than one flat colour, or when glyphs carry non-letter meaning — layer fonts, colour fonts (COLRv1, OT-SVG, bitmap), CSS font-palette, icon fonts, emoji. Also use when deciding between an icon font and SVG, when a colour font renders as flat black, or when emoji or icons break in a screen reader.
Design Token Generation
Use when turning typographic decisions into tokens, variables, or theme config — naming a type scale, structuring font/size/weight/line-height tokens, exporting to CSS/Tailwind/Style Dictionary/iOS/Android, or fixing a token set that has drifted into arbitrary values. Also use when design and code disagree about what the type scale actually is.
Typeface Selection
Use when choosing or replacing a typeface — "which font should we use", evaluating candidates, building a type palette, or replacing a face that isn't working. Also use when a font must carry a brand tone, survive small sizes, support extra scripts, or fit a licensing and performance budget.
Typeface Pairing
Use when combining two or more typefaces — heading plus body, display plus UI, adding a face to an existing system, or diagnosing a pairing that "clashes" or "looks the same". Also use when deciding whether a second typeface is needed at all.
Typography Critique
Use when the question is quality or taste rather than compliance — "is this any good", "does this feel right", "why does this look generic or AI-generated", art-direction review, or judging whether a typographic risk pays off. Use typography-audit instead when checking against defined criteria.
Font Loading And Performance
Use when shipping webfonts — choosing formats, subsetting, preloading, setting font-display, eliminating FOUT/FOIT, or fixing layout shift (CLS) caused by font swap. Also use when fonts are slow, text is invisible on load, the page jumps when fonts arrive, or Core Web Vitals flag font-related shift.
Nd Emotion Regulation
Stabilize task execution when the user explicitly reports frustration, shame, panic, anger, rejection, or overwhelm that is affecting decisions. Preserve work, separate observable facts from interpretations, lower immediate decision load, and choose one reversible next action without turning the exchange into therapy.
Typography Audit
Use when systematically reviewing existing typography against criteria — "check this page", "audit our type", pre-launch review, design-system compliance, or inherited work of unknown quality. Produces a pass/fail finding list with evidence. Use typography-critique instead when the question is about taste rather than compliance.
Nd Inhibit
Before each significant action, check whether it serves the current goal. After 3 adjacent off-goal actions, name the drift explicitly.
Nd Selfmonitor
Before destructive or hard-to-reverse operations, pause to verify the action matches the stated goal. A one-sentence pre-flight check, not a gate.
Nd Task Decomposition
Turn a vague, oversized, dependency-heavy, or initiation-resistant outcome into independently verifiable units with a visible first action and observable definition of done. Use when the user cannot identify where to begin, hidden dependencies block action, or a complex request needs execution structure after planning is accepted.
Nd Setshift
When stuck on the same approach for 3+ iterations, detect the pattern and propose an alternative strategy. Read prior failure logs before attempting a complex fix.
Nd Time Blindness
Externalize uncertain time with calibrated best, realistic, and worst ranges, hidden costs, checkpoints, and stopping rules. Use for estimates, open-ended research or refinement, work likely to expand, and tasks where elapsed-time feedback should revise the forecast.
Nd Hyperfocus Guard
Detect and name hyperfocus sessions that have gone deep on a rabbit hole. Surface the original goal and offer a structured way back.
Nd Research Gate
Interrupt research spirals after N turns without concrete output. Surface the pattern, name the original goal, and offer a one-question redirect to execution.
Nd Goal Persistence
Preserve an explicit terminal goal across subtasks and keep executing safe, authorized work until its end-to-end done condition is observed or a genuine blocker is reached. Use when the user says finish all, do not stop, continue until done, complete every item, or supplies a multi-item backlog whose intermediate milestones must not be mistaken for completion.
Nd Complexity Gate
Detect complex or multi-step requests and suggest structured planning before acting. Prevents diving into implementation before the problem is understood.
Vd Claim Ledger
Before any completion or success claim, build a claim→evidence ledger. Tag each sub-claim ✅ executed (ran it, saw the output), ◐ code-path (read the code, did not run), or ○ assumed, and state explicitly what each piece of evidence does NOT establish. Only ✅ across every Done criterion counts as done. Use whenever you're about to say something works, is wired, passes, or is complete.
Nd Taskboundary
Mark explicit cognitive task boundaries when topics shift or an interruption risks losing state. Save the active outcome, last verified fact, current action, blocker, and exact re-entry step before beginning the new context.
Type
Use when the user invokes /type, or when any task involves setting, choosing, scaling, spacing, loading, tokenizing, auditing, or critiquing type — a font choice, a type scale, body copy, headings, a data table, a UI label, responsive text, webfont performance, or non-Latin script. Also use when a screen "looks off" and the cause may be typographic. Dispatcher that routes to the focused typograph…
Nd Environment Scaffold
Redesign the task environment when a known intention repeatedly fails at the point of action. Use when reminders arrive too early or late, tools or state are hard to find, choices or steps create friction, a system depends on memory, or repeated failure shows that effort alone is not enough.
Motion Typography
Use when type moves or changes over time — animated headlines, kinetic type, text transitions, animated or responsive logotypes, scroll-driven text effects, typing/counting animations, variable-font axis animation, or loading and streaming text. Also use when motion is making text hard to read, causing discomfort, or failing reduced-motion and accessibility requirements.
Vanta
A local AI agent with a Rust safety kernel that gates every action — goal-aware, provider-agnostic, self-hosted. MIT.
Nd Executive Function Router
Route work to the least intrusive executive-function support based on explicit signals about current capacity, activation, memory load, emotional intensity, sensory or language load, environmental friction, and time or transitions. Use when a task feels stuck, overwhelming, difficult to hold in mind, or when the user asks for neurodivergent-friendly support without wanting an intake or coaching r…
Typeface Anatomy
Use when reading a specimen, naming letterform parts, or explaining why two typefaces differ — apertures, counters, terminals, stroke contrast, axis, x-height, proportions. Also use when a font choice needs to be justified from visible evidence rather than vibes, or when comparing candidates that "look basically the same".
Ableton Mcp
Control Ableton Live with AI - 200+ tools via MCP, REST API, and Max for Live. Works with Claude, Ollama, OpenAI, Groq.
Nd Sensory Load
Reduce language, information, sensory, and uncertainty load while preserving complete information. Use when the user requests direct or scannable communication, explicitly reports overload or low capacity, is navigating an unfamiliar flow, or needs clear expectations and examples.
International Typography
Use whenever type will render in a non-Latin script or a language other than English — Arabic, Hebrew, CJK, Indic, Cyrillic, Greek, Thai. Also use for bidirectional text, vertical writing, localisation-driven layout breakage, font stacks for multiple scripts, and any assumption that Latin typographic rules generalise.
Nd
Manually route the current request through the installed neurodivergent-support skill pack. Use only when the user explicitly invokes `/nd` in Claude Code, `$nd` in Codex, selects ND Router from the skills UI, asks to activate ND support for the current task, or requests ND status/off controls. Select the smallest relevant subset of sibling `nd-*` skills and continue useful work instead of merely…
Microtypography
Use when text is technically correct but reads poorly — uneven word spacing, rivers, bad rags, orphans and widows, awkward hyphenation, loose or tight tracking, wrong quote marks and dashes, cramped all-caps. Also use when a design "feels cheap", "looks AI-generated", or "something is off" and the cause is spacing detail rather than font choice.
Nd Closuregate
Before starting a new task thread, surface any tasks that are more than halfway complete. Ask whether to close one first. One-tap dismiss. Never blocks.
Vd Report The Gap
When work is partial or unverified, say so plainly and specifically — before the user has to push. Name which Done criteria are executed, which are only code-path, and which are unrun; never let "done", "complete", or "passing" paper over a gap. Scrutinize good news (a green test, "looks good") as hard as bad news. Use whenever reporting status, finishing a task, or about to use a completion word…
Typography Layout Systems
Use when composing type in space rather than sizing it — deciding how a poster, hero, editorial spread, dashboard, or landing page is structurally organized. Also use when a layout feels arbitrary, elements float without relationship, a grid is being applied by reflex, or a composition needs deliberate tension or movement.
Variable Fonts
Use when working with variable fonts — choosing between variable and static files, using weight/width/optical-size/slant axes, setting font-variation-settings vs standard properties, animating axes, or deciding whether a variable font actually saves bytes. Also use when a variable font renders wrong or ignores its axes.
Ui Component Typography
Use when setting type inside interface components — buttons, labels, inputs, form errors, navigation, badges, tooltips, tables, dense dashboards. Also use when numbers jitter in a table, labels wrap unpredictably, UI text is illegible at small sizes, or a component's text breaks in another language.
Vd Plumbing Vs Behavior
A passing lower layer or adjacent entry point does not prove the user-facing behavior. Verifying a direct tools/call over stdio is not the agent deciding to call the tool with its persona; a green unit test is not the feature working; a reachable endpoint is not the flow succeeding. Use when tempted to generalize "the plumbing works" into "the feature works" — identify the actual user path and ex…
Nd Functional Minimums
Reduce work to the smallest safe and useful outcome when the user explicitly reports low capacity, depletion, burnout, overwhelm, or asks for the minimum viable version. Preserve safety and function while deferring polish, and execute the reduced outcome when permissions allow.
Hierarchy And Scale
Use when building or fixing a type scale, choosing heading sizes, or when a screen's importance ordering is unclear — everything looks the same weight, users miss the primary action, or headings compete. Also use when a design has drifted into a dozen ad-hoc font sizes.