/ux-copy
Use when writing or reviewing any visible copy — headlines, buttons, body, errors, empty states — inside a design-method move or standalone.
$ npx -y skills add fusengine/agents --skill ux-copy --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/ux-copy
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use when writing or reviewing any visible copy — headlines, buttons, body, errors, empty states — inside a design-method move or standalone.
SKILL.md
ux-copy.SKILL.mdname: ux-copy
description: "Use when writing or reviewing any visible copy — headlines, buttons, body, errors, empty states — inside a design-method move or standalone."
when-to-use: "Any time visible copy is written or reviewed — headlines, subheads, buttons, body, captions, errors, empty states — inside any design-method move, or standalone copy work."
keywords: copy, microcopy, ban-list, register, tone, error-messages, self-audit
priority: critical
related: design-method, design-review, design-web, design-webapp
<objective> A copy self-audit pass applied any time visible copy is written or reviewed — headlines, subheads, buttons, body, captions, errors, empty states — inside any `design-method` move or as standalone copy work.
Runs 10 mechanical ban-lists: filler verbs/hype adjectives, slop placeholder names, fake-precise numbers, unjustified Title Case headlines, humor in error copy ("Oops!"), the AI production-tell catalogue, em-dash-as-crutch, "Not X. Y." manufactured contrast, the "theater" keyword, and all-caps body copy.
Enforces one copy register per page (brand traces to the POV, product stays domain-specific). Judgment calls that aren't mechanically resolvable are quoted, located, and routed to `design-review`'s challenger gate — never self-scored. </objective>
UX Copy — Self-Audit + Ban-Lists, One Register Per Page
When
Any time visible copy is written or edited — headlines, subheads, eyebrows, button labels, body, captions, alt text, error messages, empty states — inside `generate`/ `critique`/`audit`/`polish` (`design-method`) or as a standalone copy pass. Register is resolved once, at Gate 0 (`design-method/SKILL.md`), before this runs — never re-guessed here.
Input
- Register (`brand`/`product`) from Gate 0.
- Sector, if resolved, for `references/voice-tone-sectors.md`.
- Every visible string in the deliverable.
One register per page — hard rule
A single copy register per page (`references/copy-self-audit.md` §7): don't mix technical mono, editorial prose, and marketing punch on one surface unless the brand voice explicitly calls for it. Register direction is conditional exactly like layout and motion (`design-method/references/register/copy.md` §3): **brand** copy must trace to the one-sentence POV — run the Competitor Lift Test on the paragraph itself, could it run unchanged on a competitor's site; **product** copy stays precise and domain-specific, naming the real object and the real action, never marketing voice bleeding into the app shell.
Ban-lists — mechanical (grep), not vibes
1. **Filler verbs / hype adjectives** — `elevate`, `seamless(ly)`, `unleash`, `next-gen`, `revolutionize`, `empower`, `supercharge`, `game-changer`, `cutting-edge`, `unlock`, `robust`, `effortless`, `frictionless`, plus `delve` and `tapestry`. Full grep pattern and flag-not-fail nuance (read against the POV or the domain-specificity floor before rewriting): `design-method/references/register/copy.md` §1. 2. **Slop placeholder names** — `Acme`, `Nexus`, `SmartFlow`, `Cloudly`, `Initech`, `Globex`, `Contoso`, `Umbrella Corp`, `Zenith (Labs/Tech)`. Blocks unless the brief explicitly names a fictional example on purpose. Grep + rule: `design-method/references/register/copy.md` §2. 3. **Fake-precise numbers** — `92%`, `4.1x`, `48k`, `99.99%`, or any figure not traced to real data, brief/brand guidelines, or an explicitly labelled mock (`<!-- mock -->`/"example"). Real data reads organic and messy (`47.2%`), not fake-perfect. `references/copy-self-audit.md` §3. 4. **Title Case headlines** — sentence case is the default register for headings and body copy; reserve Title Case for UI labels, buttons, and eyebrows only, never a body headline, unless the brand style guide explicitly specifies Title Case. Inconsistent or unjustified Title Case on headlines is a recurring AI-slop tell (grounding corpus; general consistency principle also flagged in the reference clone's capitalization check — apply it here as a default ban, not a mere consistency note). 5. **Humor in error copy ("Oops!"/"Whoops!")** — banned. Errors use the what-happened + why + how-to-fix formula (`references/templates/error-messages.md`), never cute framing — a frustrated user doesn't want jokes. Bad-example precedent already in this skill: `references/voice-tone-sectors.md` error row flags exactly `"Whoops! Something went wrong."` against the correct `"Connection lost. Try again or continue offline."` 6. **AI production-tell catalogue** — version-label eyebrows (`v0.6`/`BETA`/`EARLY ACCESS`), numbered section eyebrows (`00 / INDEX`), scroll cues, weather/locale strips, "quietly trusted by", decorative photo-credit captions, fabricated live counters, poetic craftsman labels, generic step labels (`Stage 1/2/3`). Full table: `references/copy-self-audit.md` §2. 7. **Em-dash as a crutch** — a single `—` isn't a hard fail; 2+ occurrences reading as a repeated tic is. `references/copy-self-audit.md` §1 (shared gate with `design-review`). 8. **"Not X. Y." manufactured-contrast fragments** — one instance is fine, 2+ on one page is a blocking tic. `references/copy-self-audit.md` §4. 9. **"theater"/"théâtre" keyword** — any hit blocks, near-universal AI copy tell. `references/copy-self-audit.md` §5. 10. **All-caps body copy** — 3+ consecutive all-caps words outside a recognized UI label blocks; fine inside a button/eyebrow/badge. `references/copy-self-audit.md` §6.
Steps
1. Confirm register (inherited from Gate 0) — never re-resolve it here. 2. Write/review against the sector voice profile (`references/voice-tone-sectors.md`, NNG 4 dimensions) and the matching sector guide if one applies (`references/copy-saas.md`, `references/copy-fintech.md`, `references/copy-ecommerce.md`). 3. Apply the formula references for the surface being written: buttons/forms/toasts (`references/microcopy-patterns.md`), CTAs (`refer
Read more
name: ux-copy description: "Use when writing or reviewing any visible copy — headlines, buttons, body, errors, empty states — inside a design-method move or standalone." when-to-use: "Any time visible copy is written or reviewed — headlines, subheads, buttons, body, captions, errors, empty states — inside any design-method move, or standalone copy work." keywords: copy, microcopy, ban-list, register, tone, error-messages, self-audit priority: critical related: design-method, design-review, design-web, design-webapp
<objective> A copy self-audit pass applied any time visible copy is written or reviewed — headlines, subheads, buttons, body, captions, errors, empty states — inside any `design-method` move or as standalone copy work.
Runs 10 mechanical ban-lists: filler verbs/hype adjectives, slop placeholder names, fake-precise numbers, unjustified Title Case headlines, humor in error copy ("Oops!"), the AI production-tell catalogue, em-dash-as-crutch, "Not X. Y." manufactured contrast, the "theater" keyword, and all-caps body copy.
Enforces one copy register per page (brand traces to the POV, product stays domain-specific). Judgment calls that aren't mechanically resolvable are quoted, located, and routed to `design-review`'s challenger gate — never self-scored. </objective>
UX Copy — Self-Audit + Ban-Lists, One Register Per Page
When
Any time visible copy is written or edited — headlines, subheads, eyebrows, button labels, body, captions, alt text, error messages, empty states — inside `generate`/ `critique`/`audit`/`polish` (`design-method`) or as a standalone copy pass. Register is resolved once, at Gate 0 (`design-method/SKILL.md`), before this runs — never re-guessed here.
Input
- Register (`brand`/`product`) from Gate 0.
- Sector, if resolved, for `references/voice-tone-sectors.md`.
- Every visible string in the deliverable.
One register per page — hard rule
A single copy register per page (`references/copy-self-audit.md` §7): don't mix technical mono, editorial prose, and marketing punch on one surface unless the brand voice explicitly calls for it. Register direction is conditional exactly like layout and motion (`design-method/references/register/copy.md` §3): **brand** copy must trace to the one-sentence POV — run the Competitor Lift Test on the paragraph itself, could it run unchanged on a competitor's site; **product** copy stays precise and domain-specific, naming the real object and the real action, never marketing voice bleeding into the app shell.
Ban-lists — mechanical (grep), not vibes
1. **Filler verbs / hype adjectives** — `elevate`, `seamless(ly)`, `unleash`, `next-gen`, `revolutionize`, `empower`, `supercharge`, `game-changer`, `cutting-edge`, `unlock`, `robust`, `effortless`, `frictionless`, plus `delve` and `tapestry`. Full grep pattern and flag-not-fail nuance (read against the POV or the domain-specificity floor before rewriting): `design-method/references/register/copy.md` §1. 2. **Slop placeholder names** — `Acme`, `Nexus`, `SmartFlow`, `Cloudly`, `Initech`, `Globex`, `Contoso`, `Umbrella Corp`, `Zenith (Labs/Tech)`. Blocks unless the brief explicitly names a fictional example on purpose. Grep + rule: `design-method/references/register/copy.md` §2. 3. **Fake-precise numbers** — `92%`, `4.1x`, `48k`, `99.99%`, or any figure not traced to real data, brief/brand guidelines, or an explicitly labelled mock (`<!-- mock -->`/"example"). Real data reads organic and messy (`47.2%`), not fake-perfect. `references/copy-self-audit.md` §3. 4. **Title Case headlines** — sentence case is the default register for headings and body copy; reserve Title Case for UI labels, buttons, and eyebrows only, never a body headline, unless the brand style guide explicitly specifies Title Case. Inconsistent or unjustified Title Case on headlines is a recurring AI-slop tell (grounding corpus; general consistency principle also flagged in the reference clone's capitalization check — apply it here as a default ban, not a mere consistency note). 5. **Humor in error copy ("Oops!"/"Whoops!")** — banned. Errors use the what-happened + why + how-to-fix formula (`references/templates/error-messages.md`), never cute framing — a frustrated user doesn't want jokes. Bad-example precedent already in this skill: `references/voice-tone-sectors.md` error row flags exactly `"Whoops! Something went wrong."` against the correct `"Connection lost. Try again or continue offline."` 6. **AI production-tell catalogue** — version-label eyebrows (`v0.6`/`BETA`/`EARLY ACCESS`), numbered section eyebrows (`00 / INDEX`), scroll cues, weather/locale strips, "quietly trusted by", decorative photo-credit captions, fabricated live counters, poetic craftsman labels, generic step labels (`Stage 1/2/3`). Full table: `references/copy-self-audit.md` §2. 7. **Em-dash as a crutch** — a single `—` isn't a hard fail; 2+ occurrences reading as a repeated tic is. `references/copy-self-audit.md` §1 (shared gate with `design-review`). 8. **"Not X. Y." manufactured-contrast fragments** — one instance is fine, 2+ on one page is a blocking tic. `references/copy-self-audit.md` §4. 9. **"theater"/"théâtre" keyword** — any hit blocks, near-universal AI copy tell. `references/copy-self-audit.md` §5. 10. **All-caps body copy** — 3+ consecutive all-caps words outside a recognized UI label blocks; fine inside a button/eyebrow/badge. `references/copy-self-audit.md` §6.
Steps
1. Confirm register (inherited from Gate 0) — never re-resolve it here. 2. Write/review against the sector voice profile (`references/voice-tone-sectors.md`, NNG 4 dimensions) and the matching sector guide if one applies (`references/copy-saas.md`, `references/copy-fintech.md`, `references/copy-ecommerce.md`). 3. Apply the formula references for the surface being written: buttons/forms/toasts (`references/microcopy-patterns.md`), CTAs (`refer
Showing the first part of this file.
A plugin ecosystem that turns Claude Code into a supervised, multi-agent development environment.
Repo: fusengine/agents
Other skills on fusengine-agents.
- /agent-creator
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Open skill - /apex-methodology
Use when starting ANY development task -- feature, bug fix, refactor, hotfix (triggers: implement, create, build, fix, add feature, refactor, develop).
Open skill - /brainstorming
Use when creating a feature/component or adding functionality. Fires BEFORE APEX Analyze to refine requirements via structured questioning.
Open skill - /challenge
Use before a root-cause, done/verified claim, irreversible action, or 2nd-time fix reaches the owner (APEX or plain conversation); also fires at every eLicit/Verify gate. Not for code correctness (use sniper).
Open skill - /code-quality
Use when validating code quality after modifications -- SOLID compliance, DRY duplication, linter errors, architecture violations. Do NOT use for functional verification (run verification FIRST, then code-quality).
Open skill - /elicitation
Use when an expert agent self-reviews and self-corrects code after the Execute phase, before sniper validation (BMAD-METHOD elicitation techniques).
Open skill

