Output Style Creator
Run a five-question wizard that writes a new compliant `output-styles/<name>.md` file from your repo’s output-style guidelines.
Overview
Output Style Creator is an agent skill most often used in Build (also Launch distribution prep, Grow support tone) that runs a five-question wizard and writes a guidelines-compliant file under `output-styles/`.
Install
npx skills add https://github.com/fearovex/claude-config --skill output-style-creatorWhat is this skill?
- Hard gate: refuses to run unless `docs/output-style-guidelines.md` exists
- Step 2 collects a kebab-case experience name and blocks character/role names (`pirate`, `sergeant`, human names)
- Wizard asks five focused questions one at a time with explicit STOP/wait after each answer
- Validates collisions at `output-styles/<name>.md` and offers overwrite vs rename
- Triggers include `/output-style-create`, create output style, new output style, generate output style, add output style
- 5 focused wizard questions asked one at a time with STOP after each
- Hard dependency on docs/output-style-guidelines.md before any file is written
Adoption & trust: 1 installs on skills.sh; 1 GitHub stars; trending (+100% hot-view momentum).
What problem does it solve?
You want a new assistant output style but lack a consistent, spec-driven file and keep drifting into non-compliant character personas or duplicate style names.
Who is it for?
Solo maintainers of a claude-config-style repo who already wrote output-style guidelines and need another tone variant fast.
Skip if: Repos without `docs/output-style-guidelines.md`, teams wanting one-off chat personas without persistent style files, or users who refuse the step-by-step Q&A pacing.
When should I use this skill?
/output-style-create, create output style, new output style, generate output style, or add output style when guidelines already exist.
What do I get? / Deliverables
You get a new `output-styles/<name>.md` file that follows `docs/output-style-guidelines.md` after five explicit answers, ready to plug into your agent config.
- New or overwritten `output-styles/<name>.md` compliant with the guidelines
- Validated non-character style naming decision
- Captured answers from the five-question wizard embedded in the style file content
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Custom output styles are agent tooling created while shaping how your coding agent speaks—canonical shelf is build/agent-tooling even though you may revisit tone during grow or operate. The skill generates configuration artifacts under `output-styles/`, which is agent tooling rather than app frontend or backend code.
Where it fits
Add a `concise` output style so implementation agents stop over-explaining during feature work.
Create a `launch-clear` style before generating release notes and changelog copy with the same agent.
Define a `warm-direct` support style for customer reply drafts without breaking the guidelines doc.
How it compares
Use this wizard instead of free-form “write me a persona” prompts when styles must conform to a repo spec and land in `output-styles/`.
Common Questions / FAQ
Who is output-style-creator for?
Indie builders curating agent configuration repos who need additional output styles that match internal guidelines rather than improvised character prompts.
When should I use output-style-creator?
Use it in Build → agent-tooling when adding a style; in Launch → distribution when aligning outward-facing agent tone; in Grow → support when defining calmer or more direct support replies—always after guidelines exist.
Is output-style-creator safe to install?
It mainly writes local markdown under `output-styles/` after reading your guidelines—review the Security Audits panel on this Prism page and confirm overwrite prompts before letting an agent replace existing styles.
SKILL.md
READMESKILL.md - Output Style Creator
# output-style-creator > Wizard that creates new output-styles following `docs/output-style-guidelines.md`. > Asks the user 5 focused questions, then writes a compliant file under `output-styles/`. **Triggers**: /output-style-create, create output style, new output style, generate output style, add output style --- ## Process ### Step 1 — Verify guidelines Read `docs/output-style-guidelines.md`. If missing → stop and tell the user to create it first. This skill never operates without the spec. ### Step 2 — Ask the name One question: > What's the style name? (kebab-case, describes the experience — e.g. `direct`, > `concise`, `warm-direct`. Do NOT use a character name.) STOP and wait. Validate: - kebab-case only. - No existing file at `output-styles/<name>.md`. If it exists, ask whether to overwrite or pick a new name. - Reject names that describe characters or roles (`gentleman`, `pirate`, `sergeant`, any human name). Suggest a tone-based alternative. ### Step 3 — Ask the 5 wizard questions Ask one question at a time. STOP after each and wait for the answer. Re-reading the prior answer before each question — never assume defaults silently. **Q1 — Language behavior** ``` How should the style handle language? 1. Adaptive: match the user's input language (recommended). 2. Spanish only. 3. English only. ``` **Q2 — Register** ``` Register in Spanish: 1. Tuteo (default, recommended for technical work). 2. Voseo (rioplatense; requires justification). 3. Usted (formal; requires justification). ``` If user picks 2 or 3, ask a follow-up: "One-sentence reason this style needs voseo/usted instead of tuteo." Save the answer; it goes inline in the file. **Q3 — Pacing & density** ``` Pacing and density: 1. Concise: short sentences predominate, almost no paragraph longer than 3 lines. 2. Balanced: short sentences with one longer one when needed for nuance. 3. Expansive: full paragraphs allowed, exploratory. ``` **Q4 — Disagreement posture** ``` When the model disagrees with the user, how should it sound? 1. Direct: state disagreement immediately, evidence, no softening. 2. Direct with warmth (default): state disagreement, acknowledge user's reasoning, evidence. 3. Diplomatic: lead with user's valid points, then disagree, then evidence. ``` **Q5 — Closure** ``` How should responses end? 1. Contextual: short answers no close; debates one question; long answers one-sentence synthesis. (Recommended.) 2. Fixed: same closing pattern every time. (Specify the pattern.) ``` If user picks 2, ask: "What's the fixed closing pattern? One short example." ### Step 4 — Show preview, get confirmation Render the proposed file content based on the answers. Use the skeleton in Step 5. Show it to the user inside a code block. Ask: > Confirm to write `output-styles/<name>.md`? (y / edit / n) `y` → write. `edit` → ask which section to revise, loop back to that question. `n` → abort, leave nothing on disk. ### Step 5 — Write the file Use this exact skeleton. Fill placeholders from the answers. Keep total under 60 lines (hard limit per guidelines Principle 4). ```markdown --- name: <name> description: <one-line experience description — not a character> keep-coding-instructions: true --- # <Name> Output Style > <One-line experience description, same as frontmatter description.> ## Language <Adaptive / Spanish only / English only — and the trigger rule.> ## Register <Tuteo / Voseo / Usted in Spanish. Contractions yes/no in English.> <If voseo or usted: one-line justification.> ## Pacing & density <Concise / Balanced / Expansive. State sentence-length preference and paragraph limit. State that no decorative sections are added.> ## Emphasis <Bold for key ter