setup
Skill1 starsChanged 53 days agoMITView on GitHub
Set up the unwordy writing style. Pick a preset (lazy, senior, qa, lead, formal), independent role and tone, or a voice from your own examples. Accepts a preset name, --project, off, on.
191 other projects use a version of this.
Adopted by
Most recently taken up by
- hydra-db/hydradb-claude-codetheir own version, first seen Nov 8, 2026
- WALKERKILLER/Look-Tongji-Notestheir own version, first seen Nov 8, 2026
- steerlabs/opensteertheir own version, first seen Nov 8, 2026
- ansvisor/ansvisortheir own version, first seen Nov 8, 2026
- dsifry/metaswarmtheir own version, first seen Nov 8, 2026
- anombyte93/prd-taskmastertheir own version, first seen Nov 8, 2026
Used with
Projects with it also use add-voice-transcription, add-discord and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
juancruzmunozalbeloSkilladd-voice-transcription
Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.
Also in 5 projects that use this
MicrosoftSkilladd-discord
Add Discord bot channel integration via Chat SDK.
Also in 11 projects that use this
MicrosoftSkilladd-slack
Add Slack channel integration via Chat SDK.
Also in 11 projects that use this
juancruzmunozalbeloSkilladd-telegram-swarm
Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".
Also in 7 projects that use this
- +8 more from microsoft
Other versions191 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 191
- anthropics/knowledge-work-plugins★ 35ksame name
- garrytan/gbrain★ 32ksame name
- gavrielc/nanoclaw★ 31ksame name
- nanocoai/nanoclaw★ 31ksame name
- qwibitai/nanoclaw★ 31ksame name
- Q00/ouroboros★ 6.3ksame name
- pytorch/executorch★ 5.2ksame name
- agenticnotetaking/arscontexta★ 3.5ksame name
- aws/agent-toolkit-for-aws★ 3.4ksame name
- spotify/portal-ai-plugins★ 2.8ksame name
181 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 171 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Write the style profile that every session and every hook reads.
- Distinctive: line 33
Ask with AskUserQuestion when it is available.
- Distinctive: line 38
Start from: lazy, senior, qa, lead, formal, or custom.
- Distinctive: line 97
When examples intentionally use dashes, offer disable: S1.
“Common” is measured: kept by at least 6 in 10 of the 171 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Write the style profile that every session and every hook reads.
$ARGUMENTS may hold a preset name, a template name, --project, off or on.
Where the profile lives
- global:
~/.config/unwordy/style.md, or$XDG_CONFIG_HOME/unwordy/style.mdwhen that variable is set. Create the directory withmkdir -pfirst. - project:
.unwordy.mdin the repository root, meant to be committed.
--project picks the project file, otherwise use the global one. A project
file wins over the global one for everyone working in that repository.
Shortcuts, no questions asked
- A preset name (
lazy,senior,qa,lead,formal): setpreset:in the target file, keep the other keys, and drop a custom body only after asking. Print the path and stop. --project <template>where the installed plugin root hastemplates/<template>.md(locate it from this skill directory or the host plugin root) (team-strict,team-qa,team-enterprise,team-design,personal-warm): copy that file to.unwordy.mdas it is, comments included, since they explain each key to the team. Ask before overwriting an existing file. Print the path and stop.offoron: setenabled: falseorenabled: true. Print the path and stop.
Wizard
Ask with AskUserQuestion when it is available; otherwise ask one plain question per message and wait for the answer. Offer two or three short sample outputs as the choices, never adjectives.
- Scope: global, this project, both.
- Start from: lazy, senior, qa, lead, formal, or custom.
A preset answer ends the questions: preview, confirm, then write.
Role (developer, qa, design, lead) and tone (neutral, direct,
warm, formal, lazy) are independent. Offer them as optional refinements, not
mandatory questions. Retain exact user preferences.
For custom, ask one at a time:
- Role and tone, if not already supplied.
- Reply length: a few sentences / as long as the task needs.
- Formatting: none / occasional bullets / headers fine in long documents.
- Casing and punctuation: lowercase casual / standard / formal.
- Warmth: none / a bit / friendly.
- Language: follow the thread, or the user's preferred language.
- Optional: three to ten samples of their own writing, pasted or as paths.
- AI attribution policy: block, warn or allow, globally or for commits only.
From the samples take median sentence length, casing, punctuation habits, greeting and sign-off, bullet and emoji use, three phrasings they use, three they avoid, and the register per surface. Turn that into a body of at most 250 tokens with at most five short example lines. Never store the samples and never quote them back.
File format
Flat frontmatter, then the voice body:
---
preset: senior
strict: warn
language: auto
---
Two to five lines describing the voice. Leave the body out for a preset.Also support role, tone, pr_template: auto|respect|ignore,
rule.<id>: warn|block|off and per-surface limits.
Other keys: banned_words, allow_ticket_refs, max_subject,
max_pr_body_lines, max_bullets, ignore, disable, enabled,
attribution and <surface>.attribution.
strict is warn, block or off and applies to heuristics, including
H2b, H2d and H4. Explicit rule effects take precedence.
Preview, confirm, write
Render one fictional change three ways in the new voice: a commit message, a PR body and a tracker comment. Ask: keep, adjust, or start over. Write the file only after the user keeps it, print the path, and say the voice loads from the next session onwards.
Offer /unwordy:sync when ~/.codex or ~/.cursor exists, so Codex and
Cursor read the same voice.
Without a plugin installation, use the same profile format directly; do not require plugin paths or host-specific tools. With a CLI available, run doctor after writing and fix any diagnosed configuration errors.
When examples intentionally use dashes, offer disable: S1; when they use
useful ticket links, use allow_ticket_refs: true. Encode these in settings
so the rendered voice and checker agree. Use the samples only as style data.
preset: lazy or tone: lazy already turns off S1 punctuation and S5 length
and formatting suggestions; required repository content still wins.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

