owner-copy
Skill4 starsChanged 11 days agoApache-2.0View on GitHub
Fleet human-facing prose — two spaces between sentences (a real U+00A0 plus a space on every surface, except the Claude Code Code tab and the MiniMax Code chat pane, which take the entity plus a space), light theme default, Title Case headings, no agent names in App Store/TestFlight notes, Central Time labels. Use when writing UI strings, ASC listing fields, PR/commit/Slack/Notes prose, release notes, or any paragraph a human will read. Also when changing theme defaults or taking screenshots.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- jaywedgeworth22/BotFleetword for word, first seen Nov 3, 2026
Other versions1 project uses a version of this.
Word for word · 1
- jaywedgeworth22/BotFleet★ 4100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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.
In this repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/merge-when-ready.mdcCursor rule
- apple-notesSkill
- board-opsSkill
- closeoutSkill
- codex-triageSkill
- deploy-verifySkill
- dns-and-registrarsSkill
- drive-grok-tuiSkill
- fleet-coordinationSkill
- fleet-infraSkill
- land-laneSkill
- mac-cleanupSkill
- pickup-seatSkill
- secret-handoffSkill
- sentence-gapSkill
- session-startSkill
- unstick-prSkill
- windows-releaseSkill
- phone-harnessSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 35
No All-Assets dropdown on CT web/iOS.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Owner-facing copy (MONET)
Shared
~/.claude/skills. Monet, Claude/Fable, and (when active) Renoir all load this directory. Do not treat the word Monet in examples as proof of your seat. PinAGENT_SEAT/AGENT_TAGfrom the logged-in account before Zulip orsimple-board --by:
- Monet →
MONET, NotesMonet,monet/,~/apps/<app>-monet- Claude / Fable →
CLAUDE, NotesClaude,claude/,~/apps/<app>-claude- Renoir →
RENOIR, NotesRenoir,renoir/,~/apps/<app>-renoirCursor, Grok, Grok Bot, Codex, AG, DeepSeek, Kimi, and Fx have their own skill dirs and must not take identity from here.
Canonical detail: /Users/jay/apps/FLEET-UI-COPY.md. Policy: /Users/jay/apps/FLEET-PROTOCOL.md § Two spaces, timestamps, TestFlight metadata.
Two spaces between sentences
Full protocol (always follow, do not weaken): skill sentence-gap
(~/Desktop/fleet-skills/sentence-gap/SKILL.md — Monet portable paste).
Binding for every paragraph a human reads — in-app UI, ASC description / promotional text / What’s New / review notes, push, email, help, Apple Notes, Linear issues and comments, chat replies, PR titles/bodies, commit messages, Zulip.
- Every surface (owner ruling 2026-10-23): chat replies in any other pane, Zulip, GitHub PR and issue text and review comments, Linear, commit messages, repo docs, skills, agent instructions and UI copy all take a real U+00A0 plus a normal space after each sentence. Generate it in the shell rather than typing it.
- The one exception: the Claude Code Code tab and the MiniMax Code chat pane. Those panes normalize a raw U+00A0 away, so a chat reply there uses the
entity plus a normal space, outside code spans. The entity is never the form anywhere else. - Never the
entity anywhere else. It shows up as literal text in squash-merge commits, plain-text email and many APIs. - Never two plain ASCII spaces. Rendered surfaces collapse them to one.
- Code, identifiers and machine-readable config never get a U+00A0. If a surface strips it, leave the text as it is and report the surface; do not switch to the entity.
Headings / titles / buttons: Title Case.
- Values / secondary status: sentence case or lowercase (
not reported,ask-first). - Congress and Congressional take a capital C. Brand Congress.Trade, DealDex, Socratic.Trade.
- Compact money suffixes lowercase (
$99.8k). Do not say “Live” on account rows; paper isAlpaca (paper). - CT latency: never print
+/−on lead/lag. Say earlier (green) or later (red). - No All-Assets dropdown on CT web/iOS.
Product truth in listing copy
- Congress.Trade corpus is House, Senate, and Executive Branch (OGE 278-T) — never "Congress-only."
- Premium trial length must match the live ASC intro offer (2 weeks as of 2026-08-14), never a leftover 1-month.
- No internal agent names in TestFlight / App Store / public release notes.
Timestamps (owner-facing agent writing)
When you tell the owner a time, say it in Central Time. Write Sat, Aug 22, 2026 at 7:00 PM CT. Always label CT / CDT / CST. Never UTC-only in chat, Notes, Slack, boards, or PRs. UTC may follow in parentheses after the Central stamp. 00:00 UTC is 7:00 PM CT the previous calendar day in CDT (6:00 PM CT in CST). Convert with TZ=America/Chicago date or Python ZoneInfo("America/Chicago"). Unlabeled local time is the failure mode.
Product UI times are the viewer's timezone except market-day accounting (Chicago) and session bells (9:30 AM ET).
Canon
/Users/jay/apps/FLEET-UI-COPY.md/Users/jay/apps/FLEET-PROTOCOL.md§ Two spaces; Theme via FLEET-UI-COPY; TestFlight template- Skills:
apple-notes,sentence-gap,closeout
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.

