code-and-architecture-improvement
Skill2.4k starsChanged todayApache-2.0View on GitHub
Make one small refactor that preserves behaviour, only when the user explicitly asks to run this skill. Discussing, reviewing or editing the skill does not run its workflow.
Trending
More talk lately.about the whole repository
Who's talking about muxy-app/muxy
- A Hacker News story“Muxy is a lightweight terminal for Mac with a mobile app for remote control”Hacker News · May 20, 2026 · 3 points
- A Hacker News story“Muxy – A macOS terminal built with SwiftUI and libghostty”Hacker News · Apr 22, 2026 · 3 points
- @tom-doerr.bsky.social“https://github.com/muxy-app/muxy”Bluesky · Apr 20, 2026 · 1 likes
- A Hacker News story“Ghostty, but with Vertical tabs, lightweight and native”Hacker News · Apr 3, 2026 · 1 points
- sudosubin/agents.nix“agent-skills.github.muxy-app.muxy: 2.3.0 → 2.4.0”GitHub · Nov 7, 2026
The biggest 5 of 19 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 19
Talked about on GitHub, Hacker News and Bluesky (19 times).
On GitHub · 15
- Nov 7, 2026agent-skills.github.muxy-app.muxy: 2.3.0 → 2.4.0 — sudosubin/agents.nix0 reactions
- Oct 31, 2026agent-skills.github.muxy-app.muxy: 2.2.0 → 2.3.0 — sudosubin/agents.nix0 reactions
- Oct 29, 2026Add Muxy — AppImage/appimage.github.io0 reactions · 1 comment
- Oct 17, 2026agent-skills.github.muxy-app.muxy: 2.1.0 → 2.2.0 — sudosubin/agents.nix0 reactions
- Oct 14, 2026wr-agent: page scrollback to reattaching clients instead of repainting it whole — joelmoss/workroom0 reactions · 3 comments
10 more on GitHub
- Oct 14, 2026agent-skills.github.muxy-app.muxy: 0-unstable-2026-08-28 → 2.1.0 — sudosubin/agents.nix0 reactions
- Oct 3, 2026agent-skills.github.muxy-app.muxy: 1.6.1 → 0-unstable-2026-08-28 — sudosubin/agents.nix0 reactions
- Sep 30, 2026agent-skills.github.muxy-app.muxy: init at 1.6.1 — sudosubin/agents.nix0 reactions
- Jul 29, 2026Feature Request: Native Terminal AI Agent Support (ACP Integration & Third-Party CLI Orchestration) — github/app0 reactions · 3 comments
- Jul 10, 2026github 0.1.1 — muxy-app/extensions0 reactions · 6 comments
- May 26, 2026Fix Pi notification pill showing wrong provider name — maxschulmeister/muxy0 reactions
- May 21, 2026https://github.com/muxy-app/muxy — weihubeats/Asuna0 reactions · 1 comment
- May 14, 2026Custom project picker for adding/opening projects — sadiksaifi/muxy0 reactions
- Apr 11, 2026佈局持久化(Daemon Layout API + Restore Reconciliation) — zac15987/zplex0 reactions · 3 comments
- Apr 6, 2026Add Muxy to Terminal section — iCHAIT/awesome-macOS0 reactions · 1 comment
On Hacker News · 3
- May 20, 2026Muxy is a lightweight terminal for Mac with a mobile app for remote control3 points
- Apr 22, 2026Muxy – A macOS terminal built with SwiftUI and libghostty3 points · 1 comment
- Apr 3, 2026Ghostty, but with Vertical tabs, lightweight and native1 point · 1 comment
On Bluesky · 1
- Apr 20, 2026https://github.com/muxy-app/muxy — @tom-doerr.bsky.social1 likes and repost
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- e2e-testSkill
- implementSkill
- issues-triageSkill
- release-highlightsSkill
- report-taskSkill
- reviewSkill
- visual-testingSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 7 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
No bug fixes, features or behaviour changes.
- Distinctive: line 26
Stop if the working tree has uncommitted changes.
- Very specific: line 28
Read docs/tech/architecture.md, then find at least 3 candidate problems that fit the scope.
- Distinctive: line 35
If none is worthwhile, stop without changes.
- Very specific: line 36
Create a refactor/ branch and record the starting commit.
- Distinctive: line 37
Add any missing tests for the behaviour the refactor touches and confirm they pass on the unchanged code.
- Very specific: line 39
Run this platform's scripts/check-*.py in full and fix what it finds.
- Distinctive: line 45
Commit, push and open a pull request.
- Distinctive: line 47
Wait for CI and any review-bot comments.
- Distinctive: line 52
If checks cannot pass or the change outgrows the scope, close the PR if one exists, delete the branch, return to main and report why.
≈ “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
Address one concrete maintenance problem with one refactor, as small as a proper fix allows. Keep new or rewritten logic under about 300 lines. Tests, code that only moves and call sites updated to follow it do not count. Preserve observable behaviour, errors, public interfaces, and persisted/protocol formats. No bug fixes, features or behaviour changes.
Make a proper structural fix, not a patch. No shims, pass-through wrappers, flags, special cases or lint suppressions. Tests may move with the code, but never weaken, skip or delete them to get checks passing. For a flaky test, one that also fails intermittently on the starting commit, rerun it and name it in the PR.
This skill runs unattended and on its own. Run no other skills. Never ask the user or wait for approval. Where you would ask, go ahead if the question is about the refactor. Otherwise choose the option that touches nothing outside this run.
Steps
- Stop if the working tree has uncommitted changes. Otherwise switch to main and run git pull.
- Read docs/tech/architecture.md, then find at least 3 candidate problems that
fit the scope. Prefer structure over polish: misplaced responsibilities,
leaky boundaries, duplicated logic. Weigh each by maintenance payoff, risk
to behaviour and existing test coverage. Skip rename-only or formatting-only
churn, areas touched by open PRs, refactors a closed
refactor/PR already tried, and code whose behaviour this machine's checks cannot prove, such as rendering and input handling. Pick the strongest and explain why it helps. If none is worthwhile, stop without changes. - Create a
refactor/branch and record the starting commit. - Add any missing tests for the behaviour the refactor touches and confirm they pass on the unchanged code. Then make the refactor.
- Run this platform's
scripts/check-*.pyin full and fix what it finds. - Review once. Have a sub-agent read every changed line since the starting commit against AGENTS.md, unchanged behaviour and the scope limits, and report only problems the diff introduces, each with file:line and a concrete failure. Verify each finding, fix the real ones and rerun the checks. Do not review again.
- Commit, push and open a pull request. Keep the description short: what the refactor improves and which checks passed.
- Wait for CI and any review-bot comments. Apply the comments that are right and keep behaviour unchanged, then push. Squash-merge only after every CI job passes on the final commit and the change still fits the scope limits. Then delete the remote branch and return to main.
If checks cannot pass or the change outgrows the scope, close the PR if one exists, delete the branch, return to main and report why. Do not fix bugs found along the way. List them in the PR or the report.
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.

