Release
ngrok/ngrok-operator
Automates the ngrok-operator release process: gathers PR data, classifies changes by component (container, Helm chart, CRDs chart), generates changelogs, updates version files, and prepares the…
A skill your agent uses when wanting to systematically improve the Go backend - scans for security vulnerabilities, stability risks, performance issues, and code simplification opportunities, then…
Install Improve Backend
$ npx skills add luxury-yacht/app --skill improve-backend -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install luxury-yacht/app improve-backend --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/luxury-yacht/app.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/improve-backend .claude/skills/improve-backend && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "improve-backend" agent skill from https://github.com/luxury-yacht/app/tree/main/.agents/skills/improve-backend into .claude/skills/improve-backend/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "improve-backend", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/luxury-yacht/app/tree/main/.agents/skills/improve-backendType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add luxury-yacht/app --skill improve-backend -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install luxury-yacht/app improve-backend --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/luxury-yacht/app.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/improve-backend .agents/skills/improve-backend && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "improve-backend" agent skill from https://github.com/luxury-yacht/app/tree/main/.agents/skills/improve-backend into .agents/skills/improve-backend/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "improve-backend", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add luxury-yacht/app --skill improve-backend -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install luxury-yacht/app improve-backend --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/luxury-yacht/app.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/improve-backend .cursor/skills/improve-backend && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "improve-backend" agent skill from https://github.com/luxury-yacht/app/tree/main/.agents/skills/improve-backend into .cursor/skills/improve-backend/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "improve-backend", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/luxury-yacht/app.git --path .agents/skills/improve-backend--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add luxury-yacht/app --skill improve-backend -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install luxury-yacht/app improve-backend --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/luxury-yacht/app.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/improve-backend .gemini/skills/improve-backend && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "improve-backend" agent skill from https://github.com/luxury-yacht/app/tree/main/.agents/skills/improve-backend into .gemini/skills/improve-backend/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "improve-backend", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install luxury-yacht/app improve-backendInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add luxury-yacht/app --skill improve-backend -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/luxury-yacht/app.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/improve-backend .github/skills/improve-backend && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "improve-backend" agent skill from https://github.com/luxury-yacht/app/tree/main/.agents/skills/improve-backend into .github/skills/improve-backend/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "improve-backend", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add luxury-yacht/app --skill improve-backend -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install luxury-yacht/app improve-backend --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/luxury-yacht/app.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/improve-backend .opencode/skills/improve-backend && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "improve-backend" agent skill from https://github.com/luxury-yacht/app/tree/main/.agents/skills/improve-backend into .opencode/skills/improve-backend/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "improve-backend", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
improve-backend- GitHub stars
- 444
- Token cost
- ~1.1k tokens
- SKILL.md length
- 526 words
- Files
- 1
- Skills in repo
- 17
- Repo updated
- First seen
- Licence
- GPL-3.0
At a glance
A skill your agent uses when wanting to systematically improve the Go backend - scans for security vulnerabilities, stability risks, performance issues, and code simplification opportunities, then…
- Wanting to systematically improve the Go backend - scans for security vulnerabilities
- SKILL.md covers Scan, Present, Fix and Do not
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Stability risks
What it does
Improve Backend is an agent skill from luxury-yacht/app. Use when wanting to systematically improve the Go backend - scans for security vulnerabilities, stability risks, performance issues, and code simplification opportunities, then presents 5 ranked findings for the user to choose from
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering Code simplification and Container orchestration. It works with Kubernetes. The repository describes itself as: Luxury Yacht - A cross-platform app for managing Kubernetes clusters and resources. The licence is GPL-3.0.
When your agent uses it
- Wanting to systematically improve the Go backend - scans for security vulnerabilities
- Stability risks
- Performance issues
- Code simplification opportunities
Example prompts
- “/improve-backend”
What it can do on your machine
Read from SKILL.md and the folder at commit 7001a03. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Improve Backend loads about 1.1k tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 526 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from luxury-yacht/app at commit 7001a03, republished under its GPL-3.0 licence (© luxury-yacht). 526 words, ~1,149 tokens.
Download SKILL.mdSave it as
.claude/skills/improve-backend/SKILL.md (or your agent's skills folder).- name
- improve-backend
- description
- Use when wanting to systematically improve the Go backend - scans for security vulnerabilities, stability risks, performance issues, and code simplification opportunities, then presents 5 ranked findings for the user to choose from
Improve Backend
Scan the Go backend, present exactly 5 concrete findings ranked security > stability > performance > simplicity, wait for the user to pick one (or ask for a rescan of another area), then fix only that one.
/improve-backend [area] takes an optional focus area (for example refresh,
resources, portforward, objectcatalog); without one, scan broadly.
Scan
With [area], limit discovery to that package tree. Otherwise sample 8-12
files across packages, weighted toward recent git activity (fresh churn often
harbors fresh bugs) or high line counts. Open frontend contracts only when a
candidate crosses into a frontend consumer. Check the tiers in order:
| Tier | Category | Look for |
|---|---|---|
| Security | Input validation | Unvalidated user/API input reaching os/exec, filepath.Join, label selectors, or K8s API calls |
| Security | Secret exposure | Tokens, secrets, or kubeconfig credentials logged, returned in errors, or stored in plain text outside the intended persistence layer |
| Security | RBAC gaps | K8s writes or operations that skip permission/capability checks |
| Security | Concurrency | Shared mutable state (maps, structs) touched by several goroutines without synchronization |
| Security | Error handling | Swallowed errors (_ = f()) or sensitive details in errors sent to the frontend |
| Security | Dependency risk | go.mod versions with known CVEs |
| Stability | Resource leaks | Unclosed HTTP bodies; watchers, informers, or goroutines not stopped on context cancellation |
| Stability | Nil safety | Dereferences of optional K8s pointer fields without nil checks |
| Stability | Error propagation | return err without fmt.Errorf("doing X: %w", err) context |
| Stability | Context discipline | Long operations ignoring cancellation; blocking calls without timeouts |
| Stability | Graceful shutdown | Goroutines, resources, or watchers that outlive app shutdown or ignore stop channels |
| Stability | Multi-cluster | Paths that assume one cluster or ignore clusterId |
| Performance | Redundant K8s calls | Consolidatable calls, or fetching data the object catalog already has |
| Performance | Missing caching | Repeated expensive work whose result is stable within a refresh cycle |
| Performance | Allocation waste | Unsized slices/maps in hot paths, string concatenation in loops, copies of large structs |
| Performance | Blocking bindings | Synchronous work on the Wails binding thread that should be async |
| Performance | N+1 | Per-item API calls where a list call would work |
| Simplicity | Dead code | Exported functions/types with no callers, unreachable branches, commented-out blocks |
| Simplicity | Duplication | Copy-pasted logic across resource handlers or packages |
| Simplicity | Over-abstraction | Single-implementation interfaces, value-free wrappers, needless indirection |
| Simplicity | Consolidation | Near-identical small functions that could be unified |
| Simplicity | Stale patterns | Patterns the rest of the codebase has moved away from |
Show full SKILL.md (144 more words)Show less
For each finding, note cross-boundary effects: the frontend assumes a response shape the fix would change, must stop sending certain data, or could simplify its caching after the fix.
Present
List findings in priority order, then by impact within a tier:
N. **[SECURITY|STABILITY|PERFORMANCE|SIMPLICITY] Category — file:line**
One-line description of the issue.
Impact: What could go wrong / what improves.
[Cross-boundary: frontend effect, if any]Then ask: "Which one should we fix? (pick a number, or say 'rescan' for a different area)"
Fix
- Read the full context around the issue. When a function signature or response shape changes, update every caller.
- A fix that crosses into frontend consumers changes both layers together; read the owning frontend guidance first.
Do not
- Report style-only issues (naming, formatting);
gofmtowns formatting. - Propose comments or documentation as an improvement.
- Flag intentional patterns documented in AGENTS.md or owning docs, or consolidations recorded in the settled findings.
- Present a large-scale refactor as one finding; break it down.
- Change dependencies without strong justification (CVE, bug).
© luxury-yacht, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/improve-backend of luxury-yacht/app.
Open the folder on GitHubat commit 7001a03
Compare with similar skills
Improve Backend next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Improve Backend this skillluxury-yacht/app | 444 | — | ~1.1k | Automated safety check: Pass | GPL-3.0 | |
| Releasengrok/ngrok-operator | 272 | — | ~2.7k | Automated safety check: Pass | MIT | |
| Dotnet Debuggingnovotnyllc/dotnet-artisan | 232 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Software Design Reviewatilladeniz/Kubeli | 387 | — | ~5.3k | Automated safety check: Pass | MIT | |
| Brooks Healthhyhmrright/brooks-lint | 1.5k | 1 repos | ~425 | Automated safety check: Pass | MIT | |
| Brooks Sweephyhmrright/brooks-lint | 1.5k | 1 repos | ~508 | Automated safety check: Pass | MIT |
Similar skills
Dotnet Debugging
novotnyllc/dotnet-artisan
Debugs Windows and Linux/macOS applications (native, .NET/CLR, mixed-mode) with WinDbg MCP (crash dumps, !analyze, !syncblk, !dlk, !runaway, !dumpheap, !gcroot, BSOD), dotnet-dump, lldb with SOS…
Software Design Review
atilladeniz/Kubeli
Analyzes code based on John Ousterhout's "A Philosophy of Software Design".
Brooks Health
hyhmrright/brooks-lint
Combined codebase health dashboard that scores a project across all four quality dimensions — PR quality, architecture, tech debt, and test quality — in a single pass, drawing on twelve classic…
Brooks Sweep
hyhmrright/brooks-lint
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase.
- Official
Unblock Dependabot PR
kubernetes-sigs/cloud-provider-azure
Diagnose and unblock failed Dependabot pull requests in cloud-provider-azure by closing Kubernetes minor-version dependency bumps, classifying CI failures, syncing Go modules, retesting quota-flaked…
More from luxury-yacht/app
All 17 skills in this repoImprove Frontend
luxury-yacht/app
A skill your agent uses when wanting to systematically improve the React/TypeScript frontend - scans for security vulnerabilities, stability risks, performance issues, and code simplification…
Make Impossible States Impossible
luxury-yacht/app
Eliminate representable-but-invalid Luxury Yacht states with discriminated unions, required identity, typed status, validated constructors, or one boundary chokepoint; use for "make impossible…
Add Resource
luxury-yacht/app
Add or extend support for a Kubernetes resource kind across the required catalog, refresh, detail, object-panel, object-map, permission, documentation, and test surfaces
App Review
luxury-yacht/app
Audit broad Luxury Yacht systems or cross-cutting concerns for structural simplification, hardening, optimization, or refactoring; use for app-wide reviews and phased structural plans, not branch…
Browse Tables
luxury-yacht/app
Change cluster or namespace views, Browse/catalog surfaces, shared GridTable behavior, filters, pagination, large datasets, metrics columns, or refresh-backed resource tables
Refresh Subsystem
luxury-yacht/app
Modify Luxury Yacht refresh domains, snapshots, streams, doorbells, polling fallback, diagnostics, retained data, or refresh lifecycle while preserving cross-layer ordering and recovery contracts
Related
Works with
Categories
Questions about Improve Backend
What does Improve Backend do?
A skill your agent uses when wanting to systematically improve the Go backend - scans for security vulnerabilities, stability risks, performance issues, and code simplification opportunities, then…. Improve Backend is an agent skill from luxury-yacht/app.
When should I use Improve Backend?
Improve Backend fits situations like: wanting to systematically improve the Go backend - scans for security vulnerabilities; stability risks; performance issues; code simplification opportunities.
How do I install Improve Backend in Claude Code?
Run `npx skills add luxury-yacht/app --skill improve-backend -a claude-code`. Or copy the skill folder (.agents/skills/improve-backend in luxury-yacht/app) into .claude/skills/improve-backend in your project. Claude Code loads it when a task matches its description.
How do I install Improve Backend in Codex?
Run `npx skills add luxury-yacht/app --skill improve-backend -a codex`. Or copy the skill folder (.agents/skills/improve-backend in luxury-yacht/app) into .agents/skills/improve-backend in your project. Codex loads it when a task matches its description.
Can I use Improve Backend in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add luxury-yacht/app --skill improve-backend -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/improve-backend, .gemini/skills/improve-backend, .github/skills/improve-backend and .opencode/skills/improve-backend in your project.
What does Improve Backend need to run?
SKILL.md names no scripts, command-line tools or credentials: Improve Backend is instructions for the agent only.
Does Improve Backend access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Improve Backend safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Improve Backend use?
Improve Backend is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Improve Backend use?
About 1.1k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Improve Backend?
Skills that share tags, products or a category with Improve Backend: Release (ngrok/ngrok-operator, 272 stars), Dotnet Debugging (novotnyllc/dotnet-artisan, 232 stars), Software Design Review (atilladeniz/Kubeli, 387 stars) and Brooks Health (hyhmrright/brooks-lint, 1.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Improve Backend?
luxury-yacht (a GitHub organization) maintains it in luxury-yacht/app, which has 444 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 10, 2026.
Source: luxury-yacht/app on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.