lev-os/agents - 第 3 页

tui-inspector

Records terminal UIs with VHS and deterministic snapshots. Use when debugging TUI rendering, reproducing visual regressions, or sharing keyboard-driven UI behavior.

原文语言：英语

ui-polish

Iterative UI/UX polishing for Stripe-level visual quality. Use when app already works and looks decent, wanting to elevate to world-class through multiple passes. Not for complete overhauls.

原文语言：英语

ux-audit

Systematic UX evaluation using Nielsen heuristics and accessibility checks. Use when reviewing UI, "is this usable", improving user experience, or pre-launch.

原文语言：英语

video-obs-youtube-music

Remux OBS recordings to MP4, add YouTube music, generate intro/outro videos with WebGL shaders, and song credit overlays. Use when preparing screen recordings for YouTube or X/Twitter upload.

原文语言：英语

admin-page-for-nextjs-sites

Design cohesive Next.js SaaS admin cockpits. Use when building or expanding `/admin` and `/api/admin` with unified IA, permissions, audit, analytics, ops, moderation, billing, and user-management.

原文语言：英语

asupersync-mega-skill

Replace Tokio Rust stacks with Asupersync. Use when migrating tokio/axum/hyper/tonic apps, designing native Cx/region-based services, or debugging Asupersync internals.

原文语言：英语

changelog-md-workmanship

Rebuild CHANGELOG.md files and release histories from git, tags, releases, and issue trackers. Use when writing changelogs, version timelines, or agent-facing project history summaries.

原文语言：英语

codebase-audit

Domain-parameterized codebase auditing (security, UX, performance, API, copy, CLI). Use when auditing code, assessing quality, finding issues, or pre-launch review.

原文语言：英语

codebase-pattern-extraction

Mine patterns that recur across multiple projects and generalize into reusable artifacts. Use when "I've seen this before", DRY across repos, or building shared libraries.

原文语言：英语

db-migrations

Use when running, planning, or discussing database migrations, schema changes, or data transformations against any environment

原文语言：英语

frankensearch-integration-for-rust-projects

Complete guide for integrating frankensearch hybrid search into Rust projects. Covers fresh integration, fixing stalled/buggy integrations, and migrating from ad-hoc search. Use when: frankensearch, hybrid search, two-tier search, TwoTierSearcher,…

原文语言：英语

gdb-for-debugging

Debug running processes with GDB, strace, and /proc inspection. Use when: process hang, spin loop, segfault, crash, backtrace, attach debugger, ptrace, core dump, thread starvation, accept loop, deadlock, busy wait, or diagnose why a process is stuck.

原文语言：英语

library-updater

Update dependencies to latest stable versions. Use when upgrading libraries, updating Cargo.toml, pyproject.toml, package.json, go.mod, Gemfile, or modernizing dependencies.

原文语言：英语

multi-pass-bug-hunting

Systematic audit-fix-rescan cycle for comprehensive bug elimination. Use when code review, deep audit, "find all bugs", or pre-release hardening.

原文语言：英语

readme-writing

Craft professional README.md files for GitHub open source projects. Generates hero sections, installation instructions, feature tables, and architecture diagrams. Use when creating or revising a README, documenting a CLI tool, library, or open source project,…

原文语言：英语

rust-cli-with-sqlite

Design SQLite + JSONL sync for Rust CLIs. Use when choosing a source of truth, designing sync strategy, WAL/PRAGMA tuning, atomic JSONL writes, recovery, or durability.

原文语言：英语

saas-cli-auth-flow

SaaS CLI-to-web auth: PKCE OAuth, RFC 8628 device code, token lifecycle, secure storage. Use when building CLI login, device-code verify, token refresh, or headless SSH auth.

原文语言：英语

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

原文语言：英语

ubs

[WHAT] Static-analysis quality-gate wrapper around the external `ubs` CLI (Ultimate Bug Scanner). [HOW] Runs `ubs` on staged, diffed, or explicitly changed files with structured output, then uses the findings as a pre-commit or pre-review bug gate. [WHEN] Use…

原文语言：英语

dsr

Doodlestein Self-Releaser - fallback release infrastructure for when GitHub Actions is throttled. Local builds, cross-platform releases, supply chain security. Use when: GH Actions slow, local release, build hosts, dsr command.

原文语言：英语

gh-actions

Configure GitHub Actions CI/CD for Go, Rust, TypeScript, Bash projects. Use when creating workflows, release automation, signing, checksums, cross-platform builds, or .github/workflows files.

原文语言：英语

gh-triage-ru

GitHub issue/PR triage via ru and gh. Use when processing issues, closing PRs (no-contributions policy), or bulk triage. Independent verification required.

原文语言：英语

installer-workmanship

Write production-grade curl|bash installers. Use when creating install.sh, curl-pipe-bash installer, or one-liner install for CLI tools.

原文语言：英语

ru-multi-repo-workflow

Orchestrate multi-repo maintenance with ru: smart commits, careful sync, issue/PR review. Use when managing repos, syncing projects, reviewing GitHub issues, or automating maintenance en masse.

原文语言：英语

rust-crates-publishing

Publish Rust crates to crates.io. Use when cargo publish, crates.io tokens, GitHub Actions release workflows, or version/tag alignment are needed.

原文语言：英语

vercel

Operate Next.js 16 SaaS on Vercel with Cloudflare DNS + Supabase. Use when deploying to Vercel, reducing build costs, managing secrets, or splitting traffic between Vercel and Cloudflare.

原文语言：英语

flywheel

Internal placeholder. This skill is intentionally withheld from distribution.

原文语言：英语

de-slopify

Remove telltale signs of AI-generated "slop" writing from documentation. Use when polishing README files, API docs, or any public-facing text to sound authentically human.

原文语言：英语

ga4

Configure GA4 + GTM for Next.js SaaS: funnel tracking, scroll depth, CTA clicks, conversions, feature usage. Use when setting up analytics, tracking conversions, or implementing A/B tests.

原文语言：英语

saas-customer-analytics

SaaS analytics: MRR, churn, behavioral scoring, Monte Carlo, interventions, Stripe/PayPal. Use when building subscription analytics, revenue projections, or admin dashboards.

原文语言：英语

planning-workflow

Comprehensive markdown planning methodology for software projects. Use when starting a new project, creating implementation plans, or refining architecture before coding.

原文语言：英语

defendr

[WHAT] 4-layer security scanner for untrusted code: static analysis, malware/CVE scanning, Docker sandbox, agentic review. [HOW] Orchestrates rg patterns, ClamAV, pip-audit, osv-scanner, semgrep, Docker strace, and LLM code review. [WHEN] Before running…

原文语言：英语

e2e-testing-for-webapps

E2E testing for Next.js + Playwright + Supabase. OAuth bypass via test users, interactive debugging, visual QA. Use when: E2E, Playwright, visual regression, Electron testing.

原文语言：英语

testing-conformance-harnesses

Build conformance test harnesses that verify implementations against specifications. Use when: porting libraries across languages, implementing RFCs/specs, building database engines, validating protocol compliance, cross-platform compatibility, API contract…

原文语言：英语

testing-fuzzing

Design and implement fuzzing harnesses for crash discovery, security auditing, and correctness verification. Coverage-guided, structure-aware, differential, and grammar-based fuzzing. Use when: testing parsers, protocols, serialization, cryptography, state…

原文语言：英语

testing-metamorphic

Design and implement metamorphic testing for systems with the oracle problem. Use when: testing ML models, scientific computing, compilers, search engines, databases, graphics pipelines, or any system where correct output is unknown but input-output…

原文语言：英语

testing-real-service-e2e-no-mocks

Build mock-free integration and E2E tests that hit real databases, real APIs, and real services with structured logging. Use when: replacing mocked tests with real-DB tests, transaction rollback isolation, test data factories, structured JSON-line test…

原文语言：英语

multi-model-triangulation

Cross-validate decisions using multiple AI models (Codex, Gemini, Grok). Use when "get a second opinion", evaluating approaches, or high-stakes decisions.

原文语言：英语

operationalizing-expertise

Operationalize expert methods into corpus, quote bank, triangulated kernel, operator library, and validators. Use when distilling a methodology or mining session history into executable rules.

原文语言：英语

auth-sniffer

Deterministic browser auth extraction for agent workflows. Use when you need to stop a running Brave/Chrome/Edge session, relaunch with CDP, extract cookie/localStorage/sessionStorage auth values, and restore normal browser state.

原文语言：英语