steipete/agent-scripts
Agent skills in the GitHub repository steipete/agent-scripts, each with its code score out of 100.
Scripts for agents, shared between my repositories.
- Repository score
- 64 / 100 C
- Skills
- 54
- Verified
- 0
- Average skill score
- 56
- GitHub stars
- 7,483
- License
- MIT
Open steipete/agent-scripts on GitHub
54 skills in this repository
-
vm-lab
Parallels macOS VM lab: GUI automation, Peekaboo, TCC, Ghostty.
72B -
codex-huge-context
Codex 1M context: direct OpenAI Responses API inference, safe Astra/Sol/Terra/Luna input headroom, Keychain delivery, and Mac fleet rollout.
71B -
maintainer-orchestrator
Coordinate multiple maintainer issues, PRs, or repositories with bounded workers, serialized public actions, and clear owner decisions. Do not use for one issue or PR.
70B -
github-deep-review
GitHub deep review: bugs, PRs, best fix, stale-or-real, read code first.
69C -
fleet-maintenance
Mac fleet inventory and upkeep with full/worker profiles: collect installed apps and packages, compare desired versus observed state, audit local-account escrow references, update…
68C -
project-structure
Generate a single-file compressed symbol map of a TypeScript or Swift repository — files, exported symbols, typed signatures, plugin boundaries — sized to fit an LLM context windo…
68C -
github-project-triage
GitHub issue/PR triage: queues, CI, blockers, risk, proof, next actions.
67C -
speaking
Speaking ops: invites, keynotes, panels, Gmail/calendar, conferences.
66C -
swiftui-liquid-glass
SwiftUI Liquid Glass: implement, adopt, refactor, review correctness/perf/design.
66C -
xcode-sync
Xcode fleet sync: signed archives, compatibility, install, selection, first launch.
66C -
nano-banana-pro
Nano Banana/Gemini image gen/edit: text/image input, 512-4K workflows.
65C -
browser-use
Control the user's existing signed-in Chrome: callable Codex Chrome plugin first, then OpenClaw extension-backed mcporter, with direct DevTools attachment only as a last fallback.
64C -
remote-mac
Remote Macs: MacBooks, Mac Studios, hosted claw Macs, Tailscale, SSH, and OpenClaw.
63C -
hopper-debugger
Hopper debugging: macOS/iOS binaries, ObjC/Swift symbols, dyld, LLDB.
62C -
native-app-performance
Native app performance: xctrace, Time Profiler, traces, hotspots.
62C -
codex-first
Claude Code / OpenClaw-on-Claude work routing: delegate hands-on work to Codex under the native-Claude model gate. Keep specification, judgment, and verification in Claude; prefer…
61C -
release-mac-app
macOS app release: Sparkle, notarization, GitHub Release, Homebrew, closeout.
60C -
openclaw-relay
OpenClaw session relay: prompts/posts via local/remote acpx over SSH.
59C -
sonos
Sonos control: search, queue, playlists, rooms/groups, volume, YouTube.
59C -
obsidian
Obsidian vault: search/read/write notes, backlinks, Bases, Canvas.
58C -
skill-cleaner
Codex/OpenClaw skill audit: live budget, usage, duplicates, compact descriptions.
58C -
swiftui-performance-audit
SwiftUI performance: render, scroll, CPU/memory, updates, layout, Instruments.
58C -
instruments-profiling
Instruments/xctrace profiling: macOS/iOS traces, binaries, args, exports.
57C -
npm
npm registry ops: login, whoami, names, publish; 1Password tmux.
57C -
oracle
Oracle second-model review: bundle prompts/files, debug, refactor, design.
57C -
twilio-sms
Twilio SMS CLI: buy/list/keep numbers, send/check messages, credential routing.
57C -
things-todo
Things 3 via things CLI: add, list, search, update, delete, verify.
55C -
beeper
Beeper cache: contact hints, room lookup, WhatsApp/iMessage traces, FTS.
54D -
mac-maintenance
Mac upkeep: brew update/upgrade, pull clean repos, empty Trash.
54D -
notcrawl
Notion archive: desktop/API sync, Markdown export, page search, read-only SQL.
54D -
reminders
Apple Reminders via rem CLI: add, list, search, update, complete, delete.
54D -
swiftui-view-refactor
SwiftUI view refactor/review: layout, DI, Observation, view models.
54D -
domain-dns-ops
DNS/domain ops: registrars, zones, redirects, DNS/HTTP verify, manager truth.
53D -
github-author-context
GitHub contributor context: identity, activity, trust, company/team signal.
53D -
codex-debugging
Codex debugging: codex-rs core/tui/exec/cli/app-server/config.
52D -
swift-concurrency-expert
Swift concurrency review/fix: compiler errors, Sendable, isolation, remediation.
52D -
agent-transcript
Requested GitHub PR/issue agent transcripts: redact, trim, preview, and insert safely.
50D -
markdown-converter
Markdown conversion: PDF, Office, HTML, data, OCR, audio, ZIP, YouTube.
50D -
openai-image-gen
OpenAI Images API: batches, prompt sampler, gallery.
50D -
video-transcript-downloader
yt-dlp downloads: video, audio, subtitles, transcripts, clips, playlists.
50D -
xurl
xurl X API CLI: install, auth, app choice, shortcuts, raw endpoints.
50D -
clickclack
ClickClack ops: chat app, Cloudflare Workers deploy, DNS/docs/app, container rollout.
49D -
github-cache-hygiene
GitHub quota/cache hygiene: Gitcrawl archives, Octopool-backed gh, freshness, limits.
49D -
create-cli
CLI UX/spec: args, flags, help, output, errors, config, dry-run.
48D -
discord-clawd
Discord-backed OpenClaw agent/session relay; not archive search.
48D -
ssh-doctor
SSH triage: Remote Login, launchd sshd, pre-auth closes, stale sessions.
48D -
wrangler
Wrangler CLI: Workers, KV, tail, deploy, account routing.
48D -
clawsweeper-status
ClawSweeper status: URLs, workflow health, active workers, ops snapshot.
47D -
cloudflare-registrar
Cloudflare Registrar: domain availability, prices, registration via mcporter.
47D -
codexbar
AI service usage/quota via CodexBar CLI: Codex/OpenAI, Claude, Kimi and other provider limits, credits, reset times.
47D -
telecrawl
Telegram archive: chats, messages, contacts, folders, search; import from Telegram Desktop/macOS.
47D -
frontend-design
Frontend UI: pages, apps, components, polished non-generic design.
44D -
release-tweets
Release tweets: draft/copy/post from changelog, tags, npm/appcast, artifacts.
44D -
whatsapp
WhatsApp router: history/search/read/send; wacrawl read, wacli live.
42D
Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.