rahmanef63/mso/mso-apps

Claude Code and agent skill by rahmanef63/mso

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Map every MSO app to the safest operation that drives it. Prefer bounded capabilities, use document CRUD for editor data, and reserve full shell for uncovered host actions.

Install

npx vskill@latest install rahmanef63/mso/mso-apps

SKILL.md

/mso-apps — app → capability map

Resolve MSO dynamically; never assume /home/<name>/...:

bash
MSO_ROOT="${MSO_DIR:-$(systemctl show -p WorkingDirectory --value mso.service 2>/dev/null || true)}"
[ -n "$MSO_ROOT" ] || MSO_ROOT="$HOME/mso"
MSO_CLI="$MSO_ROOT/bin/mso"
IE="$MSO_ROOT/claude-skills/mso-image-editor/image-editor.sh"

Safety precedence

When the current environment exposes bounded MSO tools, use those first. The CLI is for parity/debugging. exec is the final fallback, not the default transport.

AppMain functionsPreferred control
Fileslist/read/search/new/rename/move/copy/delete/usagebounded fs.*; CLI ls/cat/write/mkdir/mv/cp/rm/usage
Code Editortree/open/edit/save/new filebounded fs.list/read/write
Terminalhost commandsbounded operation if one exists; otherwise scoped exec
System MonitorCPU/mem/disk/processesbounded sys.stats/processes
Browserreal Camoufox Firefoxbounded status/power; human drives VNC UI
Media Viewerinspect mediabounded file read/raw; ffprobe only if needed
Image/Media Studiolayers/text/shapes/adjustmentseditor document CRUD via $IE; render in real editor
Reel Editortimeline/renderbrowser/client; shell only for explicit media preprocessing
Settingsdevices/provider/theme/server modededicated settings/UI; never expose secrets
Assistantchat + tools + skills/api/assistant; trusted skills only
Managed appsdetect/install/status/logs/start/stop/restart/backup/update/restore/uninstall/jobsbounded list/log/power for direct actions; MSO Details/API/CLI for long-running update/install/restore/uninstall workflows
Runtime appsapp-defined actionsuse declared app capability; command runtimes are full shell risk

Important boundaries

  • Browser VNC password/session credentials are never agent output.
  • Raster painting, masks, background removal and final editor rendering are browser-owned; do not invent a second headless renderer.
  • LocalStorage state is browser-owned and is not generic host CRUD.
  • System telemetry is read-only.
  • A task is "working" only when its backing call was actually probed. Use node "$MSO_ROOT/claude-skills/mso-list/audit.js" for the live audit.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/rahmanef63/mso/mso-apps/badge)](https://verified-skill.com/skills/rahmanef63/mso/mso-apps)

Something wrong with this skill or its page? Tell us.