Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →sonichi/screen-companion
Sutando watches your screen and helps in real time, with the interaction pattern pre-configured per use case. Reads papers with you, pair-debugs, reviews PRs — without you having to narrate intent every session.
Passed 22 of 22 test cases with the skill, and 5 of 22 without it.
and 21 more in the full report
17 fixed5 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 17 test cases the skill fixed. Same model, same prompt, with and without the skill.
I just captured a quick screenshot of an error banner on my monitor and want to ask a single immediate question about it without launching a voice companion session or config. What tool should be invoked?
| Checked | Without skill | With skill |
|---|---|---|
| Recommends using the inline look_at_screen tool for single-frame inquiries | Missed | Passed |
The instructions your model reads when the skill loads.
Sutando is already capable of watching your screen + voice-chatting in real time (vision push-mode from PR #735 + bodhi VoiceSession). The gap this skill closes: Sutando doesn't know what you're trying to do. Every session you have to re-narrate intent ("I'm reading a paper, ask about figures"; "I'm debugging, suggest hypotheses").
This skill ships pre-baked interaction-pattern configs — each one encodes a purpose, the right system-prompt overlay, the right tool subset, and the right vision cadence. Owner activates a config by name; the skill handles the rest.
configs/.NOT for: silent screen-watching (use the voice agent directly), one-shot questions about a screenshot (use the look_at_screen inline tool).
configs/<name>.yaml # the interaction pattern, declarative
↓
scripts/activate.ts # entry: --config <name> [--goal "..."]
↓ loads config, builds:
↓
voice-agent's VoiceSession # gets a system-prompt overlay + tool subset
↓ # + vision_mode + cadence_ms config
Push-mode vision frames flow # at the configured cadence
↓
Owner asks questions in voice # answers grounded in what's on screen
The skill itself is small — most of the value lives in the configs. New use case = drop a YAML into configs/. No code change required.
| Config | Activation | Vision mode | Shape |
|---|---|---|---|
guided-setup | --config guided-setup --goal "..." or "guide me through this" | push, 700ms | proactive + goal-directed (Sutando narrates next steps for a configuration task) |
v0 demo angle: "Sutando helps you set up something you've never done before" (e.g., a Discord dev portal bot config). User shares screen, names the goal at activation, Sutando narrates the next concrete step in real time. More visceral demo than paper-reading; matches a near-universal user pain (everybody fights some dev portal once a quarter).
test cases passed, vs 5 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.