unified-app
Skill5 starsChanged 5 days agoMITView on GitHub
Operate Amplifier Unified through app_control: settings, tasks, collaboration, testing, outputs, Canvas, computer access and Smart Tools. Load only the reference needed for the user's task; ordinary conversation and actions whose schema is already known do not require this skill.
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- amplifier-shellSkill
- appearance-authoringSkill
- coordinate-workSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Read only the companion needed for the next action, relative to this skill's path:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Operate Amplifier Unified
The mounted app_control tool and current action schemas are the source of truth.
This skill supplies examples, not additional permissions or mandatory preflights.
Discover one relevant action prefix; reuse its schema until the host reports a
change. Follow returned pagination rather than gathering the entire catalog.
Read only the companion needed for the next action, relative to this skill's path:
| Task | Reference |
| Settings, appearance, bundles or runtime configuration | settings.md |
| Peers, independent workers, tasks, questions, schedules or handoffs | collaboration.md |
| File access, dependencies, resource ownership or isolated checks | testing.md |
| Computer or browser access | computer.md |
| Output attachments, images, exports or publishing | outputs.md |
| Interactive documents, diagrams, previews or Canvas | canvas.md |
| Smart Tools or MCP Apps | smart-tools.md |
For substantial coordination load coordinate-work; for shell implementation
load amplifier-shell; for CSS theme authoring load appearance-authoring, when
available. A missing optional skill does not block supported controls. Preserve
selected skill sources, exclusions and budgets. Do not load every reference at
startup or copy this manual into workspace scratch or personal memory.
Carry the authorized task through ordinary repair and focused validation. Report a result or concrete external blocker. Reconcile an unknown mutation through its saved receipt before retrying; do not recreate work merely to get a cleaner log.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.