capabilities

Solid

Ask the owner, on a card in chat, to connect a capability the task needs (a connector, an account, Docker, a machine) via the `capabilities` CLI. Use whenever a task hits something this sandbox isn't connected to, check what's connectable, then raise the ask instead of describing manual setup steps.

AI & Automation 35 stars 7 forks Updated 2 days ago MIT

Install

View on GitHub

Quality Score: 82/100

Stars 20%
52
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Missing capabilities The sandbox connects to outside things through capability cards: connectors (GitHub, Notion, Stripe…), browser accounts, databases, Docker, the owner's own devices. When a task needs one that isn't connected, **raise the ask in chat** with the `capabilities` command rather than telling the owner to go set something up by hand. The card does the setup handoff, and your command resumes the moment the connection is live. ## Commands ```sh capabilities list # every connectable card, and whether it's connected capabilities request <card> \ --why "one line on why the task needs it" # ask the owner on a card in their chat — and wait ``` `request` holds until it has a real answer. A `connected` answer means the capability is **live right now**: its skill and tools are available from your next tool call, so continue the task with it in this same turn. The wait can span the owner's whole setup (finding a token, a sign-in): hold the command open rather than timing it out. ## How consent works: enforced, not promised `request` connects nothing. It raises a card in the owner's chat: titled with the catalog's own words, your `--why` as the one line that is yours: and everything that happens next is the owner's click and the owner's setup flow. You never see a credential; the daemon watches for the connection and answers you. What that leaves you: 1. **Ask when the task genuinely needs it, at the moment it needs it.** Check `capabi...

Details

Author
intentic
Repository
intentic/intentic
Created
1 months ago
Last Updated
2 days ago
Language
TypeScript
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

surveying-capabilities

Survey what the local machine can actually do and bind each abstract capability a task needs to a concrete provider — an installed skill, an MCP tool, a CLI, or a subagent — before any plan is written. Use before planning multi-step work, when you need to know what tooling exists (有什么工具 / 本机能力 / 装了哪些技能 / 能不能做), or when a step fails because something is missing. Introspects your own context first at zero cost, then probes only what the task requires. Produces .superclarity/environment.md and .superclarity/<task>/capabilities.md, including an explicit list of capability gaps. Do NOT use for trivial single-step tasks, and do NOT use to enumerate the whole machine when the provider is already confirmed.

0 Updated 3 weeks ago
haxudev
AI & Automation Listed

ciao-capabilities

Authoritative catalog of what Ciaobot can do, for capability questions and feature tours. Use whenever the user asks what Ciaobot is, what it can do, what features are available, whether it can do something specific, or how one of its features works (memory, vault, vault review, archiving, adversarial review, schedules, interval automations, routines, workspaces, projects, forks, subagents, skills, MCP servers, slash commands, voice, models, providers, opencode, plan mode, permission modes, notifications, desktop app, updates, menu bar, files, document conversion, chat comments, pinned files, document previews, CSV tables and cell comments, HTML artifacts, artifact comments, backlinks, memory map, vault graph, note graph) — and when onboarding or giving a tour or walkthrough to a new user. Trigger on phrasings like "what can you do", "what can ciaobot do", "help me get started", "give me a tour", "can you remind me / remember / schedule", "can you review vault notes", "can you run an adversarial review", "can

9 Updated 5 days ago
raffaelefarinaro
AI & Automation Listed

capabilities

The system's self-model — a capability registry (scans every SKILL.md into a layered tree SENSE→DECIDE→ACT→REMEMBER→GOVERN→DEPLOY) plus a "curator" that picks the right capabilities for a goal locally. Use to see the whole toolkit as a system/arborescence, to let an agent discover what botte-secrète can do, or as the data the Conductor reads to compose a plan.

1 Updated yesterday
zedarvates