Use Skills (browse, install, edit)
A Skill is a small markdown file that teaches Claude Code how to do a specific thing, such as shipping a package or writing a postmortem. Omniscio ships an in-app Skills browser for installing skills from a curated catalog, editing your own, and keeping them current. Installed skills activate automatically when their triggers match.
On this page
What it is
A Skill is a small markdown file that teaches Claude Code how to do a specific thing — "ship a package", "write a postmortem", "schedule a cron job". Each skill has YAML frontmatter (name, description) followed by prose instructions. Omniscio ships with an in-app Skills browser that lets you install skills from a curated catalog, edit your own, and keep them up to date — all without hunting around the filesystem or hand-editing files in ~/.claude/skills/. Installed skills activate automatically whenever their trigger phrases match what you're asking (e.g. "schedule a cron" loads the omniscio-control skill bundle's cron.md reference).
Where to find it
Open the Skills view by clicking Skills (puzzle-piece icon) in the left sidebar, where it appears as a virtual project alongside Inbox, Gmail and SMS. If the entry is missing, open Marketplace → Inbuilt and confirm Skills is installed; it ships on by default. The view is a sub-sidebar with Installed and Catalog tabs plus a detail pane showing the selected skill's frontmatter, body and token cost, and it carries the Install, Edit, Update and delete actions.
How it behaves
How to use it
- Open the Skills view. Click Skills (puzzle-piece icon) in the left sidebar — it appears as a virtual project alongside Inbox, Gmail, SMS, etc. If you don't see it, open Marketplace → Inbuilt and confirm Skills is installed (it ships on by default).
- Browse Installed vs Catalog. The sub-sidebar has two tabs: Installed (skills already on disk — user-authored plus any bundled by plugins; a plugin contributes exactly the skills its own manifest publishes, whatever folder layout it uses internally, so a plugin that ships extra work-in-progress folders it doesn't publish won't show them — Claude Code wouldn't load those either) and Catalog (the curated catalog, pulled from the public
amc-skillsGitHub repo — you don't need to visit it; everything in it is browsable and searchable right here). Each tab has a search box that filters by name + description; a row shows the description on one line, and hovering it shows the whole description. Arrow keys navigate the list, Enter confirms.- A skill folder that is a shortcut counts as installed. Some installers (the
skillsCLI is the common one —npx skills add <repo>) keep a skill's files somewhere else, typically~/.agents/skills/<name>, and leave a symlink or Windows junction at~/.claude/skills/<name>. Claude Code loads those, so Omniscio lists them too: the Installed tab, the composer's/menu andGET /skillsall follow the shortcut to the real folder. A shortcut whose target is missing, is a file, or holds noSKILL.mdis simply not listed. Editing one is still refused (a CLI owns those files), and removing it moves only the shortcut to the trash — never the real files behind it. - Each plugin skill appears once. A plugin's cache can hold several versions side by side after an update; the Installed tab shows only the version Claude Code currently has installed (falling back to the newest cached one if it can't tell), and opening or removing a plugin skill acts on that same version.
- A skill folder that is a shortcut counts as installed. Some installers (the
- Install a skill from the catalog. Select a catalog skill to preview it, then click the blue Install button. The first time you install from the catalog, a trusted-source acknowledgement modal appears explaining that you're pulling content from a remote GitHub repo — click Accept to proceed. That consent is remembered (
skillsTrustedSourceAcknowledged), so you won't see the modal on subsequent installs. - Edit your own skill. Select any non-plugin skill in the Installed tab and click the pencil Edit button. A textarea reveals the raw
SKILL.mdcontent — edit it, then save with Cmd/Ctrl+S or the Save button. If you navigate away with unsaved changes, a "Discard changes?" dialog protects your work. Saving updates the view immediately — the body and the token figures you see afterwards are the file that was just written, so there is nothing to re-open to make the view catch up. A skill whose frontmatter isn't valid YAML still opens so you can repair it: the header shows no name or description, and the editor holds the file exactly as it is on disk. Plugin-bundled skills are read-only — selecting one shows a provenance line in the detail-pane header: which plugin it came from, its version, the author, the marketplace it was distributed through, and clickable links to both the marketplace's central repository and the plugin's own Repository (the source repo it was built from). Both links open in your system browser. The body of a plugin-bundled skill is drawn in the same restricted markdown mode the Marketplace uses for a plugin's README, because the plugin's publisher wrote it: a web link opens in your browser, any other kind of link (a file on this computer, an Omniscio deep link, a relative path) shows as plain words, and pictures load only from the web; your own, project and catalog skills keep the full renderer (untrusted-markdown-render-contract.md). - Update or remove. If a skill you installed has a newer catalog version, an Update button appears — click it to atomically fetch and replace the file on disk (your UUID is preserved so nothing else breaks). To remove, click the red trash icon and confirm — the dialog names what removal does for this skill, because it is not the same for every kind. A skill you installed from the catalog moves to
~/.claude/.amc-skills-trash/and shows an Undo toast that reinstalls it. A skill Omniscio ships moves to the same trash and is recorded as archived, so Omniscio stops putting it back on launch — restore it from the Archived list under the Installed tab. A skill you wrote yourself also moves to the trash, but there is no Undo and nothing in the app brings it back. Plugin skills hard-delete from their cache — reinstall the plugin to get one back. One skill can't be removed: omniscio-control, the skill the seven other Omniscio skills (omniscio-sessions, omniscio-scheduling and the rest) route into. It shows "Needed by 7 other Omniscio skills, so it can't be removed." where the button would be, the Skill Overhead card never offers it, and if an older version archived it, Omniscio puts the whole current skill back on the next launch. The declaration lives in the skill family's manifest (requiredSkillIdsin omniscio-control.ts); the rules are in bundled-skill-feature-gating-contract.md. - Spot under-used skills with usage tracking. Each Installed row shows "Last used 2d ago · 45 uses" (or "Never used") derived from your local JSONL session transcripts. The sort dropdown above the list offers Alphabetic / Least used / Never used / Most used / Recently used — "Never used" is the fastest lens for "what should I uninstall?" The header has a Scan button to force an immediate re-scan (otherwise the scanner runs 5s after launch, drains during idle, and re-checks every 60 min). Right-click any installed row to open its actions menu — today that's Reset usage (confirm-gated, per-skill). (There is no longer a three-dot ⋮ button; right-click is the way in.) The header Clear usage button wipes every skill's history in one shot. While a scan is in progress, a small pulsing-dot banner shows "Scanning N files…"; if the
AMC_DISABLE_TOOL_INVOCATION_SCANNER=1kill switch is set, the banner instead warns that usage tracking is disabled. - See how many tokens your skills cost. Skills aren't free. Every installed skill's YAML frontmatter is loaded into Claude's skill-discovery index at the start of every conversation — the "always-on" cost you pay whether or not the skill is ever invoked. The body and any linked sibling files load only when Claude actually uses the skill. Two places surface this, and both label every figure as approximate (a chars ÷ 4 estimate, shown with a leading "~"):
- Globally, a summary line directly under the Installed tab strip reads e.g. "~3k frontmatter · ~30k total". The left number sums the always-on frontmatter across every installed skill; the right number is what you'd pay if every skill fully loaded (frontmatter + body + files). The line is hidden when you have no skills installed (or none carry a measurable cost). Use the frontmatter number to watch your baseline overhead — if it climbs into the tens of thousands, every conversation pays that tax up front, and "Never used" skills (step 6) are the first to consider uninstalling.
- Per skill, selecting any skill shows a breakdown in the detail-pane header, e.g. "~12k tokens total · Frontmatter ~1k · Body ~10k · Files ~1k", with a tooltip explaining when each part loads.
Skills the Learning Loop writes
When the Learning Loop is on, Omniscio can turn a hard task from your finished work into a skill. Those skills follow a few rules of their own:
- A learned project skill is listed here, read-only, with a Learned badge. The Learning Loop keeps the skills it writes for a project in a folder Omniscio owns for that project, outside your repository and your personal skills folder. They appear in the project's skill list, the details popup and the Skills view, but you cannot edit or remove them here. Claude Code sessions in that project load them from their next start.
- History, Undo and Edit open the Learning timeline. On a learned skill, these buttons take you to the Learning timeline (under Agent Tools), narrowed to that skill. History opens its newest entry, Edit opens the edit window, and Undo puts your cursor on that entry's Undo button for you to press. A Showing one skill row with Show all clears the narrowing. The buttons are hidden on the phone app. Editing a learned skill there makes it yours.
- A learned skill for all projects shows up here once you approve it. It lands in your personal skills folder, so the Installed tab lists it like any skill you wrote, with the Learned badge while the Learning Loop is its author.
- Your own skills are never changed without asking. A change the Learning Loop proposes to a skill in your personal folder or your project's own skills folder always waits for your approval, and a skill you edit here counts as yours from then on.
- Shipped, catalog and plugin skills are never touched. The Learning Loop only reads them.
- Restoring a learned change happens on the Learning timeline. The Archived list here is only for skills Omniscio ships that the skill overhead review archived.
Related
mcp-servers.md — the sibling MCP Servers sidebar, sharing the JSONL scanner +
tool_invocationsSQLite tableomniscio-control.md — the consolidated Omniscio-control skill bundle (cron, automations, settings, recipes, sessions, projects, tags, away-mode, keybindings, pending actions)
create-cron-job-with-ai.md — the cron walkthrough, now powered by the
omniscio-controlbundlelearning-loop.md — the background reviewer that writes skills from your finished work, with its own timeline and undo
beautify-site.md — a bundled skill that takes a bland page to something deliberate in four ordered steps, and audits the built result for AI tells
Claude Code skills, and how to add one on omniscio.com — what a skill is outside the app, and where the files live
Last verified 2026-10-27