Show one skill in full — its team record or Library folder, versions, installs, health, and its eval report when it is a team skill — as Markdown boards from the terum-skills CLI. Use when the user names a skill and asks what it is, who installed it, how it scored, or what its receipt says.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Show one skill: the detail board, then its eval report when the skill is shared with the team.
Arguments: everything after the command (in Claude Code this arrives as "$ARGUMENTS"): the skill's name, a unique prefix of it, or nothing when the working directory is inside a Library skill folder; --team <name> is passed through.
npx -y terum-skills@latest ls skill <name> --format md
Then, only when that board's Next: line offers eval-report, also run
npx -y terum-skills@latest eval-report <name> --format md
and show both boards, detail first. A failure naming several candidates (Ambiguous skill name …) is a result: show it and ask which one.
Nothing to confirm: both commands only read.
Show the boards verbatim; do not re-summarise unless asked. Offer the Next: line. No skill named … is a result, not something to retry: offer the list-skills skill so the user can find the name. An italic _Resolved: …_ line says which folder or record answered a prefix or a bare invocation; keep it.
y, never drive the CLI with expect, never add --frames to dodge a question. A question the CLI asks means the verb belongs in a terminal: say so and hand over the command.!`command` injection; run every command with your shell tool and read its output.cd; run from the current working directory and pass absolute paths.When CODEX_SANDBOX_NETWORK_DISABLED=1 is set and the command starts with npx, add --prefer-offline after npx so a cached package resolves without the registry; if npx still reports a network error, ask the user to run the command in a terminal. In that sandbox the verbs that need the network — sync, install, publish, invite, eval, and update's release probe — are handed to a terminal with the reason.
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Evaluate a local skill with the terum-skills CLI — hygiene, trigger evals and execution cases against a baseline, billed to the user's own Claude Code — after confirming the cost, and show the result as a Markdown board. Use when the user asks to eval, test, score or benchmark a skill, or to see whether an edit made it better.
日本語の概要は準備中です。原文の説明を表示しています。
Show a team skill's eval history — committed receipts per version and this machine's local runs — as a Markdown board from the terum-skills CLI, without fetching. Use when the user asks how a shared skill scored, which version passed, or what its receipts say.
日本語の概要は準備中です。原文の説明を表示しています。
List the skills on this machine (your Library) and the skills your team shares (the Marketplace) as Markdown boards from the terum-skills CLI. Use when the user asks what skills they have, what the team shares, what is installed, edited, untracked or missing an eval, or wants an overview of their terum-skills state.
日本語の概要は準備中です。原文の説明を表示しています。
Search the team's shared skills by name, description or category, optionally narrowed by author or project, and show the matches as a Markdown board from the terum-skills CLI. Use when the user asks whether the team has a skill for something or wants to find one by keyword.
日本語の概要は準備中です。原文の説明を表示しています。
Show the state of terum-skills on this machine — team, clone, session hook, pending work, machine facts — and whether a newer CLI release exists, as Markdown boards. Use when the user asks whether terum-skills is set up, in sync or up to date, or when something about it seems off.
日本語の概要は準備中です。原文の説明を表示しています。
Fetch the team's shared skills — reset each disposable team clone to origin/main — and show the outcome per team as a Markdown board from the terum-skills CLI. Use when the user wants the newest catalogue, receipts or roster before listing, searching or installing.
日本語の概要は準備中です。原文の説明を表示しています。