lever公式
github / lever
基本情報
lever について
GitHub's official Copilot plugin of feedback-loop agent skills: /lever turns a vague complaint into a measurable Loop Card, runs parallel experiment arms, writes unattended briefs, shepherds PRs to green, reviews with several models and sets how much autonomy agents get.
lever をインストール
copilot plugin marketplace add github/lever && copilot plugin install lever@leverlever の使い方
- 1
Install the plugin in GitHub Copilot (CLI or app): add the github/lever marketplace, then install lever@lever.
copilot plugin marketplace add github/lever - 2
Then install the plugin itself.
copilot plugin install lever@lever - 3
Start a new session and try a read-only verb first, for example: /lever loop our test suite feels slow. just the card, don't change anything. You get a Loop Card: the metric, how to measure it, how noisy it is and what counts as a win; nothing is pushed or merged.
- 4
Run /lever setup to answer three questions and set your dials: autonomy (L0 only proposes, L2 gets PRs green and you merge, up to L5) and spend (standard, high or max).
- 5
Use the verbs by goal: brief, deliver, refactor, shepherd and land to build; loop, arms and review to improve; automate and health to run things without you; mirror, steer and autonomy to tune lever to how you work. Or describe the problem after /lever and it picks the verb.
できること
16 skills behind one /lever command: brief, deliver, refactor, backlog, shepherd, land, status, loop, arms, review, automate, health, mirror, steer, autonomy, spend
Read-only verbs such as loop return a Loop Card (metric, measurement, noise, win bar) without pushing anything
Autonomy dial L0-L5 decides who merges; spend standard/high/max sets model tier and parallel lanes
Install: copilot plugin marketplace add github/lever, then copilot plugin install lever@lever
Work is tracked as GitHub issues with the lever label; automations install paused and dry-run first
MIT licensed, from GitHub (created 2026-10-25)
要件と注意点
- What it is: 16 skills (one per verb) from how AI-forward engineers at GitHub work, packaged as one /lever command. Read-only skills such as loop can also load on their own when your ask fits.
- Requirements: GitHub Copilot with plugin support. Per-repo install for the Copilot cloud coding agent: copy skills/ plus docs, templates, config and automations into .github/.
- Limits: anything that pushes, files issues, opens PRs or schedules runs follows your autonomy dial and your repo's branch protection; automations install paused and dry-run on past events before they are turned on.
- Work lever starts is tracked as GitHub issues assigned to you with the lever label, so /lever status lists what is in flight.
- MIT licensed; repository created 2026-10-25.
参考資料
2026-11-11 にソースリポジトリと照合しました。
開発 のその他のスキル
vercel-react-best-practices
vercel-labs / agent-skills
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
improve-codebase-architecture
mattpocock / skills
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
shadcn
shadcn / ui
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", or "switch to --preset".
caveman-compress
juliusbrussee / caveman
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or "compress memory file"
caveman-stats
juliusbrussee / caveman
Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.
full-output-enforcement
leonxlnx / taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
コメント