send-it — ai-low-risk send-it, toolkit, community, ai-low-risk, ide skills, Claude Code, Cursor, Windsurf

v1.0.0

关于此技能

Official Cognite Data Fusion Toolkit CLI

# 核心主题

cognitedata cognitedata
[20]
[6]
更新于: 4/17/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 1/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Review Score
1/11
Quality Score
28
Canonical Locale
en
Detected Body Locale
en

Official Cognite Data Fusion Toolkit CLI

核心价值

Official Cognite Data Fusion Toolkit CLI

适用 Agent 类型

Suitable for operator workflows that need explicit guardrails before installation and execution.

赋予的主要能力 · send-it

! 使用限制与门槛

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The page lacks a strong recommendation layer.
  • - The page lacks concrete use-case guidance.
  • - The page lacks explicit limitations or caution signals.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

评审后的下一步

先决定动作,再继续看上游仓库材料

Killer-Skills 的主价值不应该停在“帮你打开仓库说明”,而是先帮你判断这项技能是否值得安装、是否应该回到可信集合复核,以及是否已经进入工作流落地阶段。

实验室 Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

常见问题与安装步骤

以下问题与步骤与页面结构化数据保持一致,便于搜索引擎理解页面内容。

? FAQ

send-it 是什么?

Official Cognite Data Fusion Toolkit CLI

如何安装 send-it?

运行命令:npx killer-skills add cognitedata/toolkit/send-it。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

send-it 支持哪些 IDE 或 Agent?

该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。

安装步骤

  1. 1. 打开终端

    在你的项目目录中打开终端或命令行。

  2. 2. 执行安装命令

    运行:npx killer-skills add cognitedata/toolkit/send-it。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    send-it 已启用,可立即在当前项目中调用。

! 参考页模式

此页面仍可作为安装与查阅参考,但 Killer-Skills 不再把它视为主要可索引落地页。请优先阅读上方评审结论,再决定是否继续查看上游仓库说明。

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

send-it

安装 send-it,这是一款面向AI agent workflows and automation的 AI Agent Skill。支持 Claude Code、Cursor、Windsurf,一键安装。

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Send It / Stage It

When the user says "send it":

1. Stage and pre-commit

  • Run git status to see all changed and untracked files.
  • Only stage files that were created or modified as part of this task. Use git add <file>... with explicit paths.
  • If there are unstaged changes in files not related to this task, list them and ask the user what to do (stage them too, ignore, stash, etc.). Do not silently include unrelated changes.
  • Run uv run pre-commit run --all-files to validate staged changes.
  • If pre-commit hooks fail, fix every reported issue, re-stage the fixes, and re-run. Repeat until all hooks pass.

2. Ask: stage only or commit?

Use the AskQuestion tool to ask the user:

"All pre-commit hooks pass. What would you like to do?"

  • Stage only — leave changes staged for local review
  • Commit and push — commit, push, and open/update a PR

If the user chose Stage only, stop here.

3. Commit

  • Run git diff --cached and git log --oneline -5 to review staged changes and match the repo's commit style.
  • Write a concise commit message summarizing the changes.
  • Run git commit with that message.

4. Sync and push

  • Run git pull origin main to merge latest main into the branch.
  • Run git pull origin to sync the current branch (ignore errors if the remote branch doesn't exist yet).
  • Run git push -u origin HEAD to push (sets upstream if needed).

5. PR creation (if needed)

  • Check if a PR exists: gh pr view --json url --repo cognitedata/toolkit 2>/dev/null.
  • If no PR exists, suggest creating one:
    • Ask the user for the Jira ticket ID.

    • Propose a title: [TICKET-ID] Description of changes.

    • Draft a body by reading .github/pull_request_template.md and filling it in using git log main..HEAD --oneline.

    • Show the proposed PR title and body, and ask for confirmation before creating it.

    • If the user confirms, create the PR as a draft:

      bash
      1gh pr create --title "..." --body "..." --base main --draft --repo cognitedata/toolkit
    • After creation, verify the PR body doesn't contain "Made with Cursor". If it does, suggest the user disable this in Cursor settings: Settings > General > uncheck "Include 'Made with Cursor' in PRs".

    • Comment "/gemini review" on the PR to request a review from Gemini.

6. Monitor CI

  • Launch a background agent (subagent_type="shell") to run gh pr checks --watch --repo cognitedata/toolkit.
  • When checks complete, report back: green (all passing) or red (with names of failed checks).
  • If all checks pass, mark the PR as ready for review: gh pr ready --repo cognitedata/toolkit.
  • If checks fail:
    • For each failed check, fetch its logs with gh pr checks --repo cognitedata/toolkit and gh run view <run-id> --log-failed --repo cognitedata/toolkit.
    • Transient failures (network timeouts, flaky tests, rate limits, runner issues): re-run the failed job once with gh run rerun <run-id> --failed --repo cognitedata/toolkit.
    • Non-transient failures (lint errors, test assertions, type errors, build failures): read the logs, fix the underlying code issue, then run the full "send it" flow again (stage, commit, push, monitor).

相关技能

寻找 send-it 的替代方案 (Alternative) 或可搭配使用的同类 community Skill?探索以下相关开源技能。

查看全部

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

333.8k
0
AI

widget-generator

Logo of f
f

为prompts.chat的信息反馈系统生成可定制的插件小部件

149.6k
0
AI

flags

Logo of vercel
vercel

React 框架

138.4k
0
浏览器

pr-review

Logo of pytorch
pytorch

Python中具有强大GPU加速的张量和动态神经网络

98.6k
0
开发者工具