Run Kilo CLI via background process for programmatic control.
数据来源:ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一:命令行安装(推荐)
推荐(无需提前安装 clawhub)
npx clawhub@latest --dir ~/.claude/skills install kilocli-coding-agent或使用 clawhub CLI(需提前安装)
clawhub --dir ~/.claude/skills install kilocli-coding-agent⚠️ 需要 Node.js 18+,没有 Node?请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二:手动下载安装(无需 Node)
下载 ZIP,解压后将文件夹放到以下路径,重启 Agent 即可:
安装路径
~/.claude/skills/kilocli-coding-agent/💡解压后将文件夹放到上方路径,重启 Agent 即可生效
--- name: kilocli-coding-agent description: Run Kilo CLI via background process for programmatic control. version: 0.0.9 metadata: openclaw: requires: env: - GITHUB_TOKEN bins: - kilo - git - gh - tmux primaryEnv: GITHUB_TOKEN --- ---
IMPORTANT: You need to have Kilo CLI installed and configured so OpenClaw can use it without any issue.
npm install -g @kilocode/cli
If you want to automate pull requests to Github, then you also need to authenticate Github CLI in your project: https://github.com/cli/cli#installation
Use bash background mode for non-interactive coding work. For interactive coding sessions, use the tmux skill (always, except very simple one-shot prompts).
# Create temp space for chats/scratch work
SCRATCH=$(mktemp -d)
# Start agent in target directory ("little box" - only sees relevant files)
bash workdir:$SCRATCH background:true command:"<agent command>"
# Or for project work:
bash workdir:~/project/folder background:true command:"<agent command>"
# Returns sessionId for tracking
# Monitor progress
process action:log sessionId:XXX
# Check if done
process action:poll sessionId:XXX
# Send input (if agent asks a question)
process action:write sessionId:XXX data:"y"
# Kill if needed
process action:kill sessionId:XXX
Why workdir matters: Agent wakes up in a focused directory, doesn't wander off reading unrelated files (like your soul.md 😅).
---
bash workdir:~/project background:true command:"kilo run --auto \"Build a snake game with dark theme\""
⚠️ CRITICAL: Never review PRs in OpenClaw's own project folder!
# Option 1: Review in the actual project (if NOT OpenClaw)
bash workdir:~/Projects/some-other-repo background:true command:"kilo run \"Review current branch against main branch\""
# Option 2: Clone to temp folder for safe review (REQUIRED for OpenClaw PRs!)
REVIEW_DIR=$(mktemp -d)
git clone https://github.com/openclaw/openclaw.git $REVIEW_DIR
cd $REVIEW_DIR && gh pr checkout 130
bash workdir:$REVIEW_DIR background:true command:"kilo run \"Review current branch against main branch\""
# Clean up after: rm -rf $REVIEW_DIR
# Option 3: Use git worktree (keeps main intact)
git worktree add /tmp/pr-130-review pr-130-branch
bash workdir:/tmp/pr-130-review background:true command:"kilo run \"Review current branch against main branch\""
Why? Checking out branches in the running OpenClaw repo can break the live instance!
# Fetch all PR refs first
git fetch origin '+refs/pull/*/head:refs/remotes/origin/pr/*'
# Deploy the army - one Kilo CLI per PR!
bash workdir:~/project background:true command:"kilo run \"Review PR #86. git diff origin/main...origin/pr/86\""
bash workdir:~/project background:true command:"kilo run \"Review PR #87. git diff origin/main...origin/pr/87\""
bash workdir:~/project background:true command:"kilo run \"Review PR #95. git diff origin/main...origin/pr/95\""
# ... repeat for all PRs
# Monitor all
process action:list
# Get results and post to GitHub
process action:log sessionId:XXX
gh pr comment <PR#> --body "<review content>"
git fetch origin '+refs/pull//head:refs/remotes/origin/pr/'git diff origin/main...origin/pr/XXgh pr comment to post reviews to GitHub---
Use the tmux skill for interactive coding sessions (always, except very simple one-shot prompts). Prefer bash background mode for non-interactive runs.
---
For fixing multiple issues in parallel, use git worktrees (isolated branches) + tmux sessions:
# 1. Clone repo to temp location
cd /tmp && git clone [email protected]:user/repo.git repo-worktrees
cd repo-worktrees
# 2. Create worktrees for each issue (isolated branches!)
git worktree add -b fix/issue-78 /tmp/issue-78 main
git worktree add -b fix/issue-99 /tmp/issue-99 main
# 3. Set up tmux sessions
SOCKET="${TMPDIR:-/tmp}/kilo-fixes.sock"
tmux -S "$SOCKET" new-session -d -s fix-78
tmux -S "$SOCKET" new-session -d -s fix-99
# 4. Launch Kilo CLI in each (after npm install!)
tmux -S "$SOCKET" send-keys -t fix-78 "cd /tmp/issue-78 && npm install && kilo run 'Fix issue #78: <description>. Commit and push.'" Enter
tmux -S "$SOCKET" send-keys -t fix-99 "cd /tmp/issue-99 && npm install && kilo run 'Fix issue #99: <description>. Commit and push.'" Enter
# 5. Monitor progress
tmux -S "$SOCKET" capture-pane -p -t fix-78 -S -30
tmux -S "$SOCKET" capture-pane -p -t fix-99 -S -30
# 6. Check if done (prompt returned)
tmux -S "$SOCKET" capture-pane -p -t fix-78 -S -3 | grep -q "❯" && echo "Done!"
# 7. Create PRs after fixes
cd /tmp/issue-78 && git push -u origin fix/issue-78
gh pr create --repo user/repo --head fix/issue-78 --title "fix: ..." --body "..."
# 8. Cleanup
tmux -S "$SOCKET" kill-server
git worktree remove /tmp/issue-78
git worktree remove /tmp/issue-99
Why worktrees? Each Kilo CLI works in isolated branch, no conflicts. Can run 5+ parallel fixes!
Why tmux over bash background? Kilo CLI is interactive — needs TTY for proper output. tmux provides persistent sessions with full history capture.
---
---
When submitting PRs to external repos, use this format for quality & maintainer-friendliness:
## Original Prompt
[Exact request/problem statement]
## What this does
[High-level description]
**Features:**
- [Key feature 1]
- [Key feature 2]
**Example usage:**
command example
## Feature intent (maintainer-friendly)
[Why useful, how it fits, workflows it enables]
## Prompt history (timestamped)
- YYYY-MM-DD HH:MM UTC: [Step 1]
- YYYY-MM-DD HH:MM UTC: [Step 2]
## How I tested
**Manual verification:**
1. [Test step] - Output: `[result]`
2. [Test step] - Result: [result]
**Files tested:**
- [Detail]
- [Edge cases]
## Session logs (implementation)
- [What was researched]
- [What was discovered]
- [Time spent]
## Implementation details
**New files:**
- `path/file.ts` - [description]
**Modified files:**
- `path/file.ts` - [change]
**Technical notes:**
- [Detail 1]
- [Detail 2]
---
Key principles:
安装 Kilo CLI Coding Agent 后,可以对 AI 说这些话来触发它
Help me get started with Kilo CLI Coding Agent
Explains what Kilo CLI Coding Agent does, walks through the setup, and runs a quick demo based on your current project
Use Kilo CLI Coding Agent to run Kilo CLI via background process for programmatic control
Invokes Kilo CLI Coding Agent with the right parameters and returns the result directly in the conversation
What can I do with Kilo CLI Coding Agent in my developer & devops workflow?
Lists the top use cases for Kilo CLI Coding Agent, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/kilocli-coding-agent/ 目录(个人级,所有项目可用),或 .claude/skills/kilocli-coding-agent/(项目级)。重启 AI 客户端后,用 /kilocli-coding-agent 主动调用,或让 AI 根据上下文自动发现并使用。
Kilo CLI Coding Agent 支持 Claude、Cursor、OpenClaw,可与这些 AI 平台无缝集成,扩展其能力。
Kilo CLI Coding Agent 可免费安装使用。请查阅仓库了解许可证信息。
Run Kilo CLI via background process for programmatic control.
Kilo CLI Coding Agent 属于「Developer & DevOps」分类,该分类的技能帮助 AI 智能体在此领域执行专业任务。
Automate my developer & devops tasks using Kilo CLI Coding Agent
Identifies repetitive steps in your workflow and sets up Kilo CLI Coding Agent to handle them automatically