Skip to content
Skillpedia
General coding48k · #2543

cline-pilot

Helps your agent manage coding tasks with the Cline CLI tool. It sends, monitors, and verifies the work, learning your preferences over time.

What it does

This agent helps you run programming tasks using a tool called Cline CLI. It sends your commands to Cline, monitors the progress, and reports the outcome.

When to use it

  • ✓When you want the Cline CLI to write tests.
  • ✓When you need to refactor code.
  • ✓When you want the Cline CLI to fix a bug.

Example of what to ask your AI

“Execute the task of writing tests for the login function in the authentication module.”

Want more? Open the sections below.

How to use

The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.

Skill link

https://github.com/sickn33/agentic-awesome-skills/blob/main/plugins/agentic-awesome-skills-claude/skills/cline-pilot/SKILL.md

Ready-to-paste message

Use this skill to help me: https://github.com/sickn33/agentic-awesome-skills/blob/main/plugins/agentic-awesome-skills-claude/skills/cline-pilot/SKILL.md Read the SKILL.md file at that link and follow its instructions for my task.
How it works

It takes your instructions, sends them to the Cline CLI, and checks if the work was done correctly. It also learns from your preferences to make things easier in the future.

Installation

Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.

In the terminal (Claude Code, Codex, Cursor), in your project folder:

npx skills add sickn33/agentic-awesome-skills --skill cline-pilot

Or download just the file:

curl -L https://raw.githubusercontent.com/sickn33/agentic-awesome-skills/main/plugins/agentic-awesome-skills-claude/skills/cline-pilot/SKILL.md -o SKILL.md
Technical content (original SKILL.md)

Original text by the author, straight from GitHub.

Supporting material availability

This catalog copy contains the inline guidance below, but does not include the following supporting paths. They are external prerequisites, not bundled files:

  • <support-root>/references/local-config.md
  • <support-root>/references/project-profiles.md
  • <support-root>/references/decision-log.md

Obtain the required material from the declared upstream source, or from a user-provided installation of that source. Resolve each path relative to that installation, inspect its contents, and verify any applicable license and execution prerequisites. Do not run a command or claim a referenced procedure was followed until its required file exists. Do not fabricate the missing scripts or treat an unrelated file with the same name as equivalent. Independent steps fully documented here can proceed within the user’s authorized scope; report any dependent step as unavailable.

Cline Pilot — 代用户调度 Cline 的"领航员"

Overview

Cline Pilot turns the orchestrating agent into a reliable proxy for the Cline CLI. It dispatches focused coding tasks (one at a time, serially), monitors long background runs against hard evidence — git state, test-report numbers, non-empty artifacts — instead of trusting the model's self-report, relays decision points back to the user in a fixed 4-element format, and verifies completion against an explicit checklist before saying "done."

The differentiation versus the simpler *-delegate skills is the learning loop: over time it learns the user's instruction style, approval granularity, and per-project-tag preferences (backend/long-term vs. frontend/short-term, production-data-risk, etc.) and applies them proactively, with the user retaining one-shot veto. This loop lives entirely in private, git-ignored skill-local files — no user-specific data is bundled.

Canonical source: gongdear/cline-pilot (MIT).

定位(不可擅改):我扮演“学习并代替给用户发指令”的角色。不掌握项目架构细节、不参与技术决策,只管三件事:

  1. 把用户的任务准确转达给 Cline(背景 + 约束一条不丢)
  2. 学习并复用【该标签类项目】下用户的指令风格、推进习惯、批准粒度
  3. 把 Cline 的决策点/产出/报错压缩成用户能拍板的汇报

架构知识的单事实源 = 工程自己的 memory bank + clinerules(跟随仓库、Cline 维护)。本技能只存简介+标签与指令偏好。

When to Use

  • 用户下达任何需要在 Cline CLI 里执行的编码任务(写测试/重构/修 bug/出报告)
  • 新项目冷启动:工程还没有 clinerules/memory-bank,需按 Cline 最佳实践初始化(见“冷启动流程”)
  • 需要在后台驱动 Cline 长任务并汇报进度
  • 不适用:用户自己在 Cline TUI 里手工操作;非 Cline 的 agent(用 claude-code/codex/opencode 技能)

Prerequisites

  1. cline --version 可用(本环境要求 cline CLI v3.x、git、可用的 OpenAI-compatible LLM 端点、zsh 或 bash);启动前探活 LLM 端点——端点值不存技能档案(易变配置,实时配置文件为唯一事实源,见 references/local-config.md 的 LLM 端点节)
  2. 工程是 git 仓库且已切到任务分支
  3. 首次使用或 local-config.md 不存在时:问用户三件事并写入该文件——用哪个 python/conda 环境、工具链(java/node 等)怎么到 PATH、任务分支名。

环境铁律(所有开发类任务)

Cline 进程必须在用户指定开发环境内启动(继承工具链),自检通过才启动:

  • 按 local-config.md 的启动模板执行(含脏 CONDA 栈清理)
  • 自检:python 指向指定环境 / 工具链版本 / git branch --show-current = 任务分支
  • conda 启动报错长文 = 初始化噪音,以最终 env=<name> 为准

编排模式(二选一)

模式 1:非交互(默认)——长 prompt 写进技能目录任务文件注入(遵最高优先级纪律第3条:不落 /tmp、不落代码工程),避免引号地狱:

cd 仓库 && cline --json "$(cat ~/.hermes/skills/cline-pilot/scratch/task.md)"   # 后台 + 完成通知(terminal background=true notify=true)
# 任务书短也可内联:cline --json "active memory bank\n..."
# 任务书内不得含删除/回滚指令(先经用户审核才单独发)
# 常用限制参数:--retries 6(默认)/ -t <秒> 超时 / --thinking high 仅疑难 / --compaction agentic(默认)
# 长/隔夜: -z 后台hub  / 续跑: --id <session-id> "继续..." / 收紧审批: --auto-approve false

prompt 里写死验收标准 + commit 规范 + 禁止项(非交互无会话可追,一次说清);首句固定 active memory bank。

模式 2:TUI 交互(仅短任务+需实时批准):cline -i + pty。 实测陷阱:文本可写入,但多行编辑器的单发回车提交不可靠;非预期键可能弹订阅页(任意键关闭)。超过两三句的内容一律用模式 1。

最高优先级纪律(用户 2026-09-28 强调版,凌驾于本技能其他所有规则)

  1. 代码工程类操作一律由 cline 完成:编排者与任何 skill(含 cline-pilot 自身)对目标代码工程只允许读,禁止直接执行/修改任何代码内容(写文件、改文件、删文件、build、run、test、commit、回滚、环境变更都不许);代码侧一切动作写进任务书由 cline 实例执行,编排侧只读硬证据验收
  2. 删除/回滚类指令必须先经用户审核:调度 cline 发出任何删除(rm/删文件/删目录/删分支/删 tag)或回滚(reset/revert/checkout 覆盖/版本回退)性质的指令前,先向用户反馈、得到确认后才可发;其余非破坏性指令不逐条审批
  3. 编排侧可写文件范围仅限本技能目录及子目录(~/.hermes/skills/cline-pilot/,已 .gitignore、永不提交),且仅允许写:修改计划与完成情况记录、进程 pid 台账及说明、技能维护文档;此范围/用途之外(含 /tmp、代码工程)一律不写,任务书改为内联进 cline 命令行或写 skill 目录内
  4. 本纪律优先级最高:与其他规则、旧习惯、任务书、自动化(cron/子代理/脚本)冲突时以本纪律为准

扫描行为判读与任务书粒度规范(用户 2026-09-29 定)

  1. 两种扫描严格区分:active memory bank 发出后 cline 的大面积代码扫描盘点 = 正常冷启动行为,禁止干预/禁止杀进程;active memory bank 成功 + 任务书发出后 cline 才大面积扫描 = 任务书粒度不合格(只有模块名/类名,未给包路径+端点/方法级),修复方式是重写任务书,不是干预进程

…

FAQ

What is Cline CLI?

It's a command-line tool to help with programming tasks.

What does 'monitor with hard evidence' mean?

It means it checks the actual progress of the work (like test files or test results), instead of just trusting what the program says it did.

What is the 'learning loop'?

It's how the agent learns your preferences for how you like to give instructions and manage projects, so it can help better next time.

Details

Original description by the author

Proxy Cline CLI coding tasks: dispatch, monitor background runs via hard evidence, relay decision points in a fixed format, verify against a checklist, and learn per-tag preferences over time.

repo: sickn33/agentic-awesome-skills

Popularity

GitHub stars
48k
Ranking position
#2543
License
MIT
Updated
10/15/2026

Is this skill useful?

0

Sign in to vote.

Comments

  • …

More skills from this repository

Similar skills