agentleFS
an8079an8079/take-skills/skills/hud/SKILL.md

hud

Skill4 starsChanged 8 months agoMITView on GitHub

标准 HUD 格式(单行/双行): ANSI 彩色 HUD(CLI): 纯文本 HUD(无 ANSI): HUD 自动读取以下数据: 更新触发点: 1. 任务节点开始 → 显示节点名 + 开始时间 2. 任务节点完成 → 更新进度 + 显示耗时 3. 检测到风险 → 在 HUD 底部追加警告行 4. 任务队列变化(添加/删除)→ 重绘进度条 5. 每 30 秒(无其他事件)→ 发送心跳更新 风险等级与颜色: - 🟡 WARNING(黄):可能延迟,但不阻塞 - 🟠 ALERT(橙):需要关注,可能影响进度 - 🔴 CRITICAL(红):阻塞性问题,需要人工介入 超时规则: - 单节点预估时间超过 5 分钟时,显示 ⏳ 并预估剩余时间 - 单节点实际时间超过预估 2 倍时,触发 ALERT - 连续 3 个节点超时,升级为 CRITICAL 并暂停,等待用户确认 提供以下 HUD 格式化函数(可在任何执行上下文中调用): **hud_start(project_name, total_steps):** **hud_update(current_step, next_step, progress_pct, elapsed):** **hud_warn(level, message):** **hud_done(summary):** Example 1:多步骤重构任务

9 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use visual-verdict, ai-slop-cleaner and 6 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • LucasCooperBeySkill

    visual-verdict

    Structured visual QA verdict for screenshot-to-reference comparisons. Returns JSON scores driving edit iterations. Use after any UI implementation to verify visual fidelity.

    Also in 3 projects that use this

  • Jurel89Skill

    ai-slop-cleaner

    Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode

    Also in 4 projects that use this

  • Yeachan-HeoSkill

    ultragoal

    Create and execute durable repo-native multi-goal plans over Codex goal mode artifacts.

    Also in 3 projects that use this

  • sundial-orgSkill

    skill

    Find, install, create, improve, and publish AI agent skills through the Sundial ecosystem. Use when the user wants to find or search for skills, install a skill, create a new skill, improve or evaluate an existing skill, or publish a skill to Sundial Hub. Trigger phrases include "find a skill", "install skill", "create a skill", "make a skill", "improve this skill", "evaluate skill", "publish skill", "push skill", "search for skills".

    Also in 5 projects that use this

  • dubwoahSkill

    ask

    Answer questions about the codebase without generating or modifying any code. Use when the user wants to understand how something works, find where something is defined, or explore the project structure. Invoked with /ask.

    Also in 4 projects that use this

  • javatarzSkill

    wiki

    Access and manage the local GitHub Wiki clone. Use this skill when you need to read wiki content (architecture, design docs, guides), update wiki documentation, check wiki status, or push wiki changes. The wiki contains high-level system design and architectural documentation.

    Also in 3 projects that use this

The file

Files
SKILL.md

hud — Real-Time Task Status HUD

name

hud

description

任务实时状态 HUD(Head-Up Display):以飞行员 HUD 的方式,在每个任务执行节点实时推送状态更新。HUD 不打断工作流,而是以紧凑的可视化格式呈现进度、资源消耗、风险预警。与 progress-tracking(事后报告式)不同,hud 是主动推送式——持续显示当前状态,让用户始终知道"现在在哪"。

when to activate

用户说以下话时激活:

  • "hud"
  • "显示进度"
  • "实时状态"
  • "给我一个仪表盘"
  • "显示当前任务状态"
  • "autopilot"(自动与 autopilot 技能联动)
  • 当执行时间预计超过 5 分钟的任务时自动触发

protocol

HUD 布局规范

标准 HUD 格式(单行/双行):

┌─────────────────────────────────────────────────────────┐
│ ⬡ [项目名]        ⏱ 12:34    ████████░░░░░░░░  58%   😐  │
│ [当前任务] ──▶ [下一步]                               │
│ ⚠ 风险: [如有]                                         │
└─────────────────────────────────────────────────────────┘

ANSI 彩色 HUD(CLI):

  ⬡ myproject   12:34   ▓▓▓▓▓▓▓▓░░░░  58%   ⏳ build:✓  test:▓▓
  → Writing index.ts ──▶ Running tests
  ⚠ slow query detected (>2s)

纯文本 HUD(无 ANSI):

[========----] 58% | myproject | 12:34 | BUILD:OK | TEST:RUN
-> Writing index.ts -> Running tests
[!] slow query detected (>2s)

HUD 数据源

HUD 自动读取以下数据:

数据字段来源更新频率
项目名当前工作目录名静态
耗时计时器每节点
进度条已完成任务/总任务每节点
当前节点当前执行步骤名每节点
下一步队列中下一个任务每节点
风险预警执行过程中检测实时
情绪指标错误率/成功率每节点

HUD 更新协议

更新触发点:

  1. 任务节点开始 → 显示节点名 + 开始时间
  2. 任务节点完成 → 更新进度 + 显示耗时
  3. 检测到风险 → 在 HUD 底部追加警告行
  4. 任务队列变化(添加/删除)→ 重绘进度条
  5. 每 30 秒(无其他事件)→ 发送心跳更新

风险等级与颜色:

  • 🟡 WARNING(黄):可能延迟,但不阻塞
  • 🟠 ALERT(橙):需要关注,可能影响进度
  • 🔴 CRITICAL(红):阻塞性问题,需要人工介入

超时规则:

  • 单节点预估时间超过 5 分钟时,显示 ⏳ 并预估剩余时间
  • 单节点实际时间超过预估 2 倍时,触发 ALERT
  • 连续 3 个节点超时,升级为 CRITICAL 并暂停,等待用户确认

HUD 格式化 API

提供以下 HUD 格式化函数(可在任何执行上下文中调用):

hud_start(project_name, total_steps):

┌────────────────────────────────────────┐
│ ⬡ [project_name]    ⏱ 00:00           │
│ [====--------]   0/[total_steps]       │
│ → 初始化...                             │
└────────────────────────────────────────┘

hud_update(current_step, next_step, progress_pct, elapsed):

┌────────────────────────────────────────┐
│ ⬡ [project_name]    ⏱ [elapsed]       │
│ [██████--------]   60%  [X/Y]          │
│ ✓ [完成步骤]                             │
│ → [当前步骤] ──▶ [下一步]               │
└────────────────────────────────────────┘

hud_warn(level, message):

│ ⚠ [level] [message]                    │

hud_done(summary):

┌────────────────────────────────────────┐
│ ✅ 完成!    ⏱ [total_time]            │
│ ████████████████ 100%                  │
│ → [最终结果摘要]                        │
└────────────────────────────────────────┘

examples

Example 1:多步骤重构任务

┌──────────────────────────────────────────────────────────┐
│ ⬡ react-ts-migration     ⏱ 08:23     ████████░░░░░░  47% │
│ Writing index.ts ──▶ Running type check                  │
│ ✅ Audit complete (42 files, 18 need migration)          │
└──────────────────────────────────────────────────────────┘

┌──────────────────────────────────────────────────────────┐
│ ⬡ react-ts-migration     ⏱ 14:05     ██████████████░░  82% │
│ ✓ Type fix (43 errors → 7) ──▶ Final build              │
│ ⚠ WARNING: 3 components use dynamic 'any' — manual review│
└──────────────────────────────────────────────────────────┘

┌──────────────────────────────────────────────────────────┐
│ ✅ 完成!    ⏱ 17:42                                      │
│ ████████████████ 100%                                     │
│ → 42 files migrated, 0 build errors, 3 warnings          │
└──────────────────────────────────────────────────────────┘

Example 2:数据处理 Pipeline

[████████░░░░░░░░░] 45% | etl-pipeline | 23:15 | 
  -> Parsing CSV (2.3M rows) -> Schema validation -> Loading DB
  [!] ALERT: Row 4821 has missing 'user_id', skipping...
  [memory: 1.2GB/4GB]

notes

  • HUD 输出永远不超过 4 行(不含警告),超出时旧行自动滚动出视图
  • 在 progress-tracking 技能的上下文中,HUD 作为其前端展示层
  • 与 autopilot 联动时,HUD 默认激活;用户说 "hud off" 可禁用
  • 支持 ANSI 颜色代码,在不支持彩色的终端自动降级为纯文本
  • HUD 每次更新之间保留前一次的状态(diff 显示),避免信息刷屏

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.