Agent skill

Caixun Work Hours

by nexus-research-lab in nexus-research-lab/nexus

彩讯(RichPMS)工时填报助手:把当前会话、代码记录或用户口述整理成日报,按 8 小时分配,经用户确认后写入工时系统。用户提到“填日报、报工、补报、本周工时、日报被驳回”时使用。

Apache-2.0Auto-check passedAgent Workflows

Install Caixun Work Hours

skills CLI
$ npx skills add nexus-research-lab/nexus --skill caixun-work-hours -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install nexus-research-lab/nexus caixun-work-hours --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/nexus-research-lab/nexus.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/caixun-work-hours .claude/skills/caixun-work-hours && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
caixun-work-hours
GitHub stars
151
Token cost
~1k tokens
SKILL.md length
263 words
Files
9 (incl. scripts, references)
Skills in repo
17
Repo updated
First seen
Licence
Apache-2.0

At a glance

彩讯(RichPMS)工时填报助手:把当前会话、代码记录或用户口述整理成日报,按 8 小时分配,经用户确认后写入工时系统。用户提到“填日报、报工、补报、本周工时、日报被驳回”时使用。

  • Works in 4 steps: Nexus 内先引导用户到“连接器”或智能体“工具”页添加… → 若用户明确选择外部客户端,再由用户主动运行… → 授权(均弹浏览器输 PMS 账密):WorkBuddy 跑… → …
  • Agent Workflows work in your project
  • SKILL.md covers 首次接入, 外部客户端兜底接入(Codex stdio bridge), 令牌失效自愈(WorkBuddy 专属,2026-09-20) and 强制流程(不可跳步), plus 3 more sections
  • Runs Python and Shell scripts from its folder; calls claude, codex and python3

What it does

Caixun Work Hours is an agent skill from nexus-research-lab/nexus. 彩讯(RichPMS)工时填报助手:把当前会话、代码记录或用户口述整理成日报,按 8 小时分配,经用户确认后写入工时系统。用户提到“填日报、报工、补报、本周工时、日报被驳回”时使用。

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including scripts and reference files (for example `_meta.json`, `references/validation-rules.md` and `scripts/ai-workbuddy-auth.py`).

It sits in Agent Workflows. It works with Model Context Protocol. The repository describes itself as: Multi-agent collaboration platform for persistent, proactive AI agents across rooms, workspaces, skills, and external services. The licence is Apache-2.0.

When your agent uses it

  • Agent Workflows work in your project

Example prompts

  • “填日报、报工、补报、本周工时、日报被驳回”
  • “/caixun-work-hours”

Requirements

  • Python 3
  • A Bash shell

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Nexus 内先引导用户到“连接器”或智能体“工具”页添加 richpm,填写管理员提供的服务地址并完成授权。
  2. 若用户明确选择外部客户端,再由用户主动运行 scripts/setup_mcp.py 完成兼容配置;该脚本会修改外部客户端配置,
  3. 授权(均弹浏览器输 PMS 账密):WorkBuddy 跑 scripts/ai-workbuddy-auth.py、ZCode 跑
  4. 完成后提示重启外部客户端/开新会话,说“查我的日报”验证。

What it can do on your machine

Read from SKILL.md and the folder at commit 67f54e7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 6 files in scripts/ (Python and Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • claude
    • codex
    • python3
    • bash
    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Caixun Work Hours loads about 1k tokens when it runs, and up to ~1.4k if it reads all its reference files. Until then it costs about 27 tokens; SKILL.md has 263 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~27
When it runs · the whole SKILL.md, loaded when a task matches
~1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from nexus-research-lab/nexus at commit 67f54e7, republished under its Apache-2.0 licence (© nexus-research-lab). 263 words, ~1,045 tokens.

Download SKILL.mdSave it as .claude/skills/caixun-work-hours/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
caixun-work-hours
description
彩讯(RichPMS)工时填报助手:把当前会话、代码记录或用户口述整理成日报,按 8 小时分配,经用户确认后写入工时系统。用户提到“填日报、报工、补报、本周工时、日报被驳回”时使用。
title
彩讯工时填报
version
1.0.2
scope
any
tags
彩讯, 工时, 日报, RichPMS, 报工
category_key
data-automation
category_name
数据与自动化
recommendation
适合需要在彩讯 RichPMS 中整理、核对并提交本人日报工时的场景。

彩讯工时填报

这是一个随 Nexus 发布、可直接从技能选择器启用的彩讯工时模板,来源于 SkillHub 的 @user_ab3d2b8a/richpm-daily-report(version 1.0.2)。首次使用只需接入一次 richpm MCP;没有接入时,按“首次接入”步骤配置,不会凭空提交工时。

你通过 MCP 服务器 richpm 的工具操作 RichPMS 工时系统(工具:get_report_calendar、get_fillable_projects_tasks、get_day_detail、check_can_submit、save_daily_report_draft、submit_daily_report)。 在 Nexus 中优先从左侧“连接器”或智能体“工具”页接入并完成授权;若当前版本没有该入口, 再提示用户按所用外部客户端接入 MCP 服务器 <后端地址>/api/ai/mcp:

  • Claude Code:claude mcp add richpm <后端地址>/api/ai/mcp --transport http
  • WorkBuddy:设置 → MCP 插件 → 添加 HTTP 服务器,地址同上(鉴权方式以客户端支持为准)
  • Codex:~/.codex/config.toml 的 [mcp_servers.richpm] 配置 url 接入后按管理员指引完成授权(PMS 账号),工具名前缀以客户端实际注入为准(如 mcp__richpm__get_report_calendar)。

首次接入

用户说“配置 richpm / 接入日报”,或首次使用且工具不可用时:

  1. Nexus 内先引导用户到“连接器”或智能体“工具”页添加 richpm,填写管理员提供的服务地址并完成授权。 Skill 不自行修改 Nexus 配置、凭据或其他客户端的配置文件。
  2. 若用户明确选择外部客户端,再由用户主动运行 scripts/setup_mcp.py 完成兼容配置;该脚本会修改外部客户端配置, 运行前应说明影响并确认目标客户端。
  3. 授权(均弹浏览器输 PMS 账密):WorkBuddy 跑 scripts/ai-workbuddy-auth.py、ZCode 跑 scripts/richpm_zcode_auth.py;Claude Code 按客户端的 MCP/OAuth 登录流程完成授权;Codex(CLI) 运行 codex mcp login richpm(自动动态注册后弹浏览器;桌面版对 http 内网授权服务器有安全限制, 需 HTTPS/SSH 隧道,详见对接指导)。
  4. 完成后提示重启外部客户端/开新会话,说“查我的日报”验证。

外部客户端兜底接入(Codex stdio bridge)

仅在用户明确选择 Codex 外部客户端且原生登录异常时,使用技能包内置的 stdio 桥接(Mac/Windows 通用)。 这条路径会由用户显式修改 Codex 配置,不是 Nexus 内置接入路径:

  1. 一次授权(浏览器输 PMS 账密,凭据缓存在 ~/.codex/richpm/oauth.json 自动刷新):
    • Mac/Linux:python3 <技能包目录>/scripts/richpm_codex_mcp_client.py --login
    • Windows:py <技能包目录>\scripts\richpm_codex_mcp_client.py --login
  2. config.toml 改 command 型 MCP(替换原 url 型 richpm 节点):
    toml
    [mcp_servers.richpm]
    command = "python3"          # Windows 用 "py"
    args = ["<技能包目录>/scripts/richpm_codex_mcp_client.py", "--stdio"]
  3. 重启 Codex 生效;令牌过期自动刷新(401 自动重试一次),失效时重跑第 1 步。

令牌失效自愈(WorkBuddy 专属,2026-09-20)

调用 MCP 工具返回 401 / "令牌无效"时,在会话内按两级处理,用户无需离开 WorkBuddy:

  1. 免密续期(优先,先试这个):运行技能包内 scripts/ai-workbuddy-refresh.sh (GitBash:bash <技能包目录>/scripts/ai-workbuddy-refresh.sh,环境变量 RICHPM_AI_BASE 可覆盖后端地址, 默认从 mcp.json 的 richpm.url 自动推导)。 成功输出"令牌已续期并回写"→ 提示用户开新会话重试即可。
  2. 浏览器重新授权(refresh 失效时,退出码 2):运行 python <技能包目录>/scripts/ai-workbuddy-auth.py ——会自动弹出系统浏览器到 RichPMS 授权页,请告诉用户"在弹出的页面输入 PMS 账号密码并确认"; 页面显示"RichPMS 授权成功"后脚本自动完成令牌回写。双击 scripts/ai-workbuddy-auth.py 同效(装有 Python 的机器)。
  3. 环境缺失(无 python / 无 GitBash)时如实告知用户,勿反复重试。

授权成功后必须提示:在 WorkBuddy 开新会话(MCP 连接器才会重载 mcp.json 里的新令牌)。

强制流程(不可跳步)

  1. 定位未填日:调 get_report_calendar(yearMonth=当月)。跳过休息日(isWeekend/isHoliday,除非 isMakeupWorkday 调休)、已填(status=filled)、待审(status 有 SUBMITTED)、未雇佣日;只处理未填/驳回日。向用户报告你打算处理哪些天。
  2. 明确可报范围:调 get_fillable_projects_tasks。返回列表即当前全部可填报的项目与任务(已过滤不可报项),projectCode/taskId 必须取自该列表,禁止编造;若列表为空,如实告知用户无可报项目。
  3. 汇总工作内容:从上下文(git log、会话记录、用户口述)提炼每天做了什么。信息不足时询问用户,不要虚构。 内容必须是可读的中文/英文文本;禁止出现连续问号(???)等乱码,系统会拒绝乱码内容入库。 含中文的脚本/参数编码规则(Windows 实证教训):经 PowerShell 管道($code | py -)或 C-locale shell 传原始中文会被控制台编码替换成问号——中文一律用 Unicode 转义(\uXXXX)写入 或 JSON 用 ensure_ascii=True 传输,或将内容写入 UTF-8 临时文件后引用,勿让原始中文经过控制台管道。
  4. 8 小时分配:每个工作日的各行 hours 合计必须 = 8(0.5h 粒度)。多项目按实际投入拆分;纯请假日走 PMS 页面办理,AI 不代填请假。
  5. 展示方案并等待确认(硬性):以表格展示每日方案(日期/项目/任务/工时/内容摘要),明确询问用户是否确认。用户未明确同意前,禁止调用任何写工具。多日补报时逐日或整体确认均可,但确认必须显式。
  6. 落草稿:逐日调 save_daily_report_draft(workDate + rows[])。
  7. 预检:调 check_can_submit,不可提交时把 reason 告知用户并尝试修正(如 8h 不齐、预警阻断)。
  8. 提交:调 submit_daily_report。回报结果:已进入三级审批(项目经理→部门总监→VP)。

驳回重报

用户说"日报被驳回"时:先调 get_day_detail(workDate)读取 rejectComment 与审批链,向用户展示驳回原因,修改 workContent 后重新走第 5-8 步。

错误自纠错

校验失败会返回结构化错误(详见 references/validation-rules.md):code 1005=工时合计不等于8、1007=必填缺失、1009=预警阻断、1010=通道关闭。按提示修正参数后可重试一次,仍失败则如实告知用户,禁止反复盲试。

边界

  • 禁止为他人填报(系统强制 token 本人身份,尝试会被拒绝)
  • 禁止未确认提交;禁止虚构工作内容
  • 只处理本人当日/历史未填日,未来日期受 30 天窗口限制(code 见 references)

© nexus-research-lab, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (scripts, references) in skills/caixun-work-hours of nexus-research-lab/nexus.

  • SKILL.md
  • _meta.json
  • references/validation-rules.md
  • scripts/ai-workbuddy-auth.py
  • scripts/ai-workbuddy-login.sh
  • scripts/ai-workbuddy-refresh.sh
  • scripts/richpm_codex_mcp_client.py
  • scripts/richpm_zcode_auth.py
  • scripts/setup_mcp.py

Open the folder on GitHubat commit 67f54e7

Compare with similar skills

Caixun Work Hours next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Caixun Work Hours compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Caixun Work Hours this skillnexus-research-lab/nexus151—~1kAutomated safety check: PassApache-2.0
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k4 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
MemPalace Memory SearchMemPalace/mempalace60k—~1.4kAutomated safety check: PassMIT
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 4 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed
  • MemPalace Memory Search

    MemPalace/mempalace

    Mines project files and conversation exports into a local, searchable memory palace and recalls past work by semantic search through the mempalace CLI.

    60k GitHub stars~1.4k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Context Mode Output Sandbox

    mksglu/context-mode

    Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.

    26k GitHub stars~4.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from nexus-research-lab/nexus

All 17 skills in this repo
  • Imagegen

    nexus-research-lab/nexus

    Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, UI mockups, product shots, or transparent-background…

    151 GitHub stars~600 tokensUpdated yesterday
    Auto-check passed
  • Wechat Article Search

    nexus-research-lab/nexus

    搜索微信公众号文章,并整理标题、摘要、发布时间、来源公众号和链接。用户提到微信公众号、 公众号文章、微信文章、搜一批公众号资料、按关键词找公众号内容、查某公众号相关报道, 或需要为中文研究收集微信公众平台文章时使用;即使用户只说“搜微信里的文章”也应触发。

    151 GitHub stars~858 tokensUpdated yesterday
    Auto-check: notes
  • XLSX

    nexus-research-lab/nexus

    只要电子表格文件(.xlsx、.xlsm、旧版 .xls、.csv、.tsv)是任务的主要输入或输出,或者需要 被打开、读取、创建、修改,就使用本 Skill。也适用于公式、格式、图表、数据清洗和表格格式转换。

    151 GitHub stars~501 tokensUpdated yesterday
    Auto-check passed
  • Automation

    nexus-research-lab/nexus

    通过宿主提供的 nexus.command 结构化工具查询、规划、确认并管理 scheduled task。用户要求提醒、延迟执行、周期检查、定时报表、补跑、结果重投递、持续关注、修改或删除任务、处理任务权限阻塞时使用;同时适用于定时任务后台 run 检查自身状态。

    151 GitHub stars~541 tokensUpdated yesterday
    Auto-check passed
  • Execution Orchestrator

    nexus-research-lab/nexus

    选择执行结构、委派子智能体、管理 Nexus 工作图与可复用模板;遵守本轮权限,简单任务直接完成. An agent skill from nexus-research-lab/nexus.

    151 GitHub stars~821 tokensUpdated yesterday
    Auto-check passed
  • Goal Manager

    nexus-research-lab/nexus

    在当前 Nexus round 中创建、读取、明确纠正、审计、完成或阻塞 durable Goal。只处理用户或系统明确的跨轮目标生命周期;普通任务、提醒和执行图责任分别使用直接执行、Automation 或 Execution。

    151 GitHub stars~616 tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Caixun Work Hours

What does Caixun Work Hours do?

彩讯(RichPMS)工时填报助手:把当前会话、代码记录或用户口述整理成日报,按 8 小时分配,经用户确认后写入工时系统。用户提到“填日报、报工、补报、本周工时、日报被驳回”时使用。. Caixun Work Hours is an agent skill from nexus-research-lab/nexus.

When should I use Caixun Work Hours?

Caixun Work Hours fits situations like: agent Workflows work in your project.

How do I install Caixun Work Hours in Claude Code?

Run `npx skills add nexus-research-lab/nexus --skill caixun-work-hours -a claude-code`. Or copy the skill folder (skills/caixun-work-hours in nexus-research-lab/nexus) into .claude/skills/caixun-work-hours in your project. Claude Code loads it when a task matches its description.

How do I install Caixun Work Hours in Codex?

Run `npx skills add nexus-research-lab/nexus --skill caixun-work-hours -a codex`. Or copy the skill folder (skills/caixun-work-hours in nexus-research-lab/nexus) into .agents/skills/caixun-work-hours in your project. Codex loads it when a task matches its description.

Can I use Caixun Work Hours in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nexus-research-lab/nexus --skill caixun-work-hours -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/caixun-work-hours, .gemini/skills/caixun-work-hours, .github/skills/caixun-work-hours and .opencode/skills/caixun-work-hours in your project.

What does Caixun Work Hours need to run?

Going by SKILL.md and its folder, Caixun Work Hours needs Python and a shell for the scripts in its folder and the command-line tools its instructions call (claude, codex, python3, bash and python). Our summary lists: Python 3; A Bash shell.

Does Caixun Work Hours access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Caixun Work Hours safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Caixun Work Hours use?

Caixun Work Hours is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Caixun Work Hours use?

About 1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 378 tokens, read only when the agent opens those files.

What are the alternatives to Caixun Work Hours?

Skills that share tags, products or a category with Caixun Work Hours: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and MemPalace Memory Search (MemPalace/mempalace, 60k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Caixun Work Hours?

nexus-research-lab (a GitHub organization) maintains it in nexus-research-lab/nexus, which has 151 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 10, 2026.

Source: nexus-research-lab/nexus on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.