Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Bwkyd/wps-skills --skill wps-ganttgit clone --depth 1 https://github.com/Bwkyd/wps-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bwkyd/wps-skills/wps-gantt)<a href="https://agentmods.dev/skills/bwkyd/wps-skills/wps-gantt"><img src="https://agentmods.dev/badge/skills/bwkyd/wps-skills/wps-gantt/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bwkyd/wps-skills/wps-gantt"><img src="https://agentmods.dev/badge/skills/bwkyd/wps-skills/wps-gantt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00084 | $0.01815 |
| Opus 5 | $0.00042 | $0.00907 |
| Sonnet 5 | $0.00017 | $0.00363 |
| Haiku 4.5 | $0.00008 | $0.00181 |
Grade A, and why
wps-gantt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
甘特图生成器
任务列表 → Excel甘特图。不用Project也能做项目排期。
When to Use
- 制作项目计划/排期表
- 需要可视化的时间线
- 项目进度跟踪
- 用户说"做个甘特图""项目排期表"
When NOT to Use
- 复杂项目管理 → 建议使用专业工具
- 普通表格 → 使用
wps-docx-writer
工作流程
Step 1: 确认任务信息
每个任务需要:
- 任务名称
- 开始日期
- 结束日期(或工期天数)
- 负责人(可选)
- 进度百分比(可选)
Step 2: 生成甘特图
from openpyxl import Workbook
from openpyxl.styles import (Font, Alignment, PatternFill,
Border, Side, numbers)
from openpyxl.utils import get_column_letter
from datetime import datetime, timedelta
import os
def create_gantt(tasks, output_path=None):
"""
tasks = [
{'name': '需求分析', 'start': '2026-04-01', 'end': '2026-04-07',
'owner': '张三', 'progress': 100},
{'name': '系统设计', 'start': '2026-04-08', 'end': '2026-04-14',
'owner': '李四', 'progress': 60},
...
]
"""
wb = Workbook()
ws = wb.active
ws.title = "项目甘特图"
# 计算日期范围
all_dates = []
for t in tasks:
all_dates.append(datetime.strptime(t['start'], '%Y-%m-%d'))
all_dates.append(datetime.strptime(t['end'], '%Y-%m-%d'))
min_date = min(all_dates)
max_date = max(all_dates)
total_days = (max_date - min_date).days + 1
# 样式
header_fill = PatternFill('solid', fgColor='2C3E50')
header_font = Font(name='微软雅黑', size=10, bold=True, color='FFFFFF')
bar_fill = PatternFill('solid', fgColor='3498DB')
done_fill = PatternFill('solid', fgColor='2ECC71')
milestone_fill = PatternFill('solid', fgColor='E74C3C')
today_fill = PatternFill('solid', fgColor='F39C12')
thin = Side(style='thin', color='D5D8DC')
border = Border(left=thin, right=thin, top=thin, bottom=thin)
# 左侧列标题
left_headers = ['序号', '任务名称', '负责人', '开始', '结束', '进度']
for col, h in enumerate(left_headers, 1):
cell = ws.cell(row=1, column=col, value=h)
cell.font = header_font
cell.fill = header_fill
cell.alignment = Alignment(horizontal='center')
# 列宽
ws.column_dimensions['A'].width = 5
ws.column_dimensions['B'].width = 20
ws.column_dimensions['C'].width = 8
ws.column_dimensions['D'].width = 11
ws.column_dimensions['E'].width = 11
ws.column_dimensions['F'].width = 7
# 日期列标题(每天一列或按周)
date_start_col = len(left_headers) + 1
use_weekly = total_days > 60
if use_weekly:
# 按周显示
week_start = min_date - timedelta(days=min_date.weekday())
col = date_start_col
while week_start <= max_date:
cell = ws.cell(row=1, column=col,
value=week_start.strftime('%m/%d'))
cell.font = Font(name='微软雅黑', size=8, color='FFFFFF')
cell.fill = header_fill
cell.alignment = Alignment(horizontal='center')
ws.column_dimensions[get_column_letter(col)].width = 5
week_start += timedelta(days=7)
col += 1
else:
for d in range(total_days):
date = min_date + timedelta(days=d)
col = date_start_col + d
cell = ws.cell(row=1, column=col, value=date.strftime('%m/%d'))
cell.font = Font(name='微软雅黑', size=7, color='FFFFFF')
cell.fill = header_fill
cell.alignment = Alignment(horizontal='center', text_rotation=90)
ws.column_dimensions[get_column_letter(col)].width = 3.5
# 任务行
body_font = Font(name='微软雅黑', size=10)
for row_idx, task in enumerate(tasks, 2):
ws.cell(row=row_idx, column=1, value=row_idx-1).font = body_font
ws.cell(row=row_idx, column=2, value=task['name']).font = body_font
ws.cell(row=row_idx, column=3,
value=task.get('owner', '')).font = body_font
ws.cell(row=row_idx, column=4, value=task['start']).font = body_font
ws.cell(row=row_idx, column=5, value=task['end']).font = body_font
progress = task.get('progress', 0)
ws.cell(row=row_idx, column=6,
value=f'{progress}%').font = body_font
# 画甘特条
start = datetime.strptime(task['start'], '%Y-%m-%d')
end = datetime.strptime(task['end'], '%Y-%m-%d')
if use_weekly:
week_start = min_date - timedelta(days=min_date.weekday())
s_col = date_start_col + (start - week_start).days // 7
e_col = date_start_col + (end - week_start).days // 7
else:
s_col = date_start_col + (start - min_date).days
e_col = date_start_col + (end - min_date).days
for c in range(s_col, e_col + 1):
cell = ws.cell(row=row_idx, column=c)
if progress == 100:
cell.fill = done_fill
else:
cell.fill = bar_fill
cell.border = border
ws.row_dimensions[1].height = 30
ws.freeze_panes = 'G2' # 冻结左侧列和标题行
if not output_path:
output_path = '项目甘特图.xlsx'
wb.save(output_path)
return os.path.abspath(output_path)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 199 lines · 84 tokens per session scan A b0ded7098c6f
wps-gantt is a skill published in the GitHub repository Bwkyd/wps-skills (7 stars, last pushed 4mo ago), licensed MIT. It adds 84 tokens to every session and 1,815 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
stylework-yunxiao-requirement-sync
A workflow for exporting selected requirements from Yunxiao, a project-management service, into a new sheet in an existing DingTalk online spreadsheet. It formats the result into a fixed set of columns and groups it by iteration.
doa-quotation
An Excel and Python worksheet generator for traditional project quotes or agile task plans. It reuses client and project templates found in the current workspace.
020101-contact-crm
Builds a contact-product-organization CRM using CSV files with UUID linking, phone validation, and auto-export to PDF and XLSX.
xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or…
xlsx
Create, edit, analyze, or convert Excel spreadsheets (.xlsx, .xlsm, .xltx) where the workbook file is the primary deliverable. Use for formulas, formatting, financial models, multi-sheet workbooks, and tabular cleanup exported to Excel. Also applies to .csv/.tsv when the user wants spreadsheet output. Do NOT use for…
document-generation
Generate Word (.docx), Excel (.xlsx) and PowerPoint (.pptx) documents and fill existing PDF forms, from real NetClaw data, with per-element provenance and no fabrication. Use when someone needs a deliverable rather than an answer — a change record to attach to a CR, an audit workbook for a compliance reviewer, a…