Przejdź do treści
Biblioteka skilli
Dokumenty i biuro · Pisanie

report-generator

/report-generator

Generuje profesjonalne raporty z wykresami, tabelami i wizualizacjami: raporty PDF i HTML oparte na danych, tygodniowe raporty statusu, podsumowania zarządcze i cykliczne aktualizacje zespołu.

Repozytorium
skills ↗
Licencja
Apache-2.0
Ostatnia zmiana repozytorium
25.10.2026

Ocena i bezpieczeństwo

100/ 100Klasa: dobry
Format25 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść35 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena15 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
2
Skrypty
0
Komentarze HTML
0
Adresy URL w SKILL.md
0
Przestarzałość

Brak sygnałów. Repozytorium zmienione 25.10.2026, bez odwołań do wycofanych modeli i API.

Licencja

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

Co robi i kiedy

Generuje profesjonalne raporty z wykresami, tabelami i wizualizacjami: raporty PDF i HTML oparte na danych, tygodniowe raporty statusu, podsumowania zarządcze i cykliczne aktualizacje zespołu.

Oryginalny opis (EN)

Generate professional reports with charts, tables, visualizations, and structured narratives. Covers data-driven PDF/HTML reports, weekly status reports, executive summaries, and recurring team updates. Use when a user asks to create a report, generate a data report, build a dashboard report, write a weekly report, create a status update, or produce a team progress report.

Jak działa

  1. Overview
  2. Instructions
  3. Examples
  4. Guidelines
Sekcje z nagłówków SKILL.md, w oryginale · 179 linii, 900 słów
Podgląd SKILL.md
---
name: report-generator
description: >-
  Generate professional reports with charts, tables, visualizations, and
  structured narratives. Covers data-driven PDF/HTML reports, weekly status
  reports, executive summaries, and recurring team updates. Use when a user asks
  to create a report, generate a data report, build a dashboard report, write a
  weekly report, create a status update, or produce a team progress report.
license: Apache-2.0
compatibility: "Python 3 with pandas, matplotlib, jinja2 for data reports; WeasyPrint and the Pango system library for PDF output; no deps for status reports"
metadata:
  author: terminal-skills
  version: "1.2.0"
  category: data-ai
  tags: "reports, visualization, status-updates, charts, productivity"
---

# Report Generator

## Overview

Generate professional reports combining data visualizations, narrative text, and structured updates. Supports two modes: **data reports** (charts, tables, KPI cards from CSV/database sources as HTML or PDF) and **status reports** (weekly updates, team progress, executive summaries in Markdown).

## Instructions

### Data Reports

#### Step 1: Load and analyze data

```python
import pandas as pd
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
import base64
from io import BytesIO

df = pd.read_csv("data.csv")
metrics = {
    "total_revenue": df["revenue"].sum(),
    "avg_order_value": df["revenue"].mean(),
    "total_orders": len(df),
}
```

#### Step 2: Generate charts as base64 for embedding

```python
def fig_to_base64(fig):
    buf = BytesIO()
    fig.savefig(buf, format="png", dpi=150, bbox_inches="tight")
    buf.seek(0)
    return base64.b64encode(buf.read()).decode("utf-8")

fig, ax = plt.subplots(figsize=(10, 5))
monthly = df.groupby("month")["revenue"].sum()
monthly.plot(kind="line", marker="o", ax=ax, color="#2563eb")
ax.set_title("Monthly Revenue Trend")
chart_b64 = fig_to_base64(fig)
plt.close()
```

#### Step 3: Build HTML report with Jinja2

Use a template with metric cards, chart sections, and data tables. Embed charts as base64 so the report is a single self-contained file.

```python
from jinja2 import Environment, BaseLoader
from weasyprint import HTML

template = Environment(loader=BaseLoader()).from_string("""
<html><body>
<h1>Monthly Revenue</h1>
<div class="card">Total revenue: {{ "%.2f"|format(total_revenue) }}</div>
<img src="data:image/png;base64,{{ chart_b64 }}" style="width:100%">
</body></html>
""")
html = template.render(total_revenue=metrics["total_revenue"], chart_b64=chart_b64)
with open("revenue_report.html", "w") as f:
    f.write(html)
HTML(string=html).write_pdf("revenue_report.pdf")  # WeasyPrint 70.x; needs Pango installed
```

### Status Reports (Weekly/Team Updates)

#### Identify the audience

| Audience | Focus | Detail Level |
|----------|-------|-------------|
| Direct manager | Individual contributions, blockers | High detail |
| Director/VP | Team progress, risks, metrics | Medium detail |
| Executive/C-suite | Business impact, milestones, KPIs | High-level summary |
| Cross-functional | Dependencies, shared updates | Relevant items only |

#### Use the standard template

```markdown
# Weekly Report: [Team/Project Name]
**Week of:** [Start Date] - [End Date]

## Summary
[2-3 sentence overview. Main focus, notable wins or challenges.]

## Completed This Week
- **[Project]:** [What was done and why it matters]
- **[Bug fix]:** [What was resolved]

## In Progress
| Item | Owner | Status | ETA |
|------|-------|--------|-----|
| [Task] | [Person] | On track | [Date] |
| [Task] | [Person] | Blocked | - |

## Blockers & Risks
- **[Blocker]:** [Description and what is needed to unblock]

## Key Metrics
| Metric | This Week | Last Week | Trend |
|--------|-----------|-----------|-------|
| [Metric] | [Value] | [Value] | Up/Down/Flat |

## Next Week Plan
- [ ] [Priority 1]
- [ ] [Priority 2]
```

#### Content guidelines

- Lead with impact, not activity: "Reduced page load time by 40%" beats "Worked on performance"
- Quantify wherever possible (numbers, percentages, counts)
- Be honest about blockers — hiding problems does not make them go away
- Use consistent status labels: On Track, At Risk, Blocked, Complete
- Keep the full report under 1 page (~400-500 words)

## Examples

### Example 1: Weekly engineering status report

**User request:** "Write a weekly report from these notes: shipped auth v2, fixed 3 prod bugs, started dashboard redesign, waiting on API team for endpoints, velocity was 34 points"

**Output:**
```markdown
# Weekly Report: Platform Engineering
**Week of:** Jan 20 - Jan 24

## Summary
Strong delivery week. Shipped Auth v2 on schedule and resolved 3 production
issues. Dashboard redesign kicked off but partially blocked on API dependencies.

## Completed
- **Auth v2 launch:** Rolled out to 100% of users with MFA and session management
- **Production bugs (3):** Payment timeout, avatar upload crash, timezone display

## In Progress
| Item | Status | ETA |
|------|--------|-----|
| Dashboard redesign (frontend) | On track | Feb 7 |
| Dashboard API integration | Blocked | Pending API team |

## Blockers
- **API endpoints:** Waiting on API team for analytics endpoints. No ETA yet.

## Metrics
| Metric | This Week | Last Week | Trend |
|--------|-----------|-----------|-------|
| Sprint velocity | 34 pts | 28 pts | Up |
| Open bugs (P1/P2) | 2 | 5 | Down |
```

### Example 2: Data-driven sales report from CSV

**User request:** "Generate a weekly sales report from this CSV"

The agent loads the CSV, filters to the current week, computes KPIs (revenue, orders, AOV, top product), generates charts (daily revenue trend, top 10 products, channel breakdown), and builds a polished HTML report with metric cards, charts, and a transactions table.

### Example 3: Executive summary from multiple sources

**User request:** "Create an executive summary combining sales, support, and engagement data"

The agent loads three data sources, computes cross-functional metrics, generates comparison charts, writes narrative summaries per department, and outputs a PDF with overview dashboard, per-department sections, and recommendations.

## Guidelines

- Use `matplotlib.use('Agg')` to avoid display issues in headless environments
- Embed charts as base64 in HTML for self-contained reports
- Include data source, generation date, and reporting period on every data report
- Show both value and trend (vs prior period) for metric cards
- Use consistent color schemes across all charts in a report
- For PDF output, use WeasyPrint (needs the Pango system library) or headless Chrome
- Validate data before generating — flag missing or malformed data
- For status reports, always include blockers even if none ("No blockers this week")
- Status labels should be honest — marking "on track" when at risk erodes trust
- Consistency is key — use the same structure every week so readers know where to look
- Write for the audience: executives want outcomes, managers want details
Pliki w paczce (2)
  • SKILL.md 7 KB
  • _scores.json 2 KB

Wersje

RepozytoriumWynikLicencja
Ta strona · TerminalSkills/skills100Apache-2.0
aaron-he-zhu/aaron-marketing-skills100Apache-2.0
Navinspire-ia/navin100AGPL-3.0
jeremylongshore/tons-of-skills-marketplace100MIT
guia-matthieu/clawfu-skills100MIT
ellenfengyunjing/ecommerce-product-research-skills100MIT
iamwaqargulzar/Marketing-Agent-OS90Apache-2.0

Migawka bazy z 13.11.2026 · wersja paczki e1ac26132b73 (skrót SHA-256 całej paczki)

Pobrania w ostatnich 30 dniach: 1 · ranking

Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.

Podobne skille

  • 95weekly-report-writer
    Przygotowuje tygodniowe raporty i aktualizacje statusu z notatek, zgłoszeń i spotkań, bez ujawniania danych prywatnych.
  • 100office-weekly-report
    Pisze i przegląda tygodniowe raporty na podstawie materiałów, dziennika postępów, notatek ze spotkań i aktualizacji zespołu.
  • 100status-reporting
    Generuje raporty statusu programu dla interesariuszy: tygodniowe aktualizacje, podsumowania dla zarządu i przeglądy kamieni milowych.
  • 100stakeholder-update
    Tworzy ustrukturyzowane raporty statusu i podsumowania dla interesariuszy, od cotygodniowych aktualizacji po przeglądy kwartalne.
  • 100report-generation
    Generuje raporty (retrospektywy sprintu, podsumowania finansowe, dashboardy analityczne, postmortemy incydentów) z danych strukturalnych, z szablonami, wykresami i wieloma formatami wyjścia.
  • 90team-communications
    Pisze komunikację wewnętrzną firmy: aktualizacje 3P, newslettery, zbiory FAQ, raporty incydentów, aktualizacje dla kierownictwa i raporty statusu.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.