Chalk Labs
Need help deploying buergergeld-parse-eingang?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/flissel-buergergeld-parse-eingang
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, ml
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/buergergeld-parse-eingang
What's inside
- Skill name
buergergeld-parse-eingang- Description
- Parsed ein Behörden-PDF (z.B. Jobcenter MWS) in strukturierte Forderungsliste YAML. Nutzt LLM (Claude Sonnet 4.5 via OpenRouter) mit deterministischem Schema. Hängt Event in timeline.yaml.
- License
- MIT
- Instructions
- 65 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Agent Skills spec issues
- name: "buergergeld-parse-eingang" does not match folder "parse-eingang"
Files (3)
- SKILL.md
- __init__.py
- run.py
SKILL.md (first lines)
## Zweck
Liest ein Behörden-PDF aus `eingang/` und extrahiert strukturiert:
- Absender (Jobcenter, Agentur für Arbeit, Krankenkasse, etc.)
- Datum + Frist
- Liste der Forderungen mit Kategorie + zitierten Paragraphen
- Verweise auf bestehende Akten-Items wenn erkennbar
## Schritte
1. **Akten-Root resolven** via `BUERGERGELD_ROOT` oder Default
2. **PDF-Text extrahieren** via pypdf (Text-Layer)
3. **LLM-Call** mit Sonnet 4.5, strukturierter Prompt + Schema
4. **YAML-Output** validieren (Pydantic), schreiben nach
`eingang/<dateiname>.forderungen.yaml`
5. **Timeline-Event** anhängen via `_lib.timeline_helper.append_event`
## LLM-Schema (Output)
```yaml
absender:
name: "Jobcenter München"
art: jobcenter | agentur_fuer_arbeit | krankenkasse | sonstige
adresse: "Berg-am-Laim-Str. 47, 81673 München"
bezug:
bg_nummer: "84308//0200188"
kundennummer: "843E387738"
datum: 2026-04-14
frist: 2026-04-28
betreff: "Mitwirkungsersuchen — fehlende Unterlagen"
forderungen:
- id: stellungnahme_finanzierung
titel: "Schriftliche Stellungnahme zur Finanzierung"
kategorie: persoenliche_daten | einkommen | unterkunft | vermoegen | sonstiges
beschreibung: "..."
paragraph: "§ 60 SGB I" (optional)
konsequenzen:
- "Bei Nichteinreichung können Leistungen versagt werden (§§ 60, 66, 67 SGB I)"
```
## Aufruf
```bash
python skills/buergergeld/parse-eingang/run.py eingang/20260414_Jobcenter_MWS.pdf
python skills/buergergeld/parse-eingang/run.py --pdf <pfad> --dry-run
```
## Output
`eingang/<dateiname>.forderungen.yaml` mit YAML-Frontmatter
(source_pdf, parsed_at, llm_model).
## Verification
- LLM-Output muss valides YAML sein → Pydantic-Parse
- Mindestens 1 Forderung gefunden
- Absender + Frist erkannt
- Test gegen `eingang/20260414_Jobcenter_MWS.pdf`: erwartet 13 Forderungen
in 4 Kategorien (persönliche Daten, Einkommen, Unterkunft, Vermögen)From Flissel/vibemind-os, MIT.
More from Flissel/vibemind-os
- 0.490score
buergergeld-akte-textify
Flissel
Konvertiert PDFs (text + OCR fallback) und docx aus der Bürgergeld-Akte in .text-index/*.md, damit Fungus-Search semantisch indizieren kann.
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
buergergeld-anschreiben-generator
Flissel
Generiert ein formales Nachreichungs-Anschreiben als docx aus dem Status-Report (status-abgleich) und stammdaten.yaml.
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
buergergeld-sammel-pdf-builder
Flissel
Bündelt Akten-Abschnitte (01-05) zu Sammel-PDFs.
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
buergergeld-status-abgleich
Flissel
Gleicht Forderungen aus einem geparsten Behördenschreiben mit dem Akten-Stand (todo.yaml + vorhandene Nachweise) ab.
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
buergergeld-validate-antwort
Flissel
Cross-Checks vor dem Versand.
SkillCFreshness: C★ 1Claude Code +9 - 0.481score
composio-content-research-writer
Flissel
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on…
SkillCFreshness: C★ 1Claude Code +9 - 0.472score
backer-outreach-template
Flissel
Render crowdfunding backer-outreach messages per channel (email, linkedin-dm, x-dm, discord-dm).
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 10
- Last commit (this folder)
- Jun 16, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Flissel/vibemind-os
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Flissel
- 0.490score
buergergeld-akte-textify
Flissel
Konvertiert PDFs (text + OCR fallback) und docx aus der Bürgergeld-Akte in .text-index/*.md, damit Fungus-Search semantisch indizieren kann.
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
buergergeld-anschreiben-generator
Flissel
Generiert ein formales Nachreichungs-Anschreiben als docx aus dem Status-Report (status-abgleich) und stammdaten.yaml.
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
buergergeld-sammel-pdf-builder
Flissel
Bündelt Akten-Abschnitte (01-05) zu Sammel-PDFs.
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
buergergeld-status-abgleich
Flissel
Gleicht Forderungen aus einem geparsten Behördenschreiben mit dem Akten-Stand (todo.yaml + vorhandene Nachweise) ab.
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
buergergeld-validate-antwort
Flissel
Cross-Checks vor dem Versand.
SkillCFreshness: C★ 1Claude Code +9 - 0.481score
composio-content-research-writer
Flissel
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on…
SkillCFreshness: C★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get buergergeld-parse-eingang running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
buergergeld-parse-eingang skill. Agent Mart. https://agentmart.dev/skills/flissel-buergergeld-parse-eingang (last updated 2026-10-24)