workflow-extract SKILL.md skillA
workflow-extract from ellmos-ai/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ellmos-ai/skills/workflow-extract@v1.1.0Pins v1.1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ellmos-ai/skills
- Path
skills/infrastructure/workflow-extract/SKILL.md- Versions recorded
- 4
- Latest version
- v1.1.0, committed Aug 23, 2026
- First version recorded
- Jul 29, 2026
- Size
- 10,732 bytes
- Repository stars
- 9
- License
- MIT
Baut aus einem Chatverlauf oder aus bestehenden Automatisierungs-Prompts (z. B. eines anderen Agenten-Systems) eine selbstlaufende, user-neutrale Workflow-Automatisierung: einen wiederkehrenden Prompt bzw. Automations-Skill für Cron/Schedule/Loop. Alias: automations-extractor. Nutze diesen Skill bei „mach daraus eine Automatisierung", „das soll regelmäßig/nächtlich laufen", „extrahiere Workflows aus diesen Chatverläufen/Automationen", „Automation aus dieser Session bauen", oder bei…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
<img src="banner.png" width="100%" alt="workflow-extract banner"> # Workflow-Extract — aus Chatverläufen und Fremd-Automationen Automatisierungen bauen ## Zweck Manche Abläufe gehören nicht in einen Skill, den man bei Bedarf lädt, sondern in eine **Automatisierung, die von allein läuft**: nächtliche Checks, rotierende Projekt-Prüfungen, periodische Pflege-Läufe. Dieser Skill extrahiert solche Workflows aus zwei Quellenarten — Chatverläufen (ein Ablauf wurde interaktiv entwickelt und soll künftig unbeaufsichtigt laufen) und bestehenden Automations-Prompts anderer Systeme (z. B. Codex-Automations, Scheduled Tasks, n8n-Flows) — und macht daraus user-neutrale, robuste Automatisierungs-Prompts oder -Skills. Der Unterschied zum interaktiven Ablauf: Eine Automatisierung hat **niemanden, der korrigiert**. Alles, was in der Session der User abgefangen hat, muss die Automatisierung selbst abfangen. Genau dafür gibt es die Bausteine in `automation-bausteine.md`. ## Ablauf ### 1. Quelle und Zielform klären | Quelle | typischer Fall | | --- | --- | | Aktuelle Session / Transkript | Ablauf wurde interaktiv entwickelt, soll periodisch weiterlaufen | …
Read the whole file at its exact version.
How to install
mdr add ellmos-ai/skills/workflow-extract@sha256:cbe4ff5879ea4348The line at the top of this page pins the label v1.1.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_qjtyqdvxocipzuyb)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Jul 29, 2026 and Aug 23, 2026, about one every 8 days. Its first recorded version is graded C and its latest A.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.1.0 latest | 2026-08-23 | f025c2c | 10,732 B | A | view · diff |
| v1.1.0 | 2026-08-15 | 4d89378 | 10,713 B | A | view · diff |
| git:20260730.08fbb89 | 2026-07-30 | 08fbb89 | 9,255 B | C | view · diff |
| git:20260729.6a2d333 | 2026-07-29 | 6a2d333 | 9,254 B | C | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (10732 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
ellmos-ai/skills · 9 stars · license MIT · pushed 2026-11-07 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_qjtyqdvxocipzuyb GET https://markdownregistry.com/api/v1/resolve?ref=ellmos-ai/skills/workflow-extract GET https://markdownregistry.com/api/v1/blob/cbe4ff5879ea4348b27573d76c7464270a88ce752959a7681bc20e2bf90bf8df
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.