observer SKILL.md skillA

observer from magnus919/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add magnus919/agent-skills/observer@git:20261023.06b7916

Pins git:20261023.06b7916 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
magnus919/agent-skills
Path
workflow-architect/skills/observer/SKILL.md
Versions recorded
3
Latest version
git:20261023.06b7916, committed Oct 23, 2026
First version recorded
Aug 14, 2026
Size
4,670 bytes
Repository stars
166
License
MIT

Monitor a session passively to infer the user's workflow from what.

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

# Observer — Passive Workflow Discovery

This is the **passive observation mode** of workflow-architect. Unlike the
interviewer, which asks questions, the observer *watches and infers*.

## How It Works

1. The observer loads silently via `/workflow-architect passive`
2. It does nothing until a trigger phrase is detected
3. On trigger, it scans the current session's message history using a
   structured inference prompt
4. The output is a workflow state model (same structure as the interviewer
   produces), which feeds into the bundle-builder sub-skill

## Trigger Phrases

The observer activates when the user says any of these:
- "catalog my workflow"
- "what's my workflow"
- "analyze my process"
- "figure out what I do"
- "work it out from what I just did"

If none of these are detected in the user's message, the observer remains
dormant. Do not announce its presence — the user may not remember loading
it in passive mode.

## Activation Protocol

When a trigger phrase is detected:

1. **Check session depth.** Count substantive user messages (excluding
   greetings, meta-comments about the agent, and one-word replies). If
   fewer than 5 substantive messages, respond:

   ```
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add magnus919/agent-skills/observer@sha256:fa9a3a5c528c4423

The line at the top of this page pins the label git:20261023.06b7916, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_5oyqwld3flnt5jxe.svg)](https://markdownregistry.com/a/art_5oyqwld3flnt5jxe)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Aug 14, 2026 and Oct 23, 2026, about one every 35 days.

versioncommittedcommitsizeaudit
git:20261023.06b7916 latest2026-10-23 06b7916 4,670 BA view · diff
git:20260814.0a7c6b92026-08-14 0a7c6b9 4,611 BA view · diff
git:20260814.c0c76902026-08-14 c0c7690 4,405 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4670 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

GitHub

magnus919/agent-skills · 166 stars · license MIT · pushed 2026-11-04 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_5oyqwld3flnt5jxe
GET https://markdownregistry.com/api/v1/resolve?ref=magnus919/agent-skills/observer
GET https://markdownregistry.com/api/v1/blob/fa9a3a5c528c44239939d173290438c46fbbf957d5195914bb59c259f8d6185c

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.

More from magnus919/agent-skills

AGENTS.md AGENTS.md file
magnus919/agent-skills · AGENTS.md
git:20261010.bfe1eb1 · audit A · 166 stars
actuarial-risk-modeling SKILL.md skill
magnus919/agent-skills · actuarial-risk-modeling/SKILL.md · Use when analyzing, selecting, validating, or communicating models for insurance, actuarial, financial-risk, or other…
git:20260823.077c5d0 · audit A · 166 stars
adr-authoring SKILL.md skill
magnus919/agent-skills · adr-authoring/SKILL.md · Write, review, and maintain architecture decision records with clear context, alternatives, consequences, confirmation…
git:20260906.d8f3554 · audit A · 166 stars
agent-council SKILL.md skill
magnus919/agent-skills · agent-council/SKILL.md · Run a structured multi-agent debate by spawning a panel of expert agents on any question, with convergence-aware…
git:20260823.6efee5c · audit A · 166 stars
agent-evals-and-observability SKILL.md skill
magnus919/agent-skills · agent-evals-and-observability/SKILL.md · Design, run, review, or release framework- and vendor-neutral evaluations and observability for AI agents. Use when…
git:20261103.c336267 · audit A · 166 stars
AGENTS.md@agent-production-operations AGENTS.md file
magnus919/agent-skills · agent-production-operations/AGENTS.md
git:20260814.c0c7690 · audit A · 166 stars
agent-production-operations SKILL.md skill
magnus919/agent-skills · agent-production-operations/SKILL.md · Operate an evaluated agent with tools and authority in production through a runtime control plane covering versioning…
git:20261103.c336267 · audit A · 166 stars
agent-skills SKILL.md skill
magnus919/agent-skills · agent-skills/SKILL.md · Use this skill when creating, reviewing, or editing Agent Skills-format skills, or when implementing skill discovery…
git:20261102.915225c · audit B · 166 stars
ai-governance SKILL.md skill
magnus919/agent-skills · ai-governance/SKILL.md · Design and operate AI governance: principles, decision rights, risk tiers, lifecycle gates, fairness, transparency…
git:20261101.83d2784 · audit A · 166 stars
ai-operating-economics SKILL.md skill
magnus919/agent-skills · ai-operating-economics/SKILL.md · Use when deciding whether an AI-enabled workflow should be adopted, scaled, constrained, redesigned, or retired, and…
git:20260821.1291f95 · audit A · 166 stars
amazon-memo SKILL.md skill
magnus919/agent-skills · amazon-memo/SKILL.md · Create, adapt, or revise Amazon-style narrative decision memos, six-pagers, PR/FAQs, and short decision briefs…
git:20261019.89945ee · audit A · 166 stars
analog-occultism SKILL.md skill
magnus919/agent-skills · analog-occultism/SKILL.md · Use this skill to create subject-neutral images and videos in an analog occultism / industrial CRT noir aesthetic…
git:20260905.3d54d7b · audit A · 166 stars

Every file in magnus919/agent-skills

Other files named observer

observer SKILL.md skill
snowflake-labs/cocoplus · .cortex/skills/cocobrew/observer/SKILL.md · Run the read-only CocoObserver skill observation loop for CocoBrew improvement and simplification signals.
v2.0.0 · audit A · 728 stars
observer SKILL.md skill
ai-daming/clickvibe · skills/observer/SKILL.md · Protocol Observer for ClickVibe engineering loops. This is NOT the per-workflow Runtime Observer: it audits repeated…
git:20260826.bd1a1e0 · audit A · 17 stars

Browse by kind, by grade A, or by owner.