👁️
AI EngineeringPython

Observer

by magnus919

Observer is an AI Engineering skill for Claude Code, published by magnus919 in agent-skills.

10 stars0 forkson magnus919/agent-skillsAdded 2026/07/18+67% in starsRepository updated 2026/07/18
agent-skillsagentskillsai-agentsautomationllm
Install in seconds
Install Observer
Copy Observer into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/magnus919/agent-skills/tree/main/bundles/workflow-architect/skills/observer ~/.claude/skills/observer

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/magnus919/agent-skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
bundles/workflow-architect/skills/observer/SKILL.md in magnus919/agent-skills
Installs to
~/.claude/skills/observer
Collection
One of 33 skills cataloged from this repository
Category
AI Engineering3670 skills

What Observer does

A passive observation sub-skill that scans session history to infer workflow patterns when triggered. It detects entry patterns, phases, branching, tools, pain points, and exit behavior, producing a structured workflow model for bundle generation.

Observer is cataloged under AI Engineering on DirSkills. Observer comes from a repository tagged agent-skills, agentskills, ai-agents, automation and llm.

Documentation

README

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"

This is the opening of the README. Read the full README on GitHub.

Commands Observer provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

  • /workflow-architect

Frequently asked about Observer

  • What else does magnus919 publish alongside Observer?

    Observer is one of 33 skills that DirSkills catalogs from magnus919/agent-skills, the repository it ships in. Its siblings there include ADR Authoring, API Design and Evolution and ARR CLI. Each one is a separate skill with its own page in this directory, installs the same way Observer does, and is maintained by magnus919 in that same repository. The rest of the collection is listed on the magnus919/agent-skills page.

  • How does Observer compare to other AI Engineering skills?

    Observer ranks #3666 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Observer against them. Open each page to compare what they document and how they install.

More from magnus919/agent-skills

Observer is one of 33 skills cataloged on DirSkills from magnus919/agent-skills.

See all 33 skills
📋
2026/07/18

ADR Authoring

Write, review, and maintain architecture decision records with clear context, alternatives, consequences, and lifecycle governance. Use when a consequential technical decision must remain understandable.
Writing
406
🔗
2026/07/18

API Design and Evolution

Design, document, review, and evolve consumer-facing APIs and event interfaces. Use when choosing REST, GraphQL, RPC, events, or webhooks; writing OpenAPI/AsyncAPI contracts; defining schemas, mutations, errors, idempotency, or planning API versioning, deprecation, and migration.
DevOps
406
🎬
2026/07/18

ARR CLI

CLI tool for managing Radarr (movies) and Sonarr (TV series) media libraries. Use for listing, adding, searching, checking queues, quality profiles, and more.
Automation
100
🏛️
2026/07/18

Agent Council

Spawn a panel of expert agents to debate any question using a structured protocol with convergence diagnostics. Use for high-stakes decisions requiring multi-perspective analysis.
AI Engineering
406
🔍
2026/07/18

Agent Evals and Observability

Design, run, review, or release framework- and vendor-neutral evaluations and observability for AI agents. Use when defining agent evals, datasets, graders, trajectory review, regression analysis, release gates, production traces, or privacy-aware telemetry.
Quality
406
🎛️
2026/08/11

Agent Production Operations

Provides a runtime control plane for safely deploying evaluated AI agents into production, managing versioning, staged rollouts, fallback, cost and latency budgets, tool health, human escalation, and disablement.
DevOps
406