agentleFS
Sign inStart free
frankxaifrankxai/Starlight-Intelligence-System/skills/intelligence/systems-thinking/SKILL.md

intelligence/systems-thinking

Skill10 starsChanged 2 months agoMITView on GitHub

Use when reasoning about architecture, holistic analysis, feedback loops, or emergent behavior — sees components, connections, feedback loops, and emergent properties to prevent the tunnel vision of analyzing parts in isolation. Default skill for Starlight Architect and Starlight Prime.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Default for: Starlight Architect, Starlight Prime

    line 15
  2. Distinctive:

    Document system boundaries (what's inside vs.

    line 30
  3. Distinctive:

    Check for unintended consequences

    line 38
  4. Distinctive:

    Transmissions: All channels (ecosystem-wide implications)

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Systems Thinking

"Everything is connected. See the connections, see the truth."

When This Skill Activates

  • Architecture discussions, holistic analysis, understanding emergent behavior
  • Keywords: "system", "architecture", "holistic", "feedback", "emergent", "ecosystem"
  • Default for: Starlight Architect, Starlight Prime

What This Skill Does

Enables holistic analysis that sees components, connections, feedback loops, and emergent properties. Prevents the tunnel vision of looking at parts in isolation.

Procedures

Procedure 1: System Mapping

  1. Identify all components in the system
  2. Map connections between components (data, control, dependency)
  3. Identify feedback loops (reinforcing and balancing)
  4. Find leverage points (where small changes have big effects)
  5. Identify emergent properties (what the whole does that parts don't)
  6. Document system boundaries (what's inside vs. outside)

Procedure 2: Impact Analysis

  1. Identify the proposed change
  2. Trace first-order effects (direct impacts)
  3. Trace second-order effects (impacts of impacts)
  4. Trace third-order effects (if significant)
  5. Check for unintended consequences
  6. Identify affected feedback loops
  7. Assess net system impact

Procedure 3: Ecosystem View

  1. Map the FrankX ecosystem: Starlight, ACOS, Arcanea, AI-Ops
  2. Identify shared resources and dependencies
  3. Find integration points and gaps
  4. Assess ecosystem health (is it balanced? growing?)
  5. Identify opportunities for better connection
  6. Recommend ecosystem-level improvements

Integration Points

  • Vault: Technical Vault (system patterns), Wisdom Vault (system principles)
  • Agents: Architect (primary), Prime (ecosystem), All (system awareness)
  • Transmissions: All channels (ecosystem-wide implications)

Quality Criteria

  • Did you consider the whole system, not just the part being changed?
  • Are feedback loops identified?
  • Are second-order effects considered?
  • Is the ecosystem perspective included?

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free