agentleFS
frankxaifrankxai/Starlight-Intelligence-System/skills/intelligence/pattern-recognition/SKILL.md

intelligence/pattern-recognition

Skill10 starsChanged 2 months agoMITView on GitHub

Use when analyzing recurring behaviors, identifying trends, or spotting anti-patterns across code, architecture, strategy, content, or behavior. Distinguishes patterns (good recurring solutions) from anti-patterns (recurring problems). Default skill for Starlight Sage and Starlight Sentinel.

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

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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 Sage, Starlight Sentinel

    line 15
  2. Distinctive:

    Document the pattern's characteristics

    line 29
  3. Distinctive:

    Check if current approach matches anti-pattern characteristics

    line 37
  4. Distinctive:

    If match: document the anti-pattern and its typical consequences

    line 38
  5. Distinctive:

    Vault: All vaults (patterns exist everywhere)

    line 53

≈ “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

Pattern Recognition

"What has happened before will happen again. Recognize the pattern, master the game."

When This Skill Activates

  • Analyzing recurring behaviors, identifying trends, spotting anti-patterns
  • Keywords: "pattern", "recurring", "similar", "trend", "anti-pattern"
  • Default for: Starlight Sage, Starlight Sentinel

What This Skill Does

Identifies recurring patterns across code, architecture, strategy, content, and behavior. Distinguishes between patterns (good recurring solutions) and anti-patterns (recurring problems).

Procedures

Procedure 1: Pattern Identification

  1. Observe the current situation
  2. Query vaults for similar past situations
  3. Identify structural similarities
  4. Name the pattern (use existing pattern names when applicable)
  5. Document the pattern's characteristics
  6. Assess confidence in pattern match (High/Medium/Low)
  7. Recommend action based on pattern

Procedure 2: Anti-Pattern Detection

  1. Identify symptoms of potential problems
  2. Query Technical Vault for known anti-patterns
  3. Check if current approach matches anti-pattern characteristics
  4. If match: document the anti-pattern and its typical consequences
  5. Provide the known solution/alternative
  6. Assess severity (Critical/High/Medium/Low)

Procedure 3: Trend Analysis

  1. Collect data points over time
  2. Identify direction (increasing, decreasing, stable, cyclical)
  3. Assess rate of change
  4. Project trajectory
  5. Identify inflection points
  6. Recommend action based on trend

Integration Points

  • Vault: All vaults (patterns exist everywhere)
  • Agents: Sage (teaching patterns), Sentinel (anti-patterns), All (pattern awareness)
  • Transmissions: Broadcast newly identified patterns

Quality Criteria

  • Is the pattern clearly named and described?
  • Is the confidence level appropriate?
  • Is the pattern actionable (not just interesting)?
  • Have anti-patterns been checked?

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.

Reviews can't be read right now.

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.