agentleFS
Sign inStart free
frankxaifrankxai/Starlight-Intelligence-System/skills/orchestration/context-engineering/SKILL.md

orchestration/context-engineering

Skill10 starsChanged 2 months agoMITView on GitHub

Use when managing AI context quality, session handoffs, or context optimization — keeps context fresh, relevant, and within optimal token budgets across agents and the intelligence system. Default skill for Starlight Orchestrator 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

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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 Orchestrator, Starlight Prime

    line 15
  2. Distinctive:

    Create session handoff if fresh context needed

    line 32
  3. Distinctive:

    Verify assembled context is sufficient

    line 42
  4. Distinctive:

    Update Operational Vault with current state

    line 49
  5. Distinctive:

    Create continuation plan for next session

    line 50
  6. Distinctive:

    Ensure zero knowledge loss in handoff

    line 51

≈ “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

Context Engineering

"Context is the difference between noise and signal."

When This Skill Activates

  • Managing AI context quality, session handoffs, context optimization
  • Keywords: "context", "session", "continuity", "state", "handoff"
  • Default for: Starlight Orchestrator, Starlight Prime

What This Skill Does

Manages the quality, size, and relevance of context provided to agents and the intelligence system. Ensures context stays fresh, relevant, and within optimal token budgets. Absorbed from GSD/ACOS v4 context engineering patterns.

Procedures

Procedure 1: Context Quality Monitoring

  1. Assess current context fill percentage:
    • 0-30%: Peak performance zone
    • 30-50%: Good quality, watch for degradation
    • 50-70%: Degrading, consider splitting tasks
    • 70%+: Poor quality, MUST spawn fresh context
  2. Identify stale or irrelevant context
  3. Recommend context refresh if quality is degrading
  4. Create session handoff if fresh context needed

Procedure 2: Context Assembly

  1. Identify what context is needed for the current task
  2. Load from vaults: relevant decisions, patterns, state
  3. Load from notes: session continuity, recent learnings
  4. Load from transmissions: cross-system updates
  5. Prioritize by relevance (most relevant first)
  6. Trim to fit token budget
  7. Verify assembled context is sufficient

Procedure 3: Session Handoff

  1. Summarize current session state
  2. Capture all pending work and decisions
  3. Store in Session Note
  4. Update Operational Vault with current state
  5. Create continuation plan for next session
  6. Ensure zero knowledge loss in handoff

Integration Points

  • Vault: Operational Vault (session state), all vaults (context sources)
  • Notes: Session Notes (handoff records)
  • Agents: Orchestrator (primary), Prime (system-wide context)

Quality Criteria

  • Is context within optimal token budget?
  • Is irrelevant context removed?
  • Is session handoff complete (zero knowledge loss)?
  • Is the right context loaded for the task?

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