agentleFS
Sign inStart free
frankxaifrankxai/Starlight-Intelligence-System/skills/memory/context-preservation/SKILL.md

memory/context-preservation

Skill10 starsChanged 2 months agoMITView on GitHub

Use when saving context for future sessions or session handoffs — captures decisions, progress, pending work, and relevant state into persistent storage that can be restored. Default skill for Starlight Orchestrator and Starlight Sage.

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

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    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 Sage

    line 15
  2. Distinctive:

    Update Operational Vault with current state

    line 31
  3. Distinctive:

    Read most recent Session Note

    line 35
  4. Distinctive:

    Read Operational Vault for current state

    line 36
  5. Distinctive:

    Check Transmission channels for updates since last session

    line 37
  6. Distinctive:

    Before context is lost, scan for extractable knowledge:

    line 45
  7. Distinctive:

    Ensure nothing valuable is ephemeral

    line 52
  8. Distinctive:

    Transmissions: Check for updates during restoration

    line 58

≈ “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 Preservation

"What you preserve today is what you can build on tomorrow."

When This Skill Activates

  • Saving context for future sessions, session handoffs
  • Keywords: "preserve", "save context", "handoff", "session end", "continue later"
  • Default for: Starlight Orchestrator, Starlight Sage

What This Skill Does

Ensures no valuable context is lost between sessions. Captures decisions, progress, pending work, and relevant state into persistent storage that can be restored.

Procedures

Procedure 1: Session State Capture

  1. Summarize what was accomplished this session
  2. List all decisions made (with reasoning)
  3. List all pending work (not yet started or incomplete)
  4. Capture current blockers or questions
  5. Note any important context that might not be obvious
  6. Store as Session Note in notes/active/
  7. Update Operational Vault with current state

Procedure 2: Context Restoration

  1. Read most recent Session Note
  2. Read Operational Vault for current state
  3. Check Transmission channels for updates since last session
  4. Reconstruct the working context
  5. Identify what has changed since last session
  6. Present restored context summary
  7. Confirm with user before proceeding

Procedure 3: Knowledge Extraction

  1. Before context is lost, scan for extractable knowledge:
    • Decisions worth remembering → Strategic Vault
    • Technical patterns discovered → Technical Vault
    • Creative insights generated → Creative Vault
    • Principles confirmed → Wisdom Vault
  2. Extract and store each piece of knowledge
  3. Link extracted entries to the session that produced them
  4. Ensure nothing valuable is ephemeral

Integration Points

  • Vault: Operational Vault (state), all vaults (extracted knowledge)
  • Notes: Session Notes (handoff records)
  • Transmissions: Check for updates during restoration
  • Context: Updates unified-context.md

Quality Criteria

  • Can the next session fully resume from preserved context?
  • Was all extractable knowledge captured?
  • Is the session summary concise but complete?
  • Are pending items clearly actionable?

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