agentleFS
eugenezhangco-speceugenezhangco-spec/athena/.claude/skills/compile/SKILL.md

compile

Skill0 starsChanged 7 months agoMITView on GitHub

Reads all MemPalace drawers in a specific room (or all rooms), synthesizes them into a clean, authoritative summary page, and saves it to personal/compiled/[domain].md. This is the Karpathy-inspired "compiled knowledge" upgrade — instead of searching hundreds of memory fragments every time, Athena reads one synthesized brief. - Never invent information. Only compile what exists in MemPalace. - Flag low-confidence inferences explicitly: "(inferred, not directly stated)" - If two memories contradict, note the contradiction and timestamp both. Don't silently pick one.…

13 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use expert-reset, updates and 2 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • jtenniswoodSkill

    expert-reset

    Reimagine this repository from first principles using the current product and user experience as the target. Use when the user says "/expert-reset", asks how the project should be rebuilt if starting again, wants bold architecture or component-structure recommendations, or wants a research-only reset plan unconstrained by current implementation details.

    Also in 3 projects that use this

  • jtenniswoodSkill

    updates

    Summarize user-facing project updates from the last 7 days, ordered by importance and written as one-sentence "Feature: description" entries. Use when the user says "/updates", asks what changed recently, or wants a concise list of recent features, device support, fixes that users will notice, or other product value.

    Also in 3 projects that use this

  • MicrosoftSkill

    pr-review

    Verify the technical accuracy of a vscode-docs pull request against the VS Code source code in microsoft/vscode. Use when reviewing a docs PR for factual correctness: setting names, command IDs, default values, API shapes, keybindings, versioned availability, and described behavior.

    Also in 3 projects that use this

  • MicrosoftSkill

    release

    Use ONLY when the user explicitly asks to cut/publish a Huabu desktop release or tag a version. Performs an outward action — bumps the version in apps/desktop/package.json, commits + annotated-tags vX.Y.Z, and pushes the branch + tag. That tag push auto-builds the macOS/Windows installers and publishes a GitHub Release. Provides `status`, `bump`, `tag-push`, and a one-command `run` (bump → tag-push).

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Pick the domain: If the user specified one, use it.

    line 15
  2. Distinctive:

    Synthesize into sections: Write a clean markdown summary with:

    line 27
  3. Distinctive:

    Never invent information. Only compile what exists in MemPalace.

    line 53
  4. Distinctive:

    If two memories contradict, note the contradiction and timestamp both.

    line 55
  5. Distinctive:

    Keep it under 2000 words per domain.

    line 56
  6. Very specific:

    Write in third person about the user: "[Name] works at..." not "You work at..." Use the user's actual name from personal/me.md.

    line 57
  7. Very specific:

    Use the user's actual name from personal/me.md.

    line 58

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “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

Compile — Synthesize Memory into Domain Summaries

Trigger

  • "Catch me up on [topic]", "summarize what you know about my [career/health/etc]"
  • "Compile memories", "update summaries"
  • Auto-triggered during weekly review when 20+ new memories exist in any room
  • Auto-triggered when user asks a broad question about a life domain

What This Does

Reads all MemPalace drawers in a specific room (or all rooms), synthesizes them into a clean, authoritative summary page, and saves it to personal/compiled/[domain].md. This is the Karpathy-inspired "compiled knowledge" upgrade — instead of searching hundreds of memory fragments every time, Athena reads one synthesized brief.

Procedure

  1. Pick the domain. If the user specified one, use it. If auto-triggered, compile the room with the most new memories since the last compile.
  2. Pull all drawers from MemPalace.
    Use mempalace_search with the room name, pull up to 100 results.
    Also query the knowledge graph: mempalace_kg_query for all entities in this domain.
  3. Separate by source tag.
    • user_statement memories are ground truth. Lead with these.
    • system_inference memories are supporting context. Include but flag confidence.
  4. Synthesize into sections. Write a clean markdown summary with:
    • Current state — what's true right now
    • Key facts — undisputed, high-confidence information
    • Recent changes — what changed in the last 30 days
    • Open questions — things Athena isn't sure about
    • People involved — relevant KG entities and relationships
    • Timestamp at the top: Last compiled: YYYY-MM-DD
  5. Save to personal/compiled/[domain].md. Overwrite the previous version entirely. The old version is in git history if needed.
  6. Tell the user in one sentence what was compiled and any gaps found.

Domain Map

RoomCompiled FileWhat It Covers
careercareer.mdJobs, projects, professional milestones, skills, ambitions
healthhealth.mdPhysical health, fitness, mental health, habits, conditions
relationshipsrelationships.mdKey people, dynamics, recent interactions
goalsgoals.mdActive goals, progress, deadlines, abandoned goals
financesfinances.mdIncome, expenses, investments, runway, financial goals
identityidentity.mdValues, beliefs, origin story, personality traits
coachingcoaching.mdBehavioral patterns, growth areas, accountability history

Quality Rules

  • Never invent information. Only compile what exists in MemPalace.
  • Flag low-confidence inferences explicitly: "(inferred, not directly stated)"
  • If two memories contradict, note the contradiction and timestamp both. Don't silently pick one.
  • Keep it under 2000 words per domain. This is a brief, not an encyclopedia.
  • Write in third person about the user: "[Name] works at..." not "You work at..." Use the user's actual name from personal/me.md. This keeps the compiled page readable as a reference document.

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.