agentleFS
Sign inStart free
mahik504mahik504/orchestra-workflow/skills/orchestra-vault/SKILL.md

orchestra-vault

Skill1 starsChanged 19 days agoMITView on GitHub

Maintain the private Orchestra workspace and its memory. Jump one note. Lasting files only. Record real outcomes, never synthetic ones. No secrets.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Do not open the whole workspace.

    line 14
  2. Very specific:

    Never: write synthetic evaluations.

    line 37
  3. Distinctive:

    Do not file chat transcripts.

    line 39
  4. Distinctive:

    Prefer editing the existing note over creating a new one.

    line 44
  5. Distinctive:

    Delete junk the same turn you notice it.

    line 47
  6. Very specific:

    After a like, a hate, a finished task, or a genuinely useful find, append to Preferences.md in the same turn.

    line 52
  7. Very specific:

    When a session ends, append one dated line to projects/<slug>/lessons.md.

    line 54
  8. Very specific:

    If the human rewrites a draft and asks to keep the change, append one line to Preferences.md naming the concrete edit.

    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

Orchestra vault — 3.3.6

BRAIN = MEMORY. The workspace is where Orchestra remembers; it is not a second control plane.

Root: the private workspace created by kit/init-workspace, or the path named in WORKFLOW.md. Not this public repo.

Read

Do not open the whole workspace. routes.md → one file → the app repo. Catalog files only when asked to catalog.

Layout

PathWhat
projects/<slug>/One product. Starts with idea.md. Add design, spec, progress, review, ship-post only when they exist.
templates/Copy, then fill
memory/decisions.mdDated architecture and product decisions
memory/resource-memory.jsonReal resource outcomes only
Preferences.mdTaste, stack, how the human thinks
kit/Host adapters and sync scripts

What memory is for

Three layers:

  • Global — taste and stack in Preferences.md; dated yes/no in memory/decisions.md.
  • Project — one product's context in projects/<slug>/idea.md.
  • Session — distilled at the end. Discarded, not filed.

Record after a real job: which resource combination improved the result, what failed, what the human liked or hated, and why a route was chosen.

Never write synthetic evaluations. Generated or duplicated rows in resource-memory.json are not learning — they are noise that will mislead future routing. Only an executed job writes a row.

Do not file chat transcripts. Do not restate facts the repository already shows.

Write hygiene

  1. Will this matter in a month? If not, say it in chat and do not file it.
  2. Prefer editing the existing note over creating a new one.
  3. One idea per note, self-contained, headed so a later reader can split it.
  4. A map points; it does not duplicate.
  5. Delete junk the same turn you notice it.
  6. Secrets never here. Never commit MCP configs, .env, or tokens.

Learning

After a like, a hate, a finished task, or a genuinely useful find, append to Preferences.md in the same turn. Taste is allowed to change; prefer editing the existing bullet. Do not create a second taste file.

When a session ends, append one dated line to projects/<slug>/lessons.md. One line. What happened, and what to do next time. Do not paste the chat.

A new skill is a proposal, not an install. After the same lesson appears three times, and the human says yes, write skills/_proposed/<name>/SKILL.md from templates/custom-skill.md. Stop there. Do not copy it into skills/ and do not sync it. One job. A narrow description. A way to verify.

If the human rewrites a draft and asks to keep the change, append one line to Preferences.md naming the concrete edit. Do not rewrite old taste. Do not train a model.

Git

The workspace may have a private remote. This public template is a different repo. Do not flip a populated workspace public — its history contains personal files.

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