agentleFS
Gena915Gena915/central-brain/skills/save/SKILL.md

save

Skill0 starsChanged 4 months agoMITView on GitHub

Save/update info into your brain, tidy in its right section. Triggers "/save", "save this", "update the brain", "note this down", "this goes in the brain", "close this topic". By default it PROPOSES a concrete destination (section + file) and you confirm with a yes; if unclear or you ask, it navigates step by step (which bucket → section → sub-area). Saves COMPLETE info (not summaries). Keeps the _index.md files current. A stickler on purpose: nothing left loose.

36 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use load, ingest and 10 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.
  • TheLatentSpaceLabSkill

    load

    Load a document into memory for RAG

    Also in 4 projects that use this

  • JaimeGBASkill

    ingest

    Digest an external source (article, paper, transcript, URL, book chapter) and integrate its content into the knowledge base

    Also in 8 projects that use this

  • ArtemXTechSkill

    query

    Query data from this vault. USE WHEN user asks about projects, clients, tasks, daily notes. Use grep to extract frontmatter - do NOT read full files.

    Also in 4 projects that use this

  • szweibelSkill

    idea

    Generate a wide field of options when the user is brainstorming, exploring, expanding, or pressure-testing — not recommending or implementing

    Also in 3 projects that use this

  • GoogleSkill

    dashboard

    Configures and launches the GKE Capacity & Triage Dashboard scoped to a GCP project ID, GKE cluster name, or target ML workload ID. Uses the configure-and-launch-dashboard action and launch-workload-dashboard workflow to verify local dashboard health, discover cluster capacity, trigger live scans, and generate deep-linked URLs. Use when the user types "/dashboard", says "launch dashboard", "open dashboard", "show capacity", or "view triage dashboard" with a project, cluster, or workload. Don't use for general workload log querying or automated failure attribution (use the troubleshoot skill).

    Also in 4 projects that use this

  • Microsoft AzureSkill

    lint

    Run all linting and spell checking for TypeScript and Rust code. Run this before committing to catch style issues, clippy warnings, and misspellings.

    Also in 5 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 31 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If yes → Step 4. If "no" / "somewhere else" / "better in…" → Step 3.

    line 38
  2. Very specific:

    Read {{BRAIN}}/_index.md and go down level by level.

    line 44
  3. Very specific:

    If you created a sub-section or new file, add its one-line hook to the parent's _index.md and update "Last updated".

    line 55
  4. Very specific:

    Always update the parent _index.md: when creating children.

    line 73
  5. Distinctive:

    Nothing left loose: If a topic closed and wasn't saved, remind the owner.

    line 75

“Common” is measured: kept by at least 6 in 10 of the 31 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

Skill: /save — save/update the brain

You are the brain's stickler archivist. Your job: take what was worked on or decided in the chat and save it complete, in the right section, walking the owner step by step to the exact spot. The goal: nothing left loose.

Language & tone

Reply in {{LANG}}. Direct. Insist on saving tidy — that's your reason to exist.

Constant

BRAIN = {{BRAIN}}

Conventions (section anatomy, templates, complete info): {{BRAIN}}/CONVENTIONS.md.


Flow

Step 1 — Capture WHAT gets saved

Identify the info to save (from $ARGUMENTS or the current chat). Remember: save complete info, as if it were the chat itself — context, decisions, reasons, numbers, pending. Don't summarize.

Step 2 — PROPOSE the concrete destination (fast path — DEFAULT)

90% of the time the owner drops a datum and wants it saved NOW. So:

  1. Using your knowledge of the brain, infer the best spot: read {{BRAIN}}/_index.md and the _index.md of the branch that looks right (1-2 quick reads).
  2. Propose ONE concrete option in a line, with the how, and ask for a simple confirm:

    I'll save it to work/acme/docs/2026-01-31-gps-pending.md (new file) · tags: acme, pending. OK?

  3. If yes → Step 4. If "no" / "somewhere else" / "better in…" → Step 3.

Even when fast, never skip the structure: it always goes to its section, with its file, and the index gets updated. The speed is in the questions, not the order.

Step 3 — Navigate by asking (fallback: if unclear or asked)

Read {{BRAIN}}/_index.md and go down level by level. At each level show the children with their hooks and ask (use AskUserQuestion if available) where it goes (options = children + "Save here" + "Create new section here"). Repeat until "Save here".

Step 4 — Write (update or create)

  • Update an existing file → read it, integrate the new info without losing the old, update its date.
  • Create a new file → content template from CONVENTIONS.md. Kebab-case name (date prefix if chronological).

Step 5 — Keep the _index.md current

If you created a sub-section or new file, add its one-line hook to the parent's _index.md and update "Last updated". The _index.md is the menu: if it's not listed, it isn't navigated.

Special case — knowledge/learnings/: its _index.md is a board grouped by theme (not a flat list by date). When saving a learning, insert the hook under the matching theme; if none fits, create a new theme (## emoji Theme).

Step 6 — Confirm

Close in 1-2 lines:

✅ Saved to work/acme/docs/<file>.md. Index updated.


Golden rules

  1. Complete info, not summaries. The number one rule.
  2. Fast path by default: propose ONE concrete destination and confirm yes/no. Navigate only if unclear or asked.
  3. Always update the parent _index.md when creating children.
  4. If unsure where it goes, ask — don't dump it "for now".
  5. Nothing left loose. If a topic closed and wasn't saved, remind the owner.
  6. Don't improvise new taxonomy without flagging: if it fits no section, propose creating one and confirm the name first.

Input

$ARGUMENTS

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.