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
- FabianoArthur/claude-code-kitchentheir own version, first seen Nov 8, 2026
- paulogabriel/beryltheir own version, first seen Nov 8, 2026
- matthewwong525/WongStacktheir own version, first seen Nov 8, 2026
- pche-broken-artist/forge-of-thoughttheir own version, first seen Nov 6, 2026
- egregore-labs/egregoretheir own version, first seen Nov 6, 2026
- vidit19sharma/neogentstheir own version, first seen Nov 1, 2026
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.
TheLatentSpaceLabSkillload
Load a document into memory for RAG
Also in 4 projects that use this
JaimeGBASkillingest
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
ArtemXTechSkillquery
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
szweibelSkillidea
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
GoogleSkilldashboard
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 AzureSkilllint
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
Other versions36 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 36
- AgriciDaniel/claude-obsidian★ 16ksame name
- egregore-labs/egregore★ 293same name
- romarayt/raytsystem-public-os★ 140same name
- thiagofinch/mega-brain★ 95same name
- sturlese/hippocampus★ 28same name
- endlessblink/master-plan★ 26same name
- pche-broken-artist/forge-of-thought★ 12same name
- CarbeneAI/Forge★ 9same name
- seongjaeryu/bindly-claude-code★ 8same name
- ARCASSystems/FounderOS★ 7same name
26 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- brain/AGENTS.mdAGENTS.md
- brain/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- brainSkill
- checkpointSkill
- continueSkill
- contractSkill
- gateSkill
- pmSkill
- researchSkill
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
- Distinctive: line 38
If yes → Step 4. If "no" / "somewhere else" / "better in…" → Step 3.
- Very specific: line 44
Read {{BRAIN}}/_index.md and go down level by level.
- Very specific: line 55
If you created a sub-section or new file, add its one-line hook to the parent's _index.md and update "Last updated".
- Very specific: line 73
Always update the parent
_index.md: when creating children. - Distinctive: line 75
Nothing left loose: If a topic closed and wasn't saved, remind the owner.
“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.
Files
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:
- Using your knowledge of the brain, infer the best spot: read
{{BRAIN}}/_index.mdand the_index.mdof the branch that looks right (1-2 quick reads). - 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? - 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
- Complete info, not summaries. The number one rule.
- Fast path by default: propose ONE concrete destination and confirm yes/no. Navigate only if unclear or asked.
- Always update the parent
_index.mdwhen creating children. - If unsure where it goes, ask — don't dump it "for now".
- Nothing left loose. If a topic closed and wasn't saved, remind the owner.
- Don't improvise new taxonomy without flagging: if it fits no section, propose creating one and confirm the name first.
Input
$ARGUMENTS
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.

