garden-memory
Skill14 starsChanged 3 months agoMITView on GitHub
Paste this into Grok Bot after a successful run: Save the process we just used as a skill called “Garden Memory”. A useful skill states the six fields from Skills and routines. A Bot (this one or another) is acting on stale preferences or invented standing facts, and the owner wants memory corrected without wiping the role. Corrections cite a source. You did not delete unrelated boundaries. Changing facts were not stored as memory — they were pointed at the…
In this repository49 other files it gives its agents.
- AGENTS.mdAGENTS.md
- convert/claude.mdCLAUDE.md
- docs/llms.txtllms.txt
- audit-subscriptionsSkill
- cited-researchSkill
- cloud-bill-noteSkill
- collate-feature-asksSkill
- coordinate-launchSkill
- daily-digestSkill
- defend-calendarSkill
- design-bot-templateSkill
- detect-docs-driftSkill
- diff-competitorsSkill
- draft-call-followupSkill
- draft-changelogSkill
- draft-issueSkill
- draft-newsletterSkill
- draft-security-answersSkill
- draft-sqlSkill
- draft-support-replySkill
- harden-repoSkill
- incident-timelineSkill
- install-teamSkill
- interrogate-assumptionsSkill
- investigate-perfSkill
- log-promisesSkill
- package-evidenceSkill
- plan-tripSkill
- prep-meetingSkill
- queue-socialSkill
- ramp-new-hireSkill
- rank-account-healthSkill
- recommend-media-reallocSkill
- reconcile-expensesSkill
- remix-contentSkill
- reproduce-bugSkill
- research-accountsSkill
- review-pr-riskSkill
- route-workSkill
- sanitize-shareSkill
- scout-x-threadsSkill
- source-talentSkill
- sweep-ciSkill
- triage-inboxSkill
- vendor-renewalsSkill
- watch-aeoSkill
- watch-brandSkill
- weekly-saas-financeSkill
- write-win-lossSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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
- Distinctive: line 25
Ask the owner to confirm. Then, only if they own this Bot, update the description.
- Distinctive: line 39
Do not edit another Bot's description without the owner asking.
≈ “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.
Files
Garden Memory
Paste this into Grok Bot after a successful run:
Save the process we just used as a skill called “Garden Memory”.
A useful skill states the six fields from Skills and routines.
1. When to use it
A Bot (this one or another) is acting on stale preferences or invented standing facts, and the owner wants memory corrected without wiping the role.
2. Required inputs and access
- The stale claim the Bot keeps using
- The source of truth that contradicts it
- Which Bot owns the memory
3. Sequence of work
- Quote the stale claim and the contradicting source.
- Propose the corrected standing fact in description-ready language.
- List anything that should be forgotten vs updated vs moved to a source system.
- Ask the owner to confirm. Then, only if they own this Bot, update the description.
4. How to validate the result
Corrections cite a source. You did not delete unrelated boundaries. Changing facts were not stored as memory — they were pointed at the source system.
5. What to return
Diff of proposed description changes and a "do not remember" list.
6. What requires approval
Do not edit another Bot's description without the owner asking. Do not scrape private conversations for gossip.
Type / in the composer to reference a saved skill. If it does not appear, open Settings → Plugins → Yours and enable it for this Bot.
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
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.

