save-learning — Claude Code skill: what it does, how to install
save-learning turns a user's lasting preferences into project learnings. Use it when an agent should carry a rule from one session into the next.
MIT ★ 1,319 updated 2026-09-24
npx skills add caliber-ai-org/ai-setup --skill save-learning -a claude-codeWhat save-learning does
When a user asks the agent to retain a rule, the skill rewrites it as a concise, actionable note and assigns a category such as preference, convention, or anti-pattern. It presents that note for approval before making any change.
Once approved, the skill runs caliber learn add. Personal preferences use the --personal flag, and the skill stages CALIBER_LEARNINGS.md for a later commit. A one-off request should not become a lasting project rule, so the skill filters those out.
What it helps with
- carry a project convention into later sessions
- turn a stated preference into an actionable note
- stage the learnings file for a commit
Example prompts for the agent
- Remember this for the project: use
buninstead ofnpmfor packages. - Save this preference for future sessions: avoid
anyin TypeScript. - From now on, send feature commits to
next, notmaster.
How to install save-learning
1Skills CLI (Vercel)
npx skills add caliber-ai-org/ai-setup --skill save-learning -a claude-code2Manually: put the files in place
~/.claude/skills/save-learning/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/save-learning/
1Skills CLI (Vercel)
npx skills add caliber-ai-org/ai-setup --skill save-learning -a codex2Manually: put the files in place
.agents/skills/save-learning/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add caliber-ai-org/ai-setup --skill save-learning -a cursor2Manually: put the files in place
.cursor/skills/save-learning/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install caliber-ai-org/ai-setup .agents/skills/save-learning2Manually: put the files in place
.github/skills/save-learning/SKILL.md1Skills CLI (Vercel)
npx skills add caliber-ai-org/ai-setup --skill save-learning -a gemini-cli2Platform CLI
gemini skills install https://github.com/caliber-ai-org/ai-setup --path .agents/skills/save-learningManually: put the files in place
.devin/skills/save-learning/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about save-learning
How do I install save-learning in Claude Code?
Run npx skills add caliber-ai-org/ai-setup --skill save-learning -a claude-code. The skill file is located at ~/.claude/skills/save-learning/SKILL.md.
What does save-learning do?
It turns lasting user instructions into categorized notes, asks for approval, then saves approved notes with caliber learn add and stages CALIBER_LEARNINGS.md.
How are personal preferences saved?
The skill passes --personal to caliber learn add when the note is a personal preference rather than a project-level learning.
Source text
SKILL.md · MIT
---
name: save-learning
description: Saves user instructions as persistent learnings for future sessions. Use when the user says 'remember this', 'always do X', 'from now on', 'never do Y', or gives any instruction they want persisted across sessions. Proactively suggest when the user states a preference, convention, or rule they clearly want followed in the future.
---
# Save Learning
Save a user's instruction or preference as a persistent learning that
will be applied in all future sessions on this project.
## Instructions
1. Detect when the user gives an instruction to remember, such as:
- "remember this", "save this", "always do X", "never do Y"
- "from now on", "going forward", "in this project we..."
- Any stated convention, preference, or rule
2. Refine the instruction into a clean, actionable learning bullet with
an appropriate type prefix:
- `**[convention]**` — coding style, workflow, git conventions
- `**[pattern]**` — reusable code patterns
- `**[anti-pattern]**` — things to avoid
- `**[preference]**` — personal/team preferences
- `**[context]**` — project-specific context
3. Show the refined learning to the user and ask for confirmation
4. If confirmed, run:
```bash
caliber learn add "<refined learning>"
```
For personal preferences (not project-level), add `--personal`:
```bash
caliber learn add --personal "<refined learning>"
```
5. Stage the learnings file for the next commit:
```bash
git add CALIBER_LEARNINGS.md
```
## Examples
User: "when developing features, push to next branch not master, remember it"
-> Refine: `**[convention]** Push feature commits to the \`next\` branch, not \`master\``
-> "I'll save this as a project learning:
**[convention]** Push feature commits to the \`next\` branch, not \`master\`
Save for future sessions?"
-> If yes: run `caliber learn add "**[convention]** Push feature commits to the next branch, not master"`
-> Run `git add CALIBER_LEARNINGS.md`
User: "always use bun instead of npm"
-> Refine: `**[preference]** Use \`bun\` instead of \`npm\` for package management`
-> Confirm and save
User: "never use any in TypeScript, use unknown instead"
-> Refine: `**[convention]** Use \`unknown\` instead of \`any\` in TypeScript`
-> Confirm and save
## When NOT to trigger
- The user is giving a one-time instruction for the current task only
- The instruction is too vague to be actionable
- The user explicitly says "just for now" or "only this time"
© caliber-ai-org · MIT · caliber-ai-org/ai-setup