skill-memory
Use skill-memory to download, view and edit agent skills in memory. TRIGGER by 'skill', 'memory', 'learn'.
Packaged view
This page reorganizes the original catalog entry around fit, installability, and workflow context first. The original raw source lives below.
Install command
npx @skill-hub/cli install memodb-io-skill-memory-skill-memory
Repository
Skill path: skills/skill-memory
Use skill-memory to download, view and edit agent skills in memory. TRIGGER by 'skill', 'memory', 'learn'.
Open repositoryBest for
Primary workflow: Ship Full Stack.
Technical facets: Full Stack.
Target audience: everyone.
License: Unknown.
Original source
Catalog source: SkillHub Club.
Repository owner: memodb-io.
This is still a mirrored public skill entry. Review the repository before installing into production workflows.
What it helps with
- Install skill-memory into Claude Code, Codex CLI, Gemini CLI, or OpenCode workflows
- Review https://github.com/memodb-io/skill-memory before adding skill-memory to shared team environments
- Use skill-memory for development workflows
Works across
Favorites: 0.
Sub-skills: 0.
Aggregator: No.
Original source / Raw SKILL.md
--- name: skill-memory description: Use skill-memory to download, view and edit agent skills in memory. TRIGGER by 'skill', 'memory', 'learn'. --- ## Setup - assume you have `skill-memory` cli, if not, run `npm install -g skill-memory` ## Navigation - View all [available commands](./available-commands.md) and learn how to use `skill-memory`. - If user asks you to learn experiences/skills, read [How to learn skills](./learn-skills.md) of the correct way to create or update skills in memory. --- ## Referenced Files > The following files are referenced in this skill and included for context. ### available-commands.md ```markdown ## Available Commands ### Add Skills to `skill-memory` #### Add skills from Github ```bash # download from github skill-memory remote list github.com@anthropic/skills skill-memory remote add github.com@anthropic/skills@xlsx --rename my-xlsx ``` #### Add skills from local ```bash # link from local disk skill-memory remote list localhost@/home/user/my-skill skill-memory remote add localhost@./my-skill@xlsx --rename my-xlsx ``` ### Skills in `skill-memory` #### Version control ```bash skill-memory undo # undo the last command skill-memory history # view command history ``` #### Manage skills ```bash skill-memory list skill-memory delete @xlsx skill-memory copy @xlsx my-xlsx # @xlsx and @my-xlsx skill-memory rename @xlsx my-xlsx # only @my-xlsx skill-memory init @my-fool-skill # create a hello-world SKILL.md ``` #### Use skills ```bash skill-memory view @xlsx/SKILL.md skill-memory download @xlsx/recalc.py /tmp/ skill-memory download @canvas-design/canvas-fonts ./public/fonts/ skill-memory download @xlsx/ ./ # download entire skill ``` #### Edit skills ```bash skill-memory upsert /tmp/better-recalc.py @my-xlsx/my_path/recalc.py -m "add multi-sheets support" skill-memory delete @my-xlsx/my_path/recalc.py # delete a file from a skill ``` ## Command Best Practices Skills are modular, self-contained packages that extend Agent's capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks — they transform Agent from a general-purpose agent into a specialized agent equipped with procedural knowledge that no model can fully possess. - always use `skill-memory list` to list all your skills in memory first. - always use `skill-memory view` to view `SKILL.md` first to understand a skill and its capabilities. - for executable/binary files, use `skill-memory download` to download it to a local path and use them. - when create a new skill, upsert your SKILL.md to it right after you run `skill-memory init` - when update a file of the skill, the correct way is to download it to a tmp path, use tools to edit it, then upsert them back with proper `-m` message. ``` ### learn-skills.md ```markdown # Evolve your skill memory overtime ## Update existing skills - use `skill-memory list` to find any skill you want to update, keep it precise and low-impact. - if not related skills, yet you do have valuable experiences to save, look at Create new skills section. ## Create new skills ### When to create a new skill? 1. **Domain knowledge is required** - The agent needs specialized information it wouldn't already know (APIs, internal conventions, proprietary formats) 2. **Consistent output format is critical** - You need outputs to follow a specific template or structure every time 3. **Workflow is repeatable** - You find yourself explaining the same multi-step process repeatedly 4. **Context is project-specific** - The knowledge applies to your team's standards, tools, or conventions **Don't create a skill when:** - The agent already knows how to do the task (common programming, general best practices) - It's a one-time task you won't repeat - The guidance is too generic to provide value beyond the agent's existing knowledge **Key principle:** The agent is already highly capable. Only create skills that add context it doesn't already have. Ask yourself: "Does this skill justify its token cost?" ### How to do it? - understand the knowledge, scripts and artifacts you like to save in memory. - use `skill-memory init <skill-name>` to create a new skill, then use `skill-memory upsert` command to upload the skill contents. - make sure you don't break the SKILL.md format. ```