You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
description: Pre-built skills that teach AI agents how to use Basic Memory effectively.
4
4
---
5
5
6
-
Agent skills are markdown instruction files (`SKILL.md`) that teach AI coding agents best practices for using Basic Memory's MCP tools. Your agent already has access to the tools — skills teach it *when* and *how* to use them effectively, with examples and patterns for specific workflows.
7
-
The skills are open source and live in the basic-memory monorepo — browse the full collection in [`skills/`](https://github.com/basicmachines-co/basic-memory/tree/main/skills). (The former `basic-memory-skills` repository is now just a distribution target; development happens in the monorepo.)
6
+
Agent skills are ready-made instructions that help Claude and ChatGPT use Basic Memory well. They teach your assistant when to save something, how to organize it, and how to pick up where you left off.
8
7
9
8
::tip
10
-
Skills work with Claude Desktop, Claude Code, Cursor, Windsurf, and any agent that supports markdown-based skill files.
9
+
New to Basic Memory? Start with [**memory-onboarding**](#choose-a-skill). It guides you through setting up a useful knowledge system by asking a few questions and doing the technical work for you.
11
10
::
12
11
13
12
---
14
13
15
-
## Installation
14
+
## Install a skill in Claude or ChatGPT
16
15
17
-
### npx (Recommended)
16
+
### Add the skill to Claude
18
17
19
-
`npx` ships with Node.js — if you don't have it, [install Node.js](https://nodejs.org/en/download) first.
18
+
1.[Choose a skill](#choose-a-skill) from the list below.
19
+
2. Open **Customize → Skills** and click **+**.
20
+
3. Choose **Upload a skill** and select its `SKILL.md` file. For `memory-onboarding`, upload the packaged ZIP instead.
21
+
4. Turn the skill on.
20
22
21
-
Install all skills at once:
23
+
[See Claude's walkthrough with screenshots](https://support.claude.com/en/articles/12512180-getting-started-with-skills-on-claude-ai).
If your installed Skills CLI can't load `basicmachines-co/basic-memory/skills`, update the CLI or copy the `memory-*` directories manually (see below).
42
-
::
27
+
1.[Choose a skill](#choose-a-skill) from the list below.
28
+
2. Click your **profile icon → Skills**.
29
+
3. Choose **New skill → Upload from your computer** and select its `SKILL.md` file. For `memory-onboarding`, upload the packaged ZIP instead.
30
+
4. Wait for ChatGPT to finish scanning it.
43
31
44
-
### Claude Desktop
45
-
46
-
1. Open **Settings → Capabilities**
47
-
2. Enable **Code execution** and **Skills**
48
-
3. Upload the `SKILL.md` files from each skill folder
49
-
50
-
### Manual
51
-
52
-
Clone the repo and copy skill folders to your agent's skills directory:
For project-scoped skills, copy to `.claude/skills/` in your project root instead.
32
+
[See the ChatGPT skills walkthrough](https://help.openai.com/en/articles/20001066-skills-in-chatgpt).
60
33
61
34
---
62
35
63
-
## Using skills
64
-
65
-
You don't need special syntax — once installed, skills activate when your request matches what they teach. Asking "where did we leave off?" pulls in `memory-continue`; pasting a meeting transcript triggers `memory-ingest`.
66
-
67
-
When you want a specific behavior, name the skill in plain language:
68
-
69
-
```text
70
-
"Use the /memory-notes skill to write up what we just discussed."
71
-
"Use /memory-continue to pick up where we left off on the auth refactor."
72
-
"Run /memory-defrag on my knowledge base and tell me what you'd clean up."
73
-
"Use /memory-research to look into Model Context Protocol and save what you find."
74
-
```
75
-
76
-
In Claude Code and Codex, installed skills are also literal slash commands — typing `/memory-notes` on its own invokes it directly.
77
-
78
-
---
36
+
## Choose a skill
79
37
80
-
## Available Skills
38
+
Most skills are a single `SKILL.md` file that you can upload directly. **memory-onboarding** includes supporting reference files, so it uses a packaged ZIP.
|**memory-ingest**| Process transcripts, emails, and documents into structured notes |
95
-
|**memory-research**| Web research synthesized into knowledge entities |
96
-
|**memory-literary-analysis**| Analyze a complete literary work into a structured knowledge graph |
42
+
|[**memory-onboarding**](https://github.com/basicmachines-co/basic-memory/releases/download/skills-latest/memory-onboarding.zip)| Guided setup — interview, design, and build a complete knowledge system from scratch |
|[**memory-capture**](https://github.com/basicmachines-co/basic-memory/raw/refs/heads/main/skills/memory-capture/SKILL.md)| Capture the state of a working thread into a single coherent note |
45
+
|[**memory-continue**](https://github.com/basicmachines-co/basic-memory/raw/refs/heads/main/skills/memory-continue/SKILL.md)| Resume prior work by rebuilding context from the knowledge graph |
46
+
|[**memory-tasks**](https://github.com/basicmachines-co/basic-memory/raw/refs/heads/main/skills/memory-tasks/SKILL.md)| Structured task tracking that survives context compaction |
|[**memory-lifecycle**](https://github.com/basicmachines-co/basic-memory/raw/refs/heads/main/skills/memory-lifecycle/SKILL.md)| Status transitions through folder-based organization, archive-never-delete |
|[**memory-ingest**](https://github.com/basicmachines-co/basic-memory/raw/refs/heads/main/skills/memory-ingest/SKILL.md)| Process transcripts, emails, and documents into structured notes |
54
+
|[**memory-research**](https://github.com/basicmachines-co/basic-memory/raw/refs/heads/main/skills/memory-research/SKILL.md)| Web research synthesized into knowledge entities |
55
+
|[**memory-literary-analysis**](https://github.com/basicmachines-co/basic-memory/raw/refs/heads/main/skills/memory-literary-analysis/SKILL.md)| Analyze a complete literary work into a structured knowledge graph |
97
56
98
57
::note
99
-
Start with **memory-notes** — it covers foundational note-writing patterns that all other skills build on.
58
+
The skills are open source. You can read every `SKILL.md` file in the [Basic Memory skills collection](https://github.com/basicmachines-co/basic-memory/tree/main/skills).
100
59
::
101
60
102
-
### Core Skills
103
-
104
-
**memory-notes** — The foundation. Teaches proper note structure: frontmatter, semantic observation categories, relations with wiki-links, and memory:// URL usage. Install this first.
61
+
---
105
62
106
-
**memory-tasks** — Structured task tracking with typed Task notes. Tasks survive context compaction, making this essential for multi-step work that spans beyond a single context window.
63
+
## Install skills in a coding agent
107
64
108
-
**memory-schema** — Schema lifecycle management. Discovers unschemaed notes, infers schemas from existing content, creates and edits definitions, validates notes against schemas, and detects drift.
65
+
If you use Claude Code or Codex, install skills from the terminal with `npx`. It ships with Node.js; [install Node.js](https://nodejs.org/en/download) first if needed.
109
66
110
-
**memory-capture** — Captures the state of a working thread into a single coherent note — synthesizing where it landed, not an append-log. Re-captures rewrite the same note in place.
67
+
### Install with npx
111
68
112
-
**memory-continue** — Resumes prior work by rebuilding context from the knowledge graph — `build_context` via memory:// URLs, recent activity, and search. The "where were we?" skill.
**memory-reflect** — Inspired by sleep-time compute patterns. Reviews recent conversations, extracts insights, and consolidates them into your knowledge base. Works well as a scheduled daily or twice-daily routine.
75
+
Or install one skill:
117
76
118
-
**memory-defrag** — Memory defragmentation. Splits bloated files, merges duplicates, removes stale information, and restructures folder hierarchy. Run weekly or when your knowledge base feels disorganized.
**memory-lifecycle** — Entity lifecycle management. Manages status transitions through folder-based organization with an archive-never-delete philosophy — information is preserved through moves, not removal.
81
+
List the available skills:
121
82
122
-
**memory-curate** — Knowledge-graph curation. Finds orphan notes and suggests links, proposes typed relations, merges duplicates, audits tags and folders, and builds hub notes.
If the command cannot load `basicmachines-co/basic-memory/skills`, update the Skills CLI or install manually.
89
+
::
125
90
126
-
**memory-metadata-search** — Structured metadata search. Query notes by custom frontmatter fields using equality, range, array, and nested filters. Useful for finding notes by status, priority, or any custom YAML fields.
91
+
### Install manually
127
92
128
-
**memory-ingest** — Processes unstructured external input into structured entities. Parses meeting transcripts, conversation logs, and pasted documents into properly formatted Basic Memory notes.
93
+
Clone the repo and copy a skill folder into your agent's skills directory. This example installs `memory-notes` for Claude Code:
129
94
130
-
**memory-research** — Performs web research and synthesizes findings into Basic Memory entities. Use for researching companies, people, technologies, or any topic you want to capture in your knowledge base.
**memory-literary-analysis** — Analyzes a complete literary work into a structured knowledge graph — characters, themes, chapters, locations, symbols, and literary devices.
100
+
For a project-scoped Claude Code skill, copy it to `.claude/skills/` in your project root.
0 commit comments