remember · langchain-ai — Claude Code skill: what it does, how to install
Reads back through the conversation and saves best practices and agreed rules to AGENTS.md or a new skill. Fires on phrases like "remember this" and "update memory".
MIT 236 installs ★ 31,501 updated 2026-10-25
npx skills add langchain-ai/deepagents --skill remember -a claude-codeWhat remember does
The skill goes over the current conversation and pulls out what is worth keeping. Best practices come first: approaches that worked, mistakes to avoid, the quality bar you set, and the reasoning behind a choice. Coding conventions, architecture decisions, workflows and your corrections of the agent's behavior get saved too.
Each item is sorted by type. Simple preferences and rules go into memory, either the global $DEEPAGENTS_HOME/agent/AGENTS.md or the project file .deepagents/AGENTS.md. A multi-step process becomes a new skill at $DEEPAGENTS_HOME/agent/skills/<skill-name>/SKILL.md, optionally with scripts/, references/ and assets/ folders. The agent writes files with edit_file or write_file and ends with a list of what went where.
It is built for deepagents-code, and the paths come from there. In another agent, an AGENTS.md at those locations may never get read.
What it helps with
- record why one approach was picked over another
- log a mistake as an anti-pattern so it does not come back
- turn a worked-out process, such as code review, into its own skill
- store code style conventions in the project's
.deepagents/AGENTS.md - pin down your corrections to the agent's behavior
Example prompts for the agent
- Remember this: save our architecture decision and its reasons to
.deepagents/AGENTS.md. - Save what we learned in this chat and turn the review process into a skill.
- Update memory with what we agreed on in this conversation.
How to install remember
1Skills CLI (Vercel)
npx skills add langchain-ai/deepagents --skill remember -a claude-code2Manually: put the files in place
~/.claude/skills/remember/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/remember/
1Skills CLI (Vercel)
npx skills add langchain-ai/deepagents --skill remember -a codex2Manually: put the files in place
.agents/skills/remember/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add langchain-ai/deepagents --skill remember -a cursor2Manually: put the files in place
.cursor/skills/remember/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install langchain-ai/deepagents libs/code/deepagents_code/built_in_skills/remember2Manually: put the files in place
.github/skills/remember/SKILL.md1Skills CLI (Vercel)
npx skills add langchain-ai/deepagents --skill remember -a gemini-cli2Platform CLI
gemini skills install https://github.com/langchain-ai/deepagents --path libs/code/deepagents_code/built_in_skills/rememberManually: put the files in place
.devin/skills/remember/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add langchain-ai/deepagents --skill remember -a opencodeClaude.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 remember
How do I install remember in Claude Code?
Run npx skills add langchain-ai/deepagents --skill remember -a claude-code. The skill file ends up at ~/.claude/skills/remember/SKILL.md.
What does remember do?
It reviews the conversation, picks out best practices, conventions and decisions, and writes them to AGENTS.md memory or packages them as a new skill. At the end it lists what was saved and where.
When does remember create a skill instead of editing AGENTS.md?
Preferences and simple rules, global or per project, go to AGENTS.md. A skill is created when the conversation produced a multi-step process or method worth repeating.
Source text
SKILL.md · MIT
--- name: remember description: "Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture learnings." license: MIT compatibility: designed for deepagents-code --- Review our conversation and capture valuable knowledge. Focus especially on **best practices** we discussed or discovered—these are the most important things to preserve. ## Step 1: Identify Best Practices and Key Learnings Scan the conversation for: ### Best Practices (highest priority) - **Patterns that worked well** - approaches, techniques, or solutions we found effective - **Anti-patterns to avoid** - mistakes, gotchas, or approaches that caused problems - **Quality standards** - criteria we established for good code, documentation, or processes - **Decision rationale** - why we chose one approach over another ### Other Valuable Knowledge - Coding conventions and style preferences - Project architecture decisions - Workflows and processes we developed - Tools, libraries, or techniques worth remembering - Feedback I gave about your behavior or outputs ## Step 2: Decide Where to Store Each Learning For each best practice or learning, choose the right destination: ### -> Memory (AGENTS.md) for preferences and guidelines Use memory when the knowledge is: - A preference or guideline (not a multi-step process) - Something to always keep in mind - A simple rule or pattern **Global** (`$DEEPAGENTS_HOME/agent/AGENTS.md`): Universal preferences across all projects **Project** (`.deepagents/AGENTS.md`): Project-specific conventions and decisions ### -> Skill for reusable workflows and methodologies **Create a skill when** we developed: - A multi-step process worth reusing - A methodology for a specific type of task - A workflow with best practices baked in - A procedure that should be followed consistently Skills are more powerful than memory entries because they can encode **how** to do something well, not just **what** to remember. ## Step 3: Create Skills for Significant Best Practices If we established best practices around a workflow or process, capture them in a skill. **Example:** If we discussed best practices for code review, create a `code-review` skill that encodes those practices into a reusable workflow. ### Skill Location `$DEEPAGENTS_HOME/agent/skills/<skill-name>/SKILL.md` ### Skill Structure ``` skill-name/ ├── SKILL.md (required - main instructions with best practices) ├── scripts/ (optional - executable code) ├── references/ (optional - detailed documentation) └── assets/ (optional - templates, examples) ``` ### SKILL.md Format ```markdown --- name: skill-name description: "What this skill does AND when to use it. Include triggers like 'when the user asks to X' or 'when working with Y'. This description determines when the skill activates." --- # Skill Name ## Overview Brief explanation of what this skill accomplishes. ## Best Practices Capture the key best practices upfront: - Best practice 1: explanation - Best practice 2: explanation ## Process Step-by-step instructions (imperative form): 1. First, do X 2. Then, do Y 3. Finally, do Z ## Common Pitfalls - Pitfall to avoid and why - Another anti-pattern we discovered ``` ### Key Principles 1. **Encode best practices prominently** - Put them near the top so they guide the entire workflow 2. **Concise is key** - Only include non-obvious knowledge. Every paragraph should justify its token cost. 3. **Clear triggers** - The description determines when the skill activates. Be specific. 4. **Imperative form** - Write as commands: "Create a file" not "You should create a file" 5. **Include anti-patterns** - What NOT to do is often as valuable as what to do ## Step 4: Update Memory for Simpler Learnings For preferences, guidelines, and simple rules that don't warrant a full skill: ```markdown ## Best Practices - When doing X, always Y because Z - Avoid A because it leads to B ``` Use `edit_file` to update existing files or `write_file` to create new ones. ## Step 5: Summarize Changes List what you captured and where you stored it: - Skills created (with key best practices encoded) - Memory entries added (with location)
© langchain-ai · MIT · langchain-ai/deepagents
Similar skills
All skills for Agent setup: memory, context, orchestration →remember by other authors comes first.