remember

When the user invokes this skill, the agent reflects on the most important lessons learned recently and suggests adding a new rule to AGENTS.md to prevent the same issue from recurring. Use when the user explicitly invokes the remember skill.

469 stars

Best use case

remember is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

When the user invokes this skill, the agent reflects on the most important lessons learned recently and suggests adding a new rule to AGENTS.md to prevent the same issue from recurring. Use when the user explicitly invokes the remember skill.

Teams using remember should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/remember/SKILL.md --create-dirs "https://raw.githubusercontent.com/kovrichard/catalyst/main/.agents/skills/remember/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/remember/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How remember Compares

Feature / AgentrememberStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

When the user invokes this skill, the agent reflects on the most important lessons learned recently and suggests adding a new rule to AGENTS.md to prevent the same issue from recurring. Use when the user explicitly invokes the remember skill.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Remember

When this skill is invoked, the agent should:

1. **Reflect** on the current or recent conversation: what went wrong, what was corrected, or what requirement was clarified that the agent should follow from now on.

2. **Propose a new rule** for `AGENTS.md` that:
   - States the requirement or constraint clearly.
   - Is written so a future agent (or you in a new context) will avoid repeating the same mistake or omission.

3. **Suggest the exact change**: Provide the exact markdown to add to `AGENTS.md` (e.g. a new bullet under an existing section, or a new subsection). Place it where it fits best—e.g. under "Coding guidelines", "Code organization", or "Critical files"—and keep it concise.

4. **Do not edit AGENTS.md yourself** unless the user explicitly asks you to apply the change. By default, only suggest the rule and show the proposed text; let the user review and approve before adding it.

## Example

User: Invokes `/remember`

Agent: Determines that we always use the dao for DB access, never prisma in components.

Agent: Reflects that this was a recurring mistake; suggests adding under "Coding guidelines" in AGENTS.md:

```markdown
- Use DAO functions for all database access from routes and components; never import `prisma` in components or route handlers.
```

Then asks whether the user wants this applied to AGENTS.md.

Related Skills

optimize

469
from kovrichard/catalyst

Scans the repository for optimization opportunities — complexity, performance issues, large files, and maintainability problems — and fixes them one at a time with user confirmation. Use only when the user explicitly invokes this skill.

lint

469
from kovrichard/catalyst

Contains commands to lint, format, type check, test, and build the project. Use when the user explicitly invokes the lint skill.

remember

28865
from github/awesome-copilot

Transforms lessons learned into domain-organized memory instructions (global or workspace). Syntax: `/remember [>domain [scope]] lesson clue` where scope is `global` (default), `user`, `workspace`, or `ws`.

remember-interactive-programming

28865
from github/awesome-copilot

A micro-prompt that reminds the agent that it is an interactive programmer. Works great in Clojure when Copilot has access to the REPL (probably via Backseat Driver). Will work with any system that has a live REPL that the agent can use. Adapt the prompt with any specific reminders in your workflow and/or workspace.

remember

9958
from alirezarezvani/claude-skills

Explicitly save important knowledge to auto-memory with timestamp and context. Use when a discovery is too important to rely on auto-capture.

remember

3891
from openclaw/skills

Explicitly save important knowledge to auto-memory with timestamp and context. Use when a discovery is too important to rely on auto-capture.

remember-me

3891
from openclaw/skills

Remember-this trigger: memory updates + recall for preferences, goals, boundaries, prior work, decisions, dates, and todos. Use whenever user asks to remember, continue previous context, personalize behavior, or retrieve what was decided earlier.

remembering-conversations

1864
from LeoYeAI/openclaw-master-skills

Use when user asks 'how should I...' or 'what's the best approach...' after exploring code, OR when you've tried to solve something and are stuck, OR for unfamiliar workflows, OR when user references past work. Searches conversation history.

remember

1864
from LeoYeAI/openclaw-master-skills

Explicitly save important knowledge to auto-memory with timestamp and context. Use when a discovery is too important to rely on auto-capture.

remember

422
from vibeeval/vibecosystem

Store a learning, pattern, or decision in the memory system for future recall.

remembering-conversations

242
from aiskillstore/marketplace

Use when user asks 'how should I...' or 'what's the best approach...' after exploring code, OR when you've tried to solve something and are stuck, OR for unfamiliar workflows, OR when user references past work. Searches conversation history.

/remember

170
from Miosa-osa/canopy

> Capture observations, friction patterns, and learnings for future synthesis.