remember
Save and recall knowledge — discoveries, insights, references, preferences
Skill by belt-sh
Chalk Labs
Need help deploying remember?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/belt-sh-remember
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/remember
Tools it pre-approves 5
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Bash(beltknow*),knowledge*)
What's inside
- Skill name
remember- Description
- Save and recall knowledge — discoveries, insights, references, preferences
- License
- MIT
- Allowed tools
- Bash(belt, know, *),, Bash(belt, knowledge, *)
- Instructions
- 32 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves some shell commands
Files (1)
- SKILL.md
SKILL.md (first lines)
## Remember Save knowledge that someone with zero context can understand and act on 6 months from now. Don't save generic rules — save the specific incident, decision, or reference with enough detail to be useful. ### Quality bar Every entry MUST include: what specifically happened or was decided, where (repo/file/system/project), and why it matters (what breaks if ignored). If the content lacks a concrete noun (file, project, endpoint, command), add detail before saving. ### Structure by type - **observation** — what happened + where + why it matters + when discovered - **concept** — the mental model or architectural decision + what it implies for future work - **preference** — the rule + the reason behind it (past incident or strong opinion) - **reference** — what the resource is + where it lives + when to consult it ### Commands ```bash belt know upload <file.md> # save from file (supports frontmatter) belt know search "query" # search your knowledge base belt know list --limit 10 # list recent entries belt know get <id> # view an entry belt know delete <id> # remove an entry ``` ```bash echo "content" | belt know upload - --name "descriptive-name" --type observation --tags "area,topic" ``` **Types:** observation, concept, preference, reference
From belt-sh/skills, MIT.
More from belt-sh/skills
- 0.598score
agentify
belt-sh
Build and deploy a custom AI agent on belt — define purpose, model, tools, system prompt, and deploy as a reusable agent.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
appify
belt-sh
Build and deploy an inference.sh app from a conversation — scaffold, implement, test, deploy, and configure pricing.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
flowify
belt-sh
Build and deploy an inference.sh flow — chain multiple apps into a pipeline with wired inputs/outputs.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
skillify
belt-sh
Turn a working solution into a permanent, tested skill — extract pattern, interrogate for depth, create SKILL.md, publish to registry.
SkillAFreshness: A★ 2Claude Code +9 - 0.595score
belt
belt-sh
Use the belt CLI — run hundreds of AI apps, manage knowledge, search skills, connect MCP servers.
SkillAFreshness: A★ 2Claude Code +9 - 0.587score
apps
belt-sh
Search and run hundreds of AI apps — image generation, video, TTS, web search, LLMs
SkillAFreshness: A★ 2Claude Code +9 - 0.551score
suggest
belt-sh
Search skills, knowledge, and apps in one shot — find the best tool for any task
SkillBFreshness: B★ 2Claude Code +9 - 0.546score
skill
belt-sh
Search, use, install, and publish skills from the belt registry
SkillBFreshness: B★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 17, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/belt-sh/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from belt-sh
- 0.598score
agentify
belt-sh
Build and deploy a custom AI agent on belt — define purpose, model, tools, system prompt, and deploy as a reusable agent.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
appify
belt-sh
Build and deploy an inference.sh app from a conversation — scaffold, implement, test, deploy, and configure pricing.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
flowify
belt-sh
Build and deploy an inference.sh flow — chain multiple apps into a pipeline with wired inputs/outputs.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
skillify
belt-sh
Turn a working solution into a permanent, tested skill — extract pattern, interrogate for depth, create SKILL.md, publish to registry.
SkillAFreshness: A★ 2Claude Code +9 - 0.595score
belt
belt-sh
Use the belt CLI — run hundreds of AI apps, manage knowledge, search skills, connect MCP servers.
SkillAFreshness: A★ 2Claude Code +9 - 0.587score
apps
belt-sh
Search and run hundreds of AI apps — image generation, video, TTS, web search, LLMs
SkillAFreshness: A★ 2Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get remember running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
remember skill. Agent Mart. https://agentmart.dev/skills/belt-sh-remember (last updated 2026-10-24)