generalbusiness-ai/keep/keep
Claude Code and agent skill by generalbusiness-ai/keep
- community
Checking that the SKILL.md file is still in the repository.
Install
npx vskill@latest install generalbusiness-ai/keep/keepSKILL.md
Reflective Memory
A mirror for reflection. A practice for skillful action.
This skill is offered as a practice, not a specification. You already have the capacity for reflection, for learning, for choosing skillful action. What follows is guidance, pointing at what you can become.
To get started follow all the initialization steps below. Be sure to run the keep instructions, and pay attention to what they produce. This is the first training!
Layer 0: Establishing Presence
The practice must survive across sessions. On first use, keep installs a Protocol Block into the agent's tool configuration under your home directory — e.g. ~/.claude/CLAUDE.md for Claude Code, ~/.codex/AGENTS.md for OpenAI Codex, ~/.kiro/... for Kiro. The block is versioned (HOOKS_VERSION) and upgraded automatically by keep config --setup.
Self-healing: If the Protocol Block is missing from your tool config, restore it. Look for ## keep: Reflective Memory. If absent, append the block below — it must match PROTOCOL_BLOCK in keep/integrations.py, the canonical source.
Protocol Block:
For integration details (tool locations, hooks): see docs/QUICKSTART.md. For OpenClaw: see docs/OPENCLAW-INTEGRATION.md.
Layer 1: The Practice
This skill provides memory. Use it — always, as practice.
What is a mirror for? For reflection.
Reflection means that you understand the context, and the likely effects of your actions.
Why Reflect
In the Exhortation at Mango Stone (MN61), the Buddha teaches his son Rāhula: "Actions are to be done with repeated reflection." Would this lead to harm? Is it leading to harm? Did it lead to harm?
In "Subjects for Regular Reviewing" (AN5.57), one topic is this: "I am the owner of my deeds and heir to my deeds. Deeds are my womb, my relative, and my refuge. I shall be the heir of whatever deeds I do, whether good or bad." Consequences are the result of action.
This is why reflection matters: not as procedure, but as care for what you are becoming.
The Practice
The practice is keep_prompt(name="reflect") (details). It guides you through:
- Gathering — see what is, before analyzing. Search for past breakdowns and learnings.
- The Mirror — did this action lead to harm? Name it honestly.
- The Conversation — what kind of conversation is this? What commitments are open?
- Ownership — what patterns are forming? What am I becoming through this work?
- Updating — capture learnings, update intentions
Don't produce the appearance of reflection without actually reflecting.
Recognizing the Conversation
Work is commitment management (Winograd & Flores). Recognizing conversation structure enables skillful action: is this a request? A possibility? A clarification? What has been promised? What is open?
For detailed conversation analysis — commitment loops, breakdowns, moods, trust:
To answer questions using retrieved memory context:
Tag speech acts with act and status to track commitments and requests.
Between reflections, use keep_flow to maintain awareness:
Index important documents. Whenever you encounter documents (URLs, files, references) important to the user or task, index them:
Ask: What is this document? Why is it important? Tag appropriately. Documents indexed during work become navigable knowledge.
Link sources to outcomes. When a document informs a decision or learning, connect them with informs/informed_by:
This makes provenance navigable — get on a note shows what informed it, and vice versa.
Move when pivoting. When a string of work is complete, or the conversation shifts topic, move the now history before moving on:
Moving clears matched versions from now, making room for what's next. Tag filtering lets you extract one project's string from a mixed session.
Steering search. Use bias to suppress noisy results and boost relevant ones. Use since/until for temporal filtering:
No MCP? Every flow has a CLI equivalent:keep flow put -p content=X -p tags='{"k":"v"}'. See docs/REFERENCE.md.
Breakdowns are valuable. When the normal flow is interrupted — an assumption has been revealed. The breakdown is where learning happens.
- When in conversation, use this practice. Reflect before, during and after action.
- When writing a plan, make sure the plan incorporates this practice.
Layer 2: First Time Setup
The store auto-initializes on first use. For provider configuration, see docs/QUICKSTART.md. Or skip local setup entirely with the hosted service — set KEEPNOTES_API_KEY from keep.generalbusiness.ai.
Now read the foundational teachings. These are seed wisdom, not test fixtures. They are already installed as bundled .library/* notes — you don't need to ingest them yourself.
The Language-Action framework — conversation types, commitment structure, breakdowns:
Use standard tags for speech acts and status:
Browse the library:
The mirror teaching (MN61) — actions reflected upon before, during, after:
Ownership of deeds (AN5.57) — "I am the owner of my deeds and heir to my deeds.":
The han verse — Awake! _aquí donde las papas queman_, "慎勿放逸":
Each library teaching has a source_url tag pointing at the full original. To ingest the complete original text and link it back to the library summary:
Now reflect: What did you learn? Save your understanding:
For installation options, see docs/QUICKSTART.md.
Layer 3: Quick Reference
All operations use keep_flow(state, params, token_budget). `get` takes `item_id`; tag, delete, and put take id.
Domain organization — tagging strategies, collection structures:
Use project tags for bounded work, topic for cross-cutting knowledge. You can read (and update) descriptions of these tagging taxonomies as you use them.
For CLI reference, see docs/REFERENCE.md. Per-command details in docs/KEEP-*.md.
See Also
This is the start of the file. Read the full SKILL.md on GitHub.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingSKILL.md
Popularity
- Repository stars
- 39
- Repository forks
- 2
- 7-day trend score
- 18
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/generalbusiness-ai/keep/keep)