New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Forgetful Entity Modeling

by ScottRBK in ScottRBK/forgetful

Models people, organisations, devices, products and system components as entities in a Forgetful knowledge graph, then links memories and relationships to them.

MITAuto-check passedKnowledge Management

Install Forgetful Entity Modeling

skills CLI
$ npx skills add ScottRBK/forgetful --skill forgetful-entities -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ScottRBK/forgetful forgetful-entities --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ScottRBK/forgetful.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/forgetful-entities .claude/skills/forgetful-entities && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
forgetful-entities
GitHub stars
301
Token cost
~836 tokens
SKILL.md length
370 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Models people, organisations, devices, products and system components as entities in a Forgetful knowledge graph, then links memories and relationships to them.

  • Works in 4 steps: Apply the litmus, then dedupe → Create with a type → Link knowledge and projects as they accrue → …
  • A new person, device, product or system component keeps coming up in memories
  • SKILL.md covers Invoking operations, Step 1 — Apply the litmus,…, Step 2 — Create with a type and Step 3 — Link knowledge and…, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The skill applies one test: an entity is a noun you could point at, while knowledge about it stays a memory. Sarah Chen is an entity; the fact that she is good at debugging async issues is a memory linked to her. Before creating anything, the agent searches entities under likely names, which matches both name and aka, and it sets aka at creation so a later duplicate search under another name still finds the thing.

Entities are created with create_entity and a type: Organization, Individual, Team, Device, System or Other, with a custom type required for Other. The agent checks list_entities and reuses the types already in use so the graph stays consistent. Memories and projects are attached with link_entity_to_memory and link_entity_to_project, ideally at capture time, which makes get_entity_memories work as a reverse lookup. Relationships go through create_entity_relationship using a small vocabulary such as owns, depends_on, part_of, uses and created_by. Operations run through the Forgetful MCP tool or its CLI.

When your agent uses it

  • A new person, device, product or system component keeps coming up in memories
  • Recording that one thing owns, depends on or is part of another
  • Checking whether an entity already exists before adding a duplicate

Example prompts

  • “Add Acme Corp as an organization and link the notes about their API contract to it.”
  • “Record that the billing service depends on the payments database.”
  • “Check whether Sarah Chen is already an entity before creating her.”

Requirements

  • A Forgetful memory server reachable through MCP or the forgetful CLI
  • Pre-approved tools (allowed-tools): mcp__forgetful__discover_forgetful_tools, mcp__forgetful__how_to_use_forgetful_tool, mcp__forgetful__execute_forgetful_tool, Bash(forgetful:*)

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Apply the litmus, then dedupe
  2. Create with a type
  3. Link knowledge and projects as they accrue
  4. Record relationships between entities

What it can do on your machine

Read from SKILL.md and the folder at commit ff45893. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • mcp__forgetful__discover_forgetful_tools
    • mcp__forgetful__how_to_use_forgetful_tool
    • mcp__forgetful__execute_forgetful_tool
    • Bash(forgetful:*)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Forgetful Entity Modeling loads about 836 tokens when it runs. Until then it costs about 99 tokens; SKILL.md has 370 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~99
When it runs · the whole SKILL.md, loaded when a task matches
~836

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ScottRBK/forgetful at commit ff45893, republished under its MIT licence (© ScottRBK). 370 words, ~836 tokens.

Download SKILL.mdSave it as .claude/skills/forgetful-entities/SKILL.md (or your agent's skills folder).
name
forgetful-entities
description
Model the things knowledge attaches to — people, organisations, devices, products, system components. Use when a new thing surfaces that memories will reference, when relationships between things need recording (owns, depends on, part of), or when another skill routes a pointable thing here. Litmus: an entity is a noun you could point at; knowledge about it stays a memory.
allowed-tools
mcp__forgetful__discover_forgetful_tools, mcp__forgetful__how_to_use_forgetful_tool, mcp__forgetful__execute_forgetful_tool, Bash(forgetful:*)
license
MIT
tags
entities, knowledge-graph, relationships, modelling

Modelling entities in Forgetful

Entities are the graph's nouns. Model the thing once, then let knowledge accrue to it through links — that is what makes get_entity_memories a useful reverse lookup later.

Invoking operations

Operations are named by registry name (create_entity, link_entity_to_memory, ...). Invoke via whichever surface this agent has:

  • MCP: execute_forgetful_tool(tool_name="create_entity", arguments={...})
  • CLI: forgetful call create_entity --args '{"name": "..."}' --json

Get any operation's schema at runtime: how_to_use_forgetful_tool (MCP) or forgetful tools info <operation> (CLI) — schemas are deliberately not repeated here.

Step 1 — Apply the litmus, then dedupe

Can you point at it? "Sarah Chen" is an entity; "Sarah is great at debugging async issues" is a memory linked to her. The fact stays a memory (forgetful-remember); the thing it is about becomes the entity.

Before creating, search_entities for the thing under its likely names — it matches both name and aka. Set aka at creation time for any alternative names the thing goes by, so a later dedupe search under a different name still finds it.

Done when: the thing either already exists (use it) or is confirmed new.

Step 2 — Create with a type

create_entity with a name and type: Organization, Individual, Team, Device, System, or Other (custom_type required when Other). Stored Title-case; matched case-insensitively on input. Check list_entities for the types already in use and match them — a graph where servers are sometimes typed "Device" and sometimes "System" fragments reverse lookups.

Done when: the entity exists once, typed consistently with the existing graph.

Show full SKILL.md (128 more words)Show less
  • link_entity_to_memory whenever a memory is about the entity — done at capture time, this is one line; done later, it is an archaeology project.
  • link_entity_to_project when the entity belongs to a project's world.

Done when: knowledge about the thing is reachable from the thing (get_entity_memories).

Step 4 — Record relationships between entities

create_entity_relationship with a direction and a type. Keep the vocabulary small and consistent — owns, depends_on, part_of, uses, created_by cover most structure. Check get_entity_relationships on either entity first and reuse the types already in the graph before coining new ones. Direction carries meaning: A depends_on B is a statement about A.

Done when: the relationships that answer real questions (impact, structure, responsibility) are recorded, and none duplicate an existing edge.

© ScottRBK, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/forgetful-entities of ScottRBK/forgetful.

Open the folder on GitHubat commit ff45893

Compare with similar skills

Forgetful Entity Modeling next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Forgetful Entity Modeling compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Forgetful Entity Modeling this skillScottRBK/forgetful301—~836Automated safety check: PassMIT
MemPalace MemoryMemPalace/mempalace59k—~2.7kAutomated safety check: PassMIT
Ogham Maintainogham-mcp/ogham-mcp115—~1.1kAutomated safety check: PassMIT
Ogham Recallogham-mcp/ogham-mcp115—~1kAutomated safety check: PassMIT
Ontology1mancompany/OneManCompany4412 repos~1.5kAutomated safety check: PassApache-2.0
Cortexdb Memory Hermesliliang-cn/cortexdb274—~1.7kAutomated safety check: PassMIT

Similar skills

  • MemPalace Memory

    MemPalace/mempalace

    Gives an agent a local memory palace over MCP: verbatim conversation memory, semantic search and a temporal knowledge graph, with a per-session recall protocol.

    59k GitHub stars~2.7k tokensUpdated 2 days ago
    Knowledge ManagementAuto-check passed

  • Ogham Maintain

    ogham-mcp/ogham-mcp

    Admin and maintenance workflows for Ogham shared memory. An agent skill from ogham-mcp/ogham-mcp.

    115 GitHub stars~1.1k tokensUpdated 9 days ago
    Agent WorkflowsAuto-check passed

  • Ogham Recall

    ogham-mcp/ogham-mcp

    Smart retrieval from Ogham shared memory. An agent skill from ogham-mcp/ogham-mcp.

    115 GitHub stars~1k tokensUpdated 9 days ago
    Agent WorkflowsAuto-check passed

  • Ontology

    1mancompany/OneManCompany

    Typed knowledge graph for structured agent memory and composable skills.

    441 GitHub starsUsed in 2 repos~1.5k tokens
    Knowledge ManagementAuto-check passed

  • Cortexdb Memory Hermes

    liliang-cn/cortexdb

    Give a Python agent (such as Hermes Agent by Nous Research) durable, local-first memory plus a queryable SPARQL knowledge graph, backed by CortexDB through its gRPC sidecar and the cortexdb-client…

    274 GitHub stars~1.7k tokensUpdated yesterday
    Knowledge ManagementAuto-check passed

  • Cortexdb Memory Openclaw

    liliang-cn/cortexdb

    Give a Node.js agent (such as OpenClaw) durable, local-first memory plus a queryable SPARQL knowledge graph, backed by CortexDB through its gRPC sidecar and the cortexdb-client npm package.

    274 GitHub stars~1.6k tokensUpdated yesterday
    Knowledge ManagementAuto-check passed

More from ScottRBK/forgetful

All 10 skills in this repo

  • Forgetful CLI Setup

    ScottRBK/forgetful

    Installs and connects the Forgetful CLI in local or remote mode, sets up token auth for CI, and proves the setup with a real round-trip call.

    301 GitHub stars~898 tokensUpdated yesterday
    Auto-check: notes

  • Forgetful Remember

    ScottRBK/forgetful

    Decides where a piece of knowledge belongs in the Forgetful memory server, checks for existing entries first, then creates and links it without deleting anything.

    301 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed

  • Forgetful Repo Encoding

    ScottRBK/forgetful

    Encodes a repository into the Forgetful knowledge base as a project, entities, atomic memories and documents, so a second run updates instead of duplicating.

    301 GitHub stars~1k tokensUpdated yesterday
    Auto-check passed

  • Forgetful Knowledge Graph Explorer

    ScottRBK/forgetful

    Explores the Forgetful memory graph in phases, walking memories, entities and relationships to answer cross-project and entity-centred questions.

    301 GitHub stars~898 tokensUpdated yesterday
    Auto-check passed

  • Forgetful File Storage

    ScottRBK/forgetful

    Stores screenshots, PDFs, diagrams, fonts and other binary files in the Forgetful knowledge base, with a retrieval-friendly description and an attachment route.

    301 GitHub stars~618 tokensUpdated yesterday
    Auto-check passed

  • Forgetful MCP Client Setup

    ScottRBK/forgetful

    Connects an MCP client to the Forgetful memory server over stdio or HTTP, then confirms the link works with discovery and round-trip calls.

    301 GitHub stars~682 tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Forgetful Entity Modeling

What does Forgetful Entity Modeling do?

Models people, organisations, devices, products and system components as entities in a Forgetful knowledge graph, then links memories and relationships to them. The skill applies one test: an entity is a noun you could point at, while knowledge about it stays a memory. Sarah Chen is an entity; the fact that she is good at debugging async issues is a memory linked to her.

When should I use Forgetful Entity Modeling?

Forgetful Entity Modeling fits situations like: A new person, device, product or system component keeps coming up in memories; recording that one thing owns, depends on or is part of another; checking whether an entity already exists before adding a duplicate.

How do I install Forgetful Entity Modeling in Claude Code?

Run `npx skills add ScottRBK/forgetful --skill forgetful-entities -a claude-code`. Or copy the skill folder (skills/forgetful-entities in ScottRBK/forgetful) into .claude/skills/forgetful-entities in your project. Claude Code loads it when a task matches its description.

How do I install Forgetful Entity Modeling in Codex?

Run `npx skills add ScottRBK/forgetful --skill forgetful-entities -a codex`. Or copy the skill folder (skills/forgetful-entities in ScottRBK/forgetful) into .agents/skills/forgetful-entities in your project. Codex loads it when a task matches its description.

Can I use Forgetful Entity Modeling in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ScottRBK/forgetful --skill forgetful-entities -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/forgetful-entities, .gemini/skills/forgetful-entities, .github/skills/forgetful-entities and .opencode/skills/forgetful-entities in your project.

What does Forgetful Entity Modeling need to run?

SKILL.md names no scripts, command-line tools or credentials: Forgetful Entity Modeling is instructions for the agent only. Our summary lists: A Forgetful memory server reachable through MCP or the forgetful CLI. Its frontmatter pre-approves these tools: mcp__forgetful__discover_forgetful_tools, mcp__forgetful__how_to_use_forgetful_tool, mcp__forgetful__execute_forgetful_tool, Bash(forgetful:*).

Does Forgetful Entity Modeling access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Forgetful Entity Modeling safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Forgetful Entity Modeling use?

Forgetful Entity Modeling is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Forgetful Entity Modeling use?

About 836 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Forgetful Entity Modeling?

Skills that share tags, products or a category with Forgetful Entity Modeling: MemPalace Memory (MemPalace/mempalace, 59k stars), Ogham Maintain (ogham-mcp/ogham-mcp, 115 stars), Ogham Recall (ogham-mcp/ogham-mcp, 115 stars) and Ontology (1mancompany/OneManCompany, 441 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Forgetful Entity Modeling?

ScottRBK (a GitHub user) maintains it in ScottRBK/forgetful, which has 301 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 8, 2026.

Source: ScottRBK/forgetful on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.