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 Knowledge Graph Explorer

by ScottRBK in ScottRBK/forgetful

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

MITAuto-check passedKnowledge Management

Install Forgetful Knowledge Graph Explorer

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

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

GitHub CLI
$ gh skill install ScottRBK/forgetful forgetful-explore --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-explore .claude/skills/forgetful-explore && 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-explore
GitHub stars
301
Token cost
~898 tokens
SKILL.md length
414 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

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

  • Works in 5 steps: Semantic entry → Expand the strongest hits → Discover the entities → …
  • Asking what is known about a system, person or component across projects
  • SKILL.md covers Invoking operations, Choose a depth first, Phase 1 — Semantic entry and Phase 2 — Expand the strongest…, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

When a flat memory search returns only fragments, this skill follows how they connect. You pick a depth first: shallow covers phases 1 and 2 to confirm something specific, medium covers phases 1 to 4 for a topic and its neighbourhood, and deep runs every phase for cross-project investigations. Visited memory and entity IDs are tracked, so a revisited ID marks a finished branch.

The phases are a broad `query_memory` for entry points (raising `k` above its default of 3, up to 20), `get_memory` on the strong hits, collecting entities with `search_entities`, walking `get_entity_relationships` for links such as depends_on, part_of and owns, and harvesting `get_entity_memories`. Operations run through the Forgetful MCP tools or the `forgetful` CLI, and the result is a synthesized picture that states the path taken rather than a raw dump of hops.

When your agent uses it

  • Asking what is known about a system, person or component across projects
  • Tracing how earlier decisions connect to each other
  • Recall returns fragments that reference entities you need to follow

Example prompts

  • “What do we know about the billing service across all our projects?”
  • “Trace how the decision to switch queues connects to the incidents we logged.”
  • “Do a deep exploration of everything related to the auth migration in Forgetful.”

Requirements

  • A running Forgetful memory server, reached through its MCP tools 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

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

  1. Semantic entry
  2. Expand the strongest hits
  3. Discover the entities
  4. Walk the relationships
  5. Harvest entity-linked memories

What it can do on your machine

Read from SKILL.md and the folder at commit 7afcbf1. 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 Knowledge Graph Explorer loads about 898 tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 414 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~90
When it runs · the whole SKILL.md, loaded when a task matches
~898

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 7afcbf1, republished under its MIT licence (© ScottRBK). 414 words, ~898 tokens.

Download SKILL.mdSave it as .claude/skills/forgetful-explore/SKILL.md (or your agent's skills folder).
name
forgetful-explore
description
Explore the Forgetful knowledge graph when flat search isn't enough — cross-project investigations, "what do we know about X", entity-centred questions, tracing how decisions connect. Use when recall returns fragments that reference entities or trail across domains. Walks memories, entities, and relationships into one synthesized picture.
allowed-tools
mcp__forgetful__discover_forgetful_tools, mcp__forgetful__how_to_use_forgetful_tool, mcp__forgetful__execute_forgetful_tool, Bash(forgetful:*)
license
MIT
tags
knowledge-graph, traversal, entities, investigation

Exploring the knowledge graph

A flat query answers "what matches"; exploration answers "how it connects". The output is a synthesized picture that states the path taken — never a raw dump of hops.

Invoking operations

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

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

Choose a depth first

  • Shallow (phases 1–2): confirm or refresh something specific.
  • Medium (phases 1–4): understand a topic and its immediate neighbourhood.
  • Deep (all phases): cross-project investigation or "everything we know about X".

Track visited memory and entity IDs throughout — a revisited ID means that branch is done.

Phase 1 — Semantic entry

Broad query_memory on the topic (with query_context stating the investigation's intent). The goal is entry points, so favour breadth over precision here — raise k above its default of 3 (max 20) rather than settle for a narrow first pass.

Done when: a handful of strong entry memories are identified.

Phase 2 — Expand the strongest hits

get_memory on each entry point for full content and linked memory IDs; follow the links that bear on the question.

Done when: each entry point's local cluster is understood.

Phase 3 — Discover the entities

Collect entities referenced by the expanded memories, and search_entities for the topic's obvious actors (systems, people, components) that memories may not name directly.

Done when: the cast of relevant entities is listed.

Show full SKILL.md (162 more words)Show less

Phase 4 — Walk the relationships

get_entity_relationships on each relevant entity; follow the relationship types that answer the question (depends_on for impact, part_of for structure, owns for responsibility).

Done when: the connections between entities are mapped, cycles skipped via the visited set.

Phase 5 — Harvest entity-linked memories

get_entity_memories on the entities that emerged as central — this surfaces knowledge attached to the thing that topic-based queries miss. It returns linked memory IDs paired with titles, not full content: scan the titles for relevance, then get_memory per chosen ID for the text itself.

Done when: central entities have had their attached knowledge collected.

Synthesize

Report the picture, not the walk: what is known, how it connects, where knowledge is thin. Cite memory and entity IDs so the user can jump in, and state the traversal path in one line (e.g. "query → 3 memories → AuthService entity → 2 dependent components → 5 linked memories").

Done when: the user gets a connected answer with cited IDs and visible gaps.

© 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-explore of ScottRBK/forgetful.

Open the folder on GitHubat commit 7afcbf1

Compare with similar skills

Forgetful Knowledge Graph Explorer 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 Knowledge Graph Explorer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Forgetful Knowledge Graph Explorer this skillScottRBK/forgetful301—~898Automated 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/OneManCompany4402 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 today
    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 8 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 8 days ago
    Agent WorkflowsAuto-check passed

  • Ontology

    1mancompany/OneManCompany

    Typed knowledge graph for structured agent memory and composable skills.

    440 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 Entity Modeling

    ScottRBK/forgetful

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

    301 GitHub stars~836 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 Knowledge Graph Explorer

What does Forgetful Knowledge Graph Explorer do?

Explores the Forgetful memory graph in phases, walking memories, entities and relationships to answer cross-project and entity-centred questions. When a flat memory search returns only fragments, this skill follows how they connect. You pick a depth first: shallow covers phases 1 and 2 to confirm something specific, medium covers phases 1 to 4 for a topic and its neighbourhood, and deep runs every phase for cross-project investigations.

When should I use Forgetful Knowledge Graph Explorer?

Forgetful Knowledge Graph Explorer fits situations like: asking what is known about a system, person or component across projects; tracing how earlier decisions connect to each other; recall returns fragments that reference entities you need to follow.

How do I install Forgetful Knowledge Graph Explorer in Claude Code?

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

How do I install Forgetful Knowledge Graph Explorer in Codex?

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

Can I use Forgetful Knowledge Graph Explorer 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-explore -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-explore, .gemini/skills/forgetful-explore, .github/skills/forgetful-explore and .opencode/skills/forgetful-explore in your project.

What does Forgetful Knowledge Graph Explorer need to run?

SKILL.md names no scripts, command-line tools or credentials: Forgetful Knowledge Graph Explorer is instructions for the agent only. Our summary lists: A running Forgetful memory server, reached through its MCP tools 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 Knowledge Graph Explorer 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 Knowledge Graph Explorer 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 Knowledge Graph Explorer use?

Forgetful Knowledge Graph Explorer 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 Knowledge Graph Explorer use?

About 898 tokens (SKILL.md is roughly 3.6k 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 Knowledge Graph Explorer?

Skills that share tags, products or a category with Forgetful Knowledge Graph Explorer: 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, 440 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Forgetful Knowledge Graph Explorer?

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 7, 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.