/forgetful-files
File binary content into the knowledge base — screenshots, PDFs, diagrams, fonts, assets. Use when a binary artifact is worth keeping alongside knowledge, or when a stored procedure needs a bundled asset. The description is the entire search surface: say what the file shows and
$ npx -y skills add ScottRBK/forgetful --skill forgetful-files --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/forgetful-files
Context preview
The summary Claude sees to decide when to auto-load this skill.
File binary content into the knowledge base — screenshots, PDFs, diagrams, fonts, assets. Use when a binary artifact is worth keeping alongside knowledge, or when a stored procedure needs a bundled asset. The description is the entire search surface: say what the file shows and
SKILL.md
forgetful-files.SKILL.mdname: forgetful-files
description: >-
File binary content into the knowledge base — screenshots, PDFs, diagrams, fonts, assets.
Use when a binary artifact is worth keeping alongside knowledge, or when a stored
procedure needs a bundled asset. The description is the entire search surface: say what
the file shows and when to reach for it.
license: MIT
tags: [files, binary, assets, multi-modal]
allowed-tools:
- mcp__forgetful__discover_forgetful_tools
- mcp__forgetful__how_to_use_forgetful_tool
- mcp__forgetful__execute_forgetful_tool
- Bash(forgetful:*)
Filing binary content
Files carry what text cannot: the screenshot that shows the bug, the architecture diagram, the PDF spec, the font a design system needs. Mechanics are thin; the judgment is in the description and the attachment.
File operations are feature-flagged — when discovery doesn't list them, the server has `FILES_ENABLED` off.
Invoking operations
Operations are named by registry name (`create_file`, `list_files`, ...). Invoke via whichever surface this agent has:
- **MCP**: `execute_forgetful_tool(tool_name="create_file", arguments={...})`
- **CLI**: `forgetful call create_file --args '{"filename": "..."}' --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 — Store with a retrieval-grade description
`create_file` takes the content base64-encoded, with `filename`, `mime_type`, tags, and a description. The description is what future retrieval sees — write what the file shows and when someone would reach for it ("Auth service architecture diagram — component boundaries and token flow, current as of the v2 redesign"), never just restating the filename.
Done when: the file is stored and its description answers "what is this and when is it used" on its own.
Step 2 — Attach it
A file no path leads to is lost the moment this session ends. Two attachment routes exist:
- `project_id` (at create, or later via `update_file`) puts the file in a project's world.
- `link_skill_to_file` bundles it to a stored procedure as its asset (see
`forgetful-procedures`).
For knowledge that *discusses* the file, save a memory (`forgetful-remember`) that cites the file ID in its content, so recall surfaces the pointer.
Done when: at least one route reaches the file — its project, a linked procedure, or a citing memory.
Read more
name: forgetful-files description: >- File binary content into the knowledge base — screenshots, PDFs, diagrams, fonts, assets. Use when a binary artifact is worth keeping alongside knowledge, or when a stored procedure needs a bundled asset. The description is the entire search surface: say what the file shows and when to reach for it. license: MIT tags: [files, binary, assets, multi-modal] allowed-tools: - mcp__forgetful__discover_forgetful_tools - mcp__forgetful__how_to_use_forgetful_tool - mcp__forgetful__execute_forgetful_tool - Bash(forgetful:*)
Filing binary content
Files carry what text cannot: the screenshot that shows the bug, the architecture diagram, the PDF spec, the font a design system needs. Mechanics are thin; the judgment is in the description and the attachment.
File operations are feature-flagged — when discovery doesn't list them, the server has `FILES_ENABLED` off.
Invoking operations
Operations are named by registry name (`create_file`, `list_files`, ...). Invoke via whichever surface this agent has:
- **MCP**: `execute_forgetful_tool(tool_name="create_file", arguments={...})`
- **CLI**: `forgetful call create_file --args '{"filename": "..."}' --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 — Store with a retrieval-grade description
`create_file` takes the content base64-encoded, with `filename`, `mime_type`, tags, and a description. The description is what future retrieval sees — write what the file shows and when someone would reach for it ("Auth service architecture diagram — component boundaries and token flow, current as of the v2 redesign"), never just restating the filename.
Done when: the file is stored and its description answers "what is this and when is it used" on its own.
Step 2 — Attach it
A file no path leads to is lost the moment this session ends. Two attachment routes exist:
- `project_id` (at create, or later via `update_file`) puts the file in a project's world.
- `link_skill_to_file` bundles it to a stored procedure as its asset (see
`forgetful-procedures`).
For knowledge that *discusses* the file, save a memory (`forgetful-remember`) that cites the file ID in its content, so recall surfaces the pointer.
Done when: at least one route reaches the file — its project, a linked procedure, or a citing memory.
Forgetful is a storage and retrieval tool for AI Agents. Designed as a Model Context Protocol (MCP) server built using the FastMCP framework.
Repo: ScottRBK/forgetful
Other skills on forgetful.
- /forgetful-cli-setup
Set up the Forgetful CLI and connect from a terminal — install, local or remote mode, auth, and verification. Use when connecting a human or headless agent via shell, wiring CI with token auth, or operating a local server (serve, database selection, feature flags, re-embedding).
Open skill - /forgetful-context-gather
Gather deep context before planning or implementing — one pass that turns a task description into a cited context pack: relevant decisions, patterns, constraints, code pointers, procedures, and explicit gaps. Runs recall from several angles, explores the graph around the
Open skill - /forgetful-encode-repo
Encode a repository into the Forgetful knowledge base — bootstrap the project, its entities, memories, and documents from the codebase itself. Use when bringing a new repo under Forgetful or refreshing a stale encoding. Re-encoding is an update pass: query-before-create makes it
Open skill - /forgetful-entities
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
Open skill - /forgetful-explore
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
Open skill - /forgetful-mcp-setup
Set up an MCP client for Forgetful — wire Claude Code, Cursor, Copilot, Codex, Gemini, or OpenCode to the server and verify the connection behaves. Covers stdio vs HTTP transport, auth and scopes, the three meta-tools every client sees, and delegation to subagents.
Open skill

