← Back to Skills Marketplace
phernandez

Memory Ingest

by Paul Hernandez · GitHub ↗ · v0.1.0 · MIT-0
cross-platform ✓ Security Clean
219
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install memory-ingest
Description
Process unstructured external input (meeting transcripts, conversation logs, pasted documents) into structured Basic Memory entities. Extracts entities, sear...
Usage Guidance
This skill is coherent with its description: it will read whatever text you paste, preserve the raw content verbatim in a stored note, extract/link or propose new entities, and may perform brief public web lookups for context. Before installing or using it, consider: (1) privacy — sensitive information you paste will be stored verbatim in the agent's memory, (2) web lookups — the skill may query public sources for proposed entities (limited to 2–3 queries per entity), and (3) approval flows — the skill is written to ask your approval before creating new entities, so confirm proposals before they are stored. No system credentials or downloads are required. If you need tighter controls, ensure the platform's memory storage is encrypted/accessible only to authorized agents and disable or restrict external web research.
Capability Analysis
Type: OpenClaw Skill Name: memory-ingest Version: 0.1.0 The memory-ingest skill (SKILL.md) is a well-structured tool for converting unstructured text into organized knowledge entities. It follows a safe workflow that includes searching for existing data, performing optional web research, and explicitly requiring user approval before creating new notes via the write_note function. There are no signs of malicious intent, data exfiltration, or unauthorized execution; the instructions focus entirely on the stated purpose of knowledge management.
Capability Assessment
Purpose & Capability
Name and description (Memory Ingest) align with the SKILL.md: it parses pasted transcripts/documents, extracts entities, searches existing Basic Memory, proposes creations, and writes notes. No unrelated credentials, binaries, or install steps are requested.
Instruction Scope
Instructions are explicit and scoped to ingesting user-provided text, searching the agent's Basic Memory, optionally doing limited web research (2–3 queries per entity), and proposing creations for user approval. Two things for the user to note: (1) the skill preserves source content verbatim in stored notes (privacy-sensitive), and (2) the optional web research entails outbound queries to public sources — the SKILL.md limits this but does permit network lookups.
Install Mechanism
Instruction-only skill with no install spec and no code files; nothing is written to disk or downloaded by the skill itself. This is low-risk from an install perspective.
Credentials
No environment variables, credentials, or config paths are requested. The memory and search operations appear to rely on the platform's built-in memory APIs rather than external secrets, which matches the skill's purpose.
Persistence & Privilege
always is false (normal). The skill can be invoked by the agent (default behavior), which is expected for a user-invocable memory tool. It does not request permanent platform-wide privileges or modify other skills.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install memory-ingest
  3. After installation, invoke the skill by name or use /memory-ingest
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
memory-ingest v0.1.0 - Initial release of the memory-ingest skill. - Processes unstructured external input (e.g., meeting transcripts, conversation logs, pasted documents) into structured Basic Memory entities. - Extracts entities, searches for existing matches, proposes new entities for approval, and creates structured notes with observations and relations. - Captures action items and follows a step-by-step workflow for parsing, extraction, and note creation. - Supports verbatim source preservation alongside structured metadata and observations.
Metadata
Slug memory-ingest
Version 0.1.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Memory Ingest?

Process unstructured external input (meeting transcripts, conversation logs, pasted documents) into structured Basic Memory entities. Extracts entities, sear... It is an AI Agent Skill for Claude Code / OpenClaw, with 219 downloads so far.

How do I install Memory Ingest?

Run "/install memory-ingest" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Memory Ingest free?

Yes, Memory Ingest is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Memory Ingest support?

Memory Ingest is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Memory Ingest?

It is built and maintained by Paul Hernandez (@phernandez); the current version is v0.1.0.

💬 Comments