memory-ingest

Process unstructured external input (meeting transcripts, conversation logs, pasted documents) into structured Basic Memory entities. Extracts entities, searches for existing matches, proposes new entities with approval, creates notes with observations and relations, and captures action items.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/memory-ingest/SKILL.md

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable multi-step workflow with concrete tool-call examples and an explicit approval gate before mutations. Its main weaknesses are inlining template material that belongs in reference files and the absence of any post-creation validation for the batch note-creation operations.

Suggestions

Move the Person/Organization/Concept note templates and the observation-categories table into a references/ file (e.g. references/templates.md) and link to it from Step 7, keeping SKILL.md as an overview.

Add a post-creation verification step, e.g. re-read created notes to confirm wiki-links resolve to the intended entities and no duplicates were created.

Trim the Guidelines section to only non-obvious guidance (approval, selectivity, hedging) since "preserve verbatim" and "search before creating" already appear in Steps 1 and 3.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows and mostly earns its tokens, but the Guidelines section repeats earlier step guidance ("Preserve source content verbatim", "Search before creating") and the three full entity templates carry bracketed placeholder filler that could be trimmed.	4 / 5
Actionability	Concrete write_note() calls with real parameters, multi-variation search_queries, and a copy-ready entity proposal format provide mostly executable guidance; minor gaps remain in that template note bodies contain bracketed pseudocode placeholders rather than complete content.	4 / 5
Workflow Clarity	Eight clearly numbered steps with an explicit approval checkpoint before any creation (Step 5) and Existing/Proposed classification give a clear sequence with most checkpoints present; the batch note-creation workflow lacks a post-creation verification step, keeping it below the score-5 anchor.	4 / 5
Progressive Disclosure	No bundle files exist and the entire ~305-line body — including three full entity templates and the observation-category table — is inlined in SKILL.md; section headers give it structure, but content that clearly belongs in separate reference files is inline, matching the score-3 anchor.	3 / 5
	Total	15 / 20 Passed

Description

71%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with excellent specificity and concrete action coverage, written in correct third-person voice. Its main weakness is the absence of any "Use when..." trigger guidance, which caps completeness and slightly weakens trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user pastes a meeting transcript, conversation log, or document, or asks to 'process these notes' or 'add this to Basic Memory'."

Include natural trigger synonyms such as "email threads", "knowledge extraction", and "process these notes" that users would actually say.

Tighten the opening to reduce overlap risk with sibling memory skills, e.g. lead with "Basic Memory" rather than the broad "unstructured external input".

Dimension	Reasoning	Score
Specificity	"Extracts entities, searches for existing matches, proposes new entities with approval, creates notes with observations and relations, and captures action items" lists multiple specific concrete actions covering the full pipeline comprehensively, matching the score-5 anchor exactly.	5 / 5
Completeness	It clearly answers "what" (process unstructured input into Basic Memory entities with a full action list) but has no "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	"meeting transcripts, conversation logs, pasted documents" are natural user phrases, but common variations users would say ("email threads", "process these notes", "add this to memory", "knowledge extraction") are missing, placing it just below comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	"structured Basic Memory entities" and "notes with observations and relations" establish a clear niche, but "unstructured external input (meeting transcripts, conversation logs, pasted documents)" is broad enough to overlap with sibling memory skills (capture/research/tasks).	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: basicmachines-co/basic-memory
Path: skills/memory-ingest/SKILL.md
Commit: 194afe1

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.