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

82%

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

Quality

Content

83%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.

The content is highly actionable with concrete, executable code templates for every note type and a clear multi-step workflow including an approval checkpoint. It is efficient and well-structured, with only minor room to tighten repeated phrasing and add an explicit post-creation validation step.

Suggestions

Add an explicit validation step after Step 7 (e.g. re-search to confirm no duplicate entities were created) to strengthen the feedback loop for this batch-creation workflow.

Tighten the repeated 'Preserve source content verbatim' guidance so it appears once in the Guidelines rather than also inside template comments.

Consider externalizing the observation-categories table into a references file if the category list grows, keeping SKILL.md lean.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient — well-organized steps, tables, and code examples that assume Claude's competence — with only minor instances of explanation that could be trimmed (e.g. restating 'Preserve source content verbatim' in both prose and template comments).	4 / 5
Actionability	Provides copy-paste ready, executable write_note() calls with concrete titles, directories, tags, metadata, and content blocks covering meeting, document, person, organization, and concept cases, plus concrete search_notes() query examples.	5 / 5
Workflow Clarity	The 8-step sequence is clearly numbered and progresses parse → extract → search → present → create → extract actions, with an explicit approval checkpoint before entity creation; however batch note creation lacks an explicit verify/dedup feedback loop after the search step beyond the stated guideline.	4 / 5
Progressive Disclosure	Well-organized sections with a workflow overview and clearly signaled one-level-deep references to sibling skills (memory-research, memory-tasks, memory-notes search-before-create pattern); no bundle files exist, so all content is appropriately inline with minor opportunity to externalize the observation-category table.	4 / 5
	Total	17 / 20 Passed

Description

81%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.

The description is strong: it enumerates concrete, specific capabilities and uses natural trigger terms tied to unstructured external input. Its main gap is the absence of an explicit 'Use when...' clause, which weakens the 'when' half of completeness.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user pastes a meeting transcript, conversation log, document, or email thread and wants it turned into structured Basic Memory knowledge.'

Include a few more natural trigger synonyms such as 'notes', 'email threads', or 'raw text' to broaden keyword coverage.

Keep the third-person voice ('Processes', 'Extracts') which is already correct — no change needed.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Extracts entities, searches for existing matches, proposes new entities with approval, creates notes with observations and relations, and captures action items' — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Clearly answers 'what' with a detailed capability list, and the 'what' input types imply 'when' (unstructured external input), but there is no explicit 'Use when...' trigger clause stating when Claude should invoke it.	4 / 5
Trigger Term Quality	Includes natural phrases users would say ('meeting transcripts', 'conversation logs', 'pasted documents'), though it lacks common synonym variations like 'notes' or explicit file extensions; coverage is good with a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	The Basic Memory / entity-extraction niche is distinct with specific triggers (meeting transcripts, conversation logs), with only minor overlap risk against related memory skills like memory-research or memory-notes.	4 / 5
	Total	17 / 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: a5fb68e

Reviewed: 3 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.