memory-capture

Capture the current state of a working thread or conversation into a single coherent Basic Memory note — synthesize where it landed, don't append a log. On re-capture, rewrite the same note in place instead of duplicating. Use mid-thread or end-of-thread when decisions, insights, or context are worth preserving.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%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 body is highly actionable with executable tool calls and concrete worked examples, and is well-structured for a self-contained skill. The main improvement is trimming the repeated 'synthesize, don't append' messaging and making the overwrite validation checkpoint explicit.

Suggestions

Consolidate the 'synthesize, don't append' guidance so it appears once authoritatively (e.g., in Synthesis Rules) rather than being restated in Purpose and the Example 2 'Notice that' block.

Add an explicit validation checkpoint before the destructive overwrite (e.g., 'Confirm the matched note is the same thread before calling write_note with overwrite=True') to strengthen the feedback loop.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (executable tool calls, no basic-concept padding), but the 'synthesize, don't append' idea is restated across Purpose, Synthesis Rules, and the post-example 'Notice that' block, which could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready search_notes/read_note/write_note calls with concrete parameters plus two full before/after worked examples covering the common create and update cases.	5 / 5
Workflow Clarity	Decision Flow gives a clear numbered sequence with match/no-match branches and gates the destructive overwrite behind a prior same-thread lookup, but the validate-then-act loop is implicit (read existing note before overwrite) rather than an explicit validation checkpoint.	4 / 5
Progressive Disclosure	A self-contained skill with no bundle files; all content lives in one well-organized file with clear section headers, which is the appropriate structure for this scope.	5 / 5
	Total	18 / 20 Passed

Description

87%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 and explicit, clearly stating both the capability and when to invoke it with concrete, natural trigger phrases. It is concise, third-person, and distinguishes the skill well from generic note-taking.

Dimension	Reasoning	Score
Specificity	Names the domain (Basic Memory note) and several concrete actions — 'synthesize where it landed', 'rewrite the same note in place', 'don't append a log' — with only minor coverage gaps, fitting the 'several specific actions' anchor.	4 / 5
Completeness	Explicitly answers both what ('Capture the current state... into a single coherent Basic Memory note') and when ('Use mid-thread or end-of-thread when decisions, insights, or context are worth preserving') with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('capture', 'decisions, insights, or context', 'mid-thread or end-of-thread') with good coverage, missing only a few synonyms like 'save' or 'remember' that the body later surfaces.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche — single Basic Memory note per thread, rewrite-in-place on re-capture — with triggers unlikely to fire for unrelated skills.	5 / 5
	Total	18 / 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-capture/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.