memory-defrag

Defragment and reorganize agent memory files: split bloated files, merge duplicates, remove stale information, and restructure the memory hierarchy. Use when memory files have grown unwieldy, contain redundancies, or need reorganization. Run periodically (weekly) or on demand.

Quality

92%

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

92%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, concise instruction skill with a clear sequenced workflow and an explicit validation checkpoint for its destructive/batch operations. The single area for improvement is actionability — adding a few concrete listing/measurement commands would make the audit and threshold checks fully executable.

Suggestions

Add a concrete audit command or snippet (e.g. `wc -l MEMORY.md memory/**/*.md` or `ls -la memory/`) so the 'Audit Current State' step is executable rather than implied.

Show one example of the before/after comparison used in the Verify step (e.g. a diff or line-count tally) to make 'verify no information was lost' concrete.

Optionally surface the key numeric thresholds (>300 lines, 14/30 days) in a short 'Quick rules' summary near the top for faster reference.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout — a compact table, terse bullets, and minimal code templates with no padding or explanation of concepts Claude already knows; every section earns its place, matching the score-5 anchor.	5 / 5
Actionability	Concrete and specific guidance with explicit thresholds (>300 lines, ~500 lines, 14/30 days) and named operations plus ready-to-fill plan/log templates, but as an instruction-only skill it lacks copy-paste executable commands (e.g. listing/line-count commands), leaving minor gaps that fit the score-4 anchor.	4 / 5
Workflow Clarity	Clear five-step sequence (Audit → Identify → Plan → Execute → Verify & Log) with an explicit validation checkpoint ('Verify no information was lost (compare before/after)'), an ask-before-destructive feedback loop, and a checklist-style plan template, satisfying the score-5 anchor and avoiding the destructive-operation cap since validation is present.	5 / 5
Progressive Disclosure	A self-contained, well-sectioned single file with no bundle files or nested references, appropriate for a skill of this size; per the simple-skill scoring note, clear organization with no needed external references matches the score-5 anchor.	5 / 5
	Total	19 / 20 Passed

Description

92%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, specific description that clearly states both capability and trigger conditions with concrete actions and use-when guidance. The only minor weakness is trigger-term breadth — it relies on somewhat internal phrasing rather than the full range of natural user requests.

Dimension	Reasoning	Score
Specificity	Lists four concrete, distinct actions — 'split bloated files, merge duplicates, remove stale information, and restructure the memory hierarchy' — giving comprehensive coverage of the domain, matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both 'what' (the four reorganization actions) and 'when' ('Use when memory files have grown unwieldy, contain redundancies, or need reorganization. Run periodically (weekly) or on demand.'), with concrete trigger phrases matching the score-5 anchor.	5 / 5
Trigger Term Quality	Includes natural terms like 'memory files', 'reorganize', 'redundancies', and 'reorganization', but leans on internal phrasing and misses common user variants like 'clean up memory' or 'organize notes', fitting the score-4 anchor with a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (agent memory maintenance/defragmentation) with distinct triggers and minimal overlap risk with other skills, matching the score-5 anchor.	5 / 5
	Total	19 / 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-defrag/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.