memory

Execute extract and use project memories from previous sessions for context-aware assistance. Use when recalling past decisions, checking project conventions, or understanding user preferences. Trigger with phrases like "remember when", "like before", or "what was our decision about".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

50%

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

The body is well-organized with a clear six-step workflow and error table, but it stays abstract on the actual memory-file mechanics and under-utilizes its own bundle files. Tightening redundancy and wiring up the existing references and script would lift it across dimensions.

Suggestions

Reference the bundled examples.md and manage-memory.py from the body (e.g. in Examples and Instructions) instead of inlining duplicate examples, so progressive disclosure and actionability both improve.

Replace the abstract 'parse the JSON structure' guidance with a concrete, executable snippet or a direct call to scripts/manage-memory.py for read/add/remove operations.

Add an explicit validation/checkpoint to the cleanup step (e.g. confirm preserved entries count and re-read the file after consolidation) to strengthen workflow clarity, and trim the redundant Output section.

Dimension	Reasoning	Score
Conciseness	The body is structured and mostly avoids explaining concepts Claude already knows, but the Output section restates the Instructions and the Error Handling table duplicates errors.md, so it could be tightened to earn level 3.	2 / 3
Actionability	It provides concrete paths and commands (/remember, /forget, /memories), but the core read/parse/write-memory mechanics are described abstractly and the bundled manage-memory.py and examples.md are never invoked, leaving guidance incomplete rather than copy-paste ready.	2 / 3
Workflow Clarity	The six-step sequence is clearly ordered with conflict-resolution and cleanup steps, but the cleanup step (>10 entries) lacks an explicit validation/checkpoint and steps describe rather than verify, capping it at level 2.	2 / 3
Progressive Disclosure	implementation.md and errors.md are signaled one level deep, but the substantial examples.md bundle is not referenced from the body (which inlines its own examples) and manage-memory.py is unreferenced, so the content split and navigation are incomplete.	2 / 3
	Total	8 / 12 Passed

Description

67%

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 successfully states both purpose and an explicit 'Use when' trigger, but suffers from a garbled leading verb and fairly generic trigger phrases that limit specificity and distinctiveness. It is functional but could be sharpened to reduce overlap with similar skills.

Suggestions

Fix the malformed opening verb phrase ('Execute extract and use') into a clean third-person action list such as 'Extract and apply project memories from previous sessions for context-aware assistance.'

Broaden trigger-term coverage with common phrasings users actually say, e.g. 'remember that', 'last time we', 'we decided', alongside the existing examples.

Add a more distinctive cue (e.g. 'project conventions', 'user preferences across sessions') to the trigger clause to reduce conflict with generic recall skills.

Dimension	Reasoning	Score
Specificity	The description names the memory domain and several concrete actions ('Execute extract and use project memories', 'recalling past decisions, checking project conventions'), but the opening verb phrase is malformed ('Execute extract and use') and the action list is not as clean or comprehensive as the level-3 anchor.	2 / 3
Completeness	It explicitly answers both what the skill does ('Execute extract and use project memories... for context-aware assistance') and when to use it via an explicit 'Use when recalling past decisions...' clause, matching the level-3 anchor.	3 / 3
Trigger Term Quality	It offers natural trigger phrases ('remember when', 'like before', 'what was our decision about'), but coverage is narrow and misses common variations such as 'remember that', 'last time', or 'we decided', so it falls short of level 3.	2 / 3
Distinctiveness Conflict Risk	The memory-persistence niche is somewhat specific, but generic triggers like 'like before' and 'what was our decision about' could overlap with general recall or other context skills, so it is not a clearly distinct, conflict-free niche.	2 / 3
	Total	9 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 607d11b

Reviewed: 1 day 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.