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

77%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/community/claude-never-forgets/skills/memory/SKILL.md

Quality

Content

65%Weight 40%Scale 1-3

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

The content is concise and well-organized with a clear sequence, error table, and examples, but it stops short of fully actionable guidance (the bundled script is unused) and has a broken reference plus orphaned bundle files. Validation/verification checkpoints for destructive memory operations are also missing.

Suggestions

Reference and use scripts/manage-memory.py in the workflow steps (e.g., show invoking it for add/list/remove) so the executable tool is actually integrated, or remove it from the bundle.

Fix the broken reference: the body cites hooks/stop_cleanup.py for the configurable cleanup threshold, but that file does not exist — either add it or point to a real location.

Add explicit validation/verification checkpoints to destructive steps (Step 5 delete/forget and Step 6 cleanup), e.g., 'confirm the entry matches before removing' and 'verify the file still parses after cleanup'.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it does not explain what JSON, memory files, or sessions are, and every section earns its place; the Error Handling table and Examples are compact and purposeful.	3 / 3
Actionability	User-facing commands are concrete, but the core agent workflow ('locate and read the memory file', 'parse the JSON structure', 'apply memories silently') stays at an abstract describe-rather-than-instruct level, and the provided executable script scripts/manage-memory.py is never invoked or referenced in the body.	2 / 3
Workflow Clarity	The six steps are clearly sequenced and conflict-resolution is addressed, but destructive/batch operations (memory deletion, the >10-entry cleanup) have no validation or verification checkpoint before proceeding, which the rubric says caps this dimension at 2.	2 / 3
Progressive Disclosure	References are signaled one level deep and point to real files, but the body references hooks/stop_cleanup.py which does not exist, while references/examples.md and scripts/manage-memory.py are present in the bundle yet never linked from the body — structure is incomplete rather than cleanly partitioned.	2 / 3
	Total	9 / 12 Passed

Description

90%Weight 40%Scale 1-3

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 clearly answers both what the skill does and when to use it, with natural trigger phrases and a distinct niche. Its main weakness is the thin, awkwardly-worded action list ('Execute extract and use'), which undersells the concrete capabilities.

Dimension	Reasoning	Score
Specificity	It names the domain ('project memories from previous sessions') and the high-level actions 'extract and use', but does not enumerate multiple concrete operations comparable to the level-3 'extract/fill/merge' anchor; the lead verb 'Execute extract and use' is also grammatically mangled, weakening concreteness.	2 / 3
Completeness	It answers both 'what' (extract and use project memories for context-aware assistance) and 'when' via an explicit 'Use when recalling past decisions, checking project conventions, or understanding user preferences' clause, matching the level-3 anchor that requires explicit triggers.	3 / 3
Trigger Term Quality	It provides natural phrases a user would actually say — 'remember when', 'like before', 'what was our decision about' — alongside relevant topic keywords (past decisions, project conventions, user preferences), giving good coverage of natural triggers.	3 / 3
Distinctiveness Conflict Risk	The niche — persisting and recalling cross-session project memories — is distinct, and the trigger phrases are specific to recall/convention-checking scenarios, making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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
Path: plugins/community/claude-never-forgets/skills/memory/SKILL.md
Commit: 4c47e33

Reviewed: 2 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.