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".
71
66%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/community/claude-never-forgets/skills/memory/SKILL.mdQuality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a reasonably well-crafted description that clearly communicates both purpose and trigger conditions. Its main strengths are the explicit 'Use when' clause and natural trigger phrases. Its weaknesses are slightly vague capability descriptions (what does 'execute extract' mean exactly?) and some potential overlap with other context/convention-related skills.
Suggestions
Clarify the concrete actions more precisely — e.g., 'Retrieves stored project decisions, conventions, and preferences from memory files' instead of the awkward 'Execute extract and use project memories'.
Add file type or storage mechanism references (e.g., '.memory files', 'MEMORIES.md', 'session logs') to improve distinctiveness and reduce conflict with general documentation or configuration skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (project memories) and some actions ('extract and use project memories', 'recalling past decisions', 'checking project conventions'), but the actions are somewhat abstract rather than concrete operations like 'retrieve stored decisions from memory files' or 'search conversation logs'. | 2 / 3 |
Completeness | Clearly answers both 'what' (extract and use project memories for context-aware assistance) and 'when' (recalling past decisions, checking conventions, understanding preferences) with explicit trigger phrases provided. | 3 / 3 |
Trigger Term Quality | Includes natural trigger phrases users would actually say: 'remember when', 'like before', 'what was our decision about', plus conceptual triggers like 'past decisions', 'project conventions', and 'user preferences'. Good coverage of how users naturally invoke memory recall. | 3 / 3 |
Distinctiveness Conflict Risk | The memory/context domain is fairly specific, but 'context-aware assistance' and 'project conventions' could overlap with skills related to project configuration, documentation lookup, or general context retrieval. The trigger phrases help distinguish it but the core capability description is somewhat broad. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a reasonable conceptual framework for memory management across sessions with good structure (numbered steps, error table, examples, resources section). However, it lacks executable code for core operations, relying on descriptions and references to implementation files that don't exist in the bundle. The content could be more concise by trimming the overview and prerequisites, and more actionable by including the actual JSON schema and read/write code inline.
Suggestions
Add the actual JSON schema for `project_memory.json` and executable code snippets for reading/writing memory entries, rather than deferring entirely to a non-existent `implementation.md`.
Include a validation checkpoint after writing new memories (e.g., re-read and verify the JSON is valid) and after cleanup consolidation.
Trim the overview paragraph—Claude doesn't need an explanation of what persistent context means. Start directly with the instructions or a minimal one-line purpose statement.
Either provide the referenced bundle files (`references/implementation.md`, `references/errors.md`) or inline the critical implementation details to make the skill self-contained.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The overview section explains what memory is in a way Claude already understands. Phrases like 'persistent context across Claude Code sessions' and the prerequisites section add some bloat. However, the instructions themselves are reasonably efficient and the error handling table is well-structured. | 2 / 3 |
Actionability | The instructions describe what to do at a conceptual level (read JSON, match keywords, store entries) but lack executable code for the core operations—no actual JSON schema, no concrete code for reading/writing the memory file, no implementation of the matching logic. The examples show command usage but not the underlying implementation. | 2 / 3 |
Workflow Clarity | The six-step workflow is clearly sequenced and covers the full lifecycle (load → match → apply → store → resolve → cleanup). However, there are no explicit validation checkpoints—step 4 doesn't verify the write succeeded, step 6 lacks a verification step after consolidation, and there's no feedback loop for confirming memories were correctly applied. | 2 / 3 |
Progressive Disclosure | References to `${CLAUDE_SKILL_DIR}/references/implementation.md` and `references/errors.md` are well-signaled and one level deep, which is good. However, no bundle files were provided, so these references point to non-existent files. The error handling table and examples could arguably be in separate reference files to keep the main skill leaner. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
09b10d6
- Reviewed
Table of Contents
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.