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".
79
76%
Does it follow best practices?
Impact
Pending
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-constructed 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 somewhat vague capability descriptions and moderate overlap risk with convention or documentation skills.
Suggestions
Replace 'context-aware assistance' with more concrete actions like 'retrieve stored decisions, recall coding patterns, and surface previously agreed-upon conventions'.
Add distinguishing terms to reduce conflict risk, such as specifying the memory storage mechanism (e.g., 'memory files', 'session logs') to differentiate from documentation or config lookup skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (project memories, previous sessions) and some actions (extract, use, recall), but the actions are somewhat vague—'context-aware assistance' is abstract, and it doesn't list concrete operations like 'retrieve stored decisions', 'list project conventions', or 'search session history'. | 2 / 3 |
Completeness | Clearly answers both 'what' (extract and use project memories from previous sessions for context-aware assistance) and 'when' (recalling past decisions, checking project conventions, understanding user preferences) with explicit trigger phrases. | 3 / 3 |
Trigger Term Quality | Includes natural trigger phrases users would actually say: 'remember when', 'like before', 'what was our decision about', plus relevant keywords like 'past decisions', 'project conventions', 'user preferences'. Good coverage of how users naturally invoke memory recall. | 3 / 3 |
Distinctiveness Conflict Risk | The memory/recall niche is fairly distinct, but 'context-aware assistance' and 'project conventions' could overlap with skills related to project configuration, documentation lookup, or general context management. The trigger phrases help differentiate but the core description could still conflict with convention-checking or documentation skills. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with clear workflow sequencing and good progressive disclosure to reference files. Its main weaknesses are moderate verbosity (explaining concepts Claude can infer, like what memory persistence means) and limited actionability since the actual implementation details are deferred to reference files without showing the JSON schema or any executable code in the main skill.
Suggestions
Add the expected JSON schema for project_memory.json (even a minimal example) so Claude knows the exact structure without needing to read the reference file.
Trim the Overview paragraph—Claude doesn't need an explanation of what persistent context means; jump straight to the file path and behavior expectations.
Include a concrete code snippet for reading/writing the memory file rather than only describing the process abstractly and deferring to implementation.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The overview section explains what memory is in a way Claude already understands. Some sections like 'Apply memories silently' describe behavior Claude can infer. The error handling table and examples add value but the overall content could be tightened by ~30%. | 2 / 3 |
Actionability | The instructions provide a clear process but lack executable code. Steps reference a JSON file structure without showing its schema, and the actual implementation is deferred to a reference file. Commands like /remember and /forget are mentioned but their implementation isn't shown. | 2 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced from loading memories through conflict resolution to cleanup. It includes validation-like steps (conflict resolution, cleanup thresholds) and the error handling table provides explicit recovery paths for each failure mode. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references to implementation.md and errors.md. Content is appropriately split between the main skill file and reference documents, with the Resources section providing clear navigation. | 3 / 3 |
Total | 10 / 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
c8a915c
- 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.