memory
Two-layer memory system with grep-based recall.
64
Quality
47%
Does it follow best practices?
Impact
95%
1.30xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./nanobot/skills/memory/SKILL.mdDiscovery
7%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 description is too terse and technical to be useful for skill selection. It describes an implementation detail ('grep-based recall') rather than user-facing capabilities, and provides no guidance on when Claude should select this skill. Users asking to 'remember something' or 'look up what we discussed' would not trigger this skill.
Suggestions
Add concrete actions describing what the skill does, e.g., 'Stores and retrieves information across conversations, maintains persistent notes, searches through saved memories'
Add a 'Use when...' clause with natural trigger terms like 'remember', 'recall', 'save this', 'what did we discuss', 'look up', 'notes'
Replace technical jargon ('grep-based recall', 'two-layer') with user-facing language that describes the benefit, not the implementation
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language ('memory system', 'grep-based recall') without describing any concrete actions Claude would perform. No specific capabilities like 'store notes', 'retrieve information', or 'search memories' are listed. | 1 / 3 |
Completeness | Only vaguely addresses 'what' (a memory system) with no explanation of specific functionality. Completely missing 'when' guidance - no 'Use when...' clause or trigger conditions. | 1 / 3 |
Trigger Term Quality | Contains technical jargon ('grep-based recall', 'two-layer') that users would not naturally say. Missing natural keywords like 'remember', 'recall', 'notes', 'save information', or 'look up'. | 1 / 3 |
Distinctiveness Conflict Risk | The 'two-layer' and 'grep-based' qualifiers provide some specificity that distinguishes it from generic memory skills, but 'memory system' is still broad enough to potentially conflict with other note-taking or storage skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
87%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-crafted, concise skill that efficiently explains a two-layer memory system with actionable search commands. The structure is clear and the examples are executable. Minor weakness is the lack of validation guidance for write operations, though this may be acceptable given the non-destructive nature of append-only history.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and purposeful. No explanation of what memory is or why it matters—assumes Claude understands the concept. The structure, search methods, and update triggers are all stated without padding. | 3 / 3 |
Actionability | Provides concrete, executable commands for all three major platforms (Linux/macOS, Windows, cross-platform Python). The grep/findstr examples are copy-paste ready, and the update triggers give specific examples of what to write. | 3 / 3 |
Workflow Clarity | The skill describes when to search and when to update, but lacks explicit validation steps. For a memory system where incorrect writes could corrupt context, there's no guidance on verifying writes succeeded or checking for duplicate entries. | 2 / 3 |
Progressive Disclosure | For a simple skill under 50 lines, the structure is appropriate. Clear sections (Structure, Search, Update, Auto-consolidation) with no need for external references. The two-file architecture is explained upfront without nesting. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- 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.