memory
Two-layer memory system with Dream-managed knowledge files.
62
53%
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 ./nanobot/skills/memory/SKILL.mdQuality
Discovery
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 extremely vague and fails to communicate what concrete actions the skill performs or when it should be selected. It relies on internal jargon ('Dream-managed', 'two-layer memory system') that would not match any natural user request. It needs a complete rewrite with specific capabilities and explicit trigger conditions.
Suggestions
Add a 'Use when...' clause specifying explicit triggers, e.g., 'Use when the user asks to save, recall, or manage persistent information across conversations.'
Replace abstract jargon with concrete actions, e.g., 'Stores and retrieves persistent notes, facts, and context using a two-layer file-based memory system.'
Include natural trigger terms users might say, such as 'remember this', 'save a note', 'recall', 'what did I tell you about', 'memory', 'knowledge base'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language like 'two-layer memory system' and 'Dream-managed knowledge files' without describing any concrete actions the skill performs. No specific capabilities are listed. | 1 / 3 |
Completeness | The description barely addresses 'what' (a memory system) in vague terms and completely lacks any 'when' clause or explicit trigger guidance for when Claude should use this skill. | 1 / 3 |
Trigger Term Quality | The terms 'two-layer memory system' and 'Dream-managed knowledge files' are technical jargon that users would never naturally say. There are no natural keywords a user would use to invoke this skill. | 1 / 3 |
Distinctiveness Conflict Risk | The mention of 'Dream-managed' and 'two-layer memory system' is somewhat distinctive terminology that narrows the domain, but the overall vagueness of 'knowledge files' could overlap with other knowledge management or memory-related skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
100%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 clearly defines a two-layer memory system with explicit boundaries (what not to edit) and actionable search patterns. The grep examples are concrete and progressively more specific, and the structure makes it easy to quickly find the right approach. The constraints are clearly communicated without being verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. No unnecessary explanations of what JSONL is or how grep works conceptually. The content is lean, with clear structure and no padding. | 3 / 3 |
Actionability | Provides concrete, copy-paste-ready grep examples with specific parameters (case_insensitive, fixed_strings, output_mode, etc.). The guidance is specific and executable rather than abstract. | 3 / 3 |
Workflow Clarity | The search workflow is clearly sequenced: start broad (count/files_with_matches), then narrow (content with context), then fallback (exec). The constraints about not editing managed files are explicit and repeated. For this non-destructive read-only task, the workflow is appropriately clear. | 3 / 3 |
Progressive Disclosure | For a skill under 50 lines, the content is well-organized into logical sections (Structure, Search Past Events, Important). The file references (SOUL.md, USER.md, MEMORY.md, history.jsonl) are clearly listed with their purposes. No need for external references given the scope. | 3 / 3 |
Total | 12 / 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 | |
- Repository
- HKUDS/nanobot
- Commit
04a41e3
- 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.