memory

Two-layer memory system with Dream-managed knowledge files.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

100%

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

The body is concise, actionable, and well-organized, providing concrete grep examples and a clear escalation strategy for searching history without padding. It is a strong, focused skill body.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence, and contains no concept explanations or padding; every section delivers concrete guidance or structure.	3 / 3
Actionability	It provides copy-paste-ready grep calls with specific parameters (output_mode, fixed_strings, head_limit, glob) and concrete file roles, giving fully executable guidance.	3 / 3
Workflow Clarity	The search guidance is a clear, ordered escalation (broad count search, then content mode, fixed_strings for literals, paging, exec as last resort) for a simple non-destructive task.	3 / 3
Progressive Disclosure	The skill is under 50 lines with no bundle files and is organized into well-labeled sections (Structure, Search Past Events, Important), satisfying the simple-skill criterion for a top score.	3 / 3
	Total	12 / 12 Passed

Description

50%

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 identifies the skill's domain and structure clearly but provides no concrete actions or explicit usage triggers, leaving it indistinguishable in many situations. It is competent but underspecified.

Suggestions

Add concrete actions the skill performs, e.g. 'Search past events in append-only history and surface long-term facts.'

Append an explicit trigger clause such as 'Use when recalling past events, searching conversation history, or checking stored facts.'

Include natural user terms like 'remember', 'recall', and 'history' to improve trigger matching.

Dimension	Reasoning	Score
Specificity	The description names a concrete domain ('Two-layer memory system with Dream-managed knowledge files') but states no concrete actions, only structure, so it does not reach the level of listing multiple specific actions.	2 / 3
Completeness	It states what the system is but lacks any 'Use when...' trigger clause, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Terms like 'memory system' and 'knowledge files' are somewhat natural but it omits common user phrasings such as 'remember', 'recall', 'search history', or 'past events'.	2 / 3
Distinctiveness Conflict Risk	The 'Dream-managed knowledge files' niche adds specificity, but 'memory system' is generic enough to overlap with other memory-related skills.	2 / 3
	Total	8 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: HKUDS/nanobot
Commit: c9c69e4

Reviewed: 1 day 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.