memory

Search conversation history and understand Dream-managed profile and memory files.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./nanobot/skills/memory/SKILL.md

Quality

Content

86%Weight 40%Scale 1-5

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

The body is an efficient, highly actionable guide to searching conversation history with concrete grep examples and clear guardrails around Dream-managed files. It is a simple, single-purpose skill that is well structured and needs no external references.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, avoiding explanations of JSONL or grep; only the repeated "Managed by Dream. Do NOT edit." phrasing across bullets could be tightened slightly.	4 / 5
Actionability	It provides copy-paste-ready grep examples with concrete parameters (output_mode, fixed_strings, case_insensitive, head_limit/offset) and clear guidance on which mode to use when, covering common search cases.	5 / 5
Workflow Clarity	The read-only search flow (identify the system-prompt path, pick an output mode, page results) is clear and unambiguous; as a simple non-destructive skill it lacks an explicit multi-step checklist but the single action is well sequenced.	4 / 5
Progressive Disclosure	At under 50 lines with no external references needed, the content is organized into well-signaled sections (Structure, Search Past Events, Important); no bundle files exist to verify.	5 / 5
	Total	18 / 20 Passed

Description

50%Weight 40%Scale 1-5

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 states the domain and one concrete action but lacks an explicit "Use when" trigger clause and natural synonyms, capping several dimensions at 3. It is distinguishable via the Dream-managed framing yet remains somewhat broad on the search side.

Suggestions

Add a "Use when..." clause naming concrete triggers, e.g. recalling past events, user preferences, or project context.

Include natural user synonyms such as "remember", "recall", or "past conversations" alongside "memory" and "conversation history".

Sharpen the action verbs: replace "understand ... files" with concrete actions like "read", "search", or "reference".

Dimension	Reasoning	Score
Specificity	"Search conversation history" names one concrete action, but "understand ... profile and memory files" is vague; it states the domain plus one concrete action without comprehensive coverage.	3 / 5
Completeness	It has a clear "what" but no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Terms like "memory", "conversation history", and "profile" are relevant, but common synonyms users would say (e.g. "remember", "recall", "past") are missing.	3 / 5
Distinctiveness Conflict Risk	"Dream-managed profile and memory files" provides a niche, but "search conversation history" is broad enough to overlap with generic history/memory skills.	3 / 5
	Total	12 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: HKUDS/nanobot
Path: nanobot/skills/memory/SKILL.md
Commit: c4a25c9

Reviewed: ~2 hours 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.