CtrlK
BlogDocsLog inGet started
Tessl Logo

memory

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

59

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./nanobot/skills/memory/SKILL.md
SKILL.md
Quality
Evals
Security

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 a tight, actionable reference: lean prose, concrete grep examples, and a well-structured single-purpose layout. It earns top marks on conciseness and progressive disclosure, with only minor actionability and explicit-checkpoint gaps preventing a perfect score.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: it never explains what JSONL or grep is, and every line (structure list, terse guidance, four example calls, brief warnings) earns its place.

5 / 5

Actionability

Concrete, executable grep invocations with specific parameters cover broad search, literal timestamps, counts, and content matches; minor gaps remain (head_limit/offset are mentioned but not shown in an example, and a placeholder path is used).

4 / 5

Workflow Clarity

A clear escalation strategy is sequenced (absolute path → pick output_mode → expand to content with context → page with head_limit), with an explicit guard against substituting a project-relative path; no destructive/batch operation is involved, but explicit numbered checkpoints and a validation feedback loop are absent.

4 / 5

Progressive Disclosure

No bundle files exist and the under-50-line single-purpose body is cleanly organized into Structure, Search Past Events, and Important sections with no nested navigational references.

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 a clear 'what' but omits any explicit 'when to use' trigger guidance, capping completeness. Keywords are domain-relevant yet miss the natural phrasings a user would actually say.

Suggestions

Add a 'Use when ...' clause with concrete user trigger phrases, e.g. 'Use when the user asks to recall past messages, look up earlier conversation events, or review Dream-managed profile/memory files.'

Replace the vague verb 'understand' with concrete actions like 'read' or 'inspect' for SOUL.md, USER.md, and MEMORY.md.

Include natural synonyms users say ('remember', 'look up', 'past messages', 'history log') alongside the technical terms.

DimensionReasoningScore

Specificity

Names two domains (conversation history, profile/memory files) with one concrete action ('Search'), but the second verb 'understand' is vague rather than a concrete capability.

3 / 5

Completeness

The 'what' is clearly stated, but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Relevant domain keywords ('conversation history', 'profile', 'memory files', 'Dream-managed') are present, but common natural user phrasings ('remember', 'look up', 'past messages') are missing.

3 / 5

Distinctiveness Conflict Risk

The 'Dream-managed profile and memory files' framing narrows the niche, but 'Search conversation history' is generic enough to overlap with other memory/search skills.

3 / 5

Total

12

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
HKUDS/nanobot
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.