CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

mem0-tour

Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.

67

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

A strong, highly actionable instruction-only skill: exact API payloads, deterministic grouping rules, and literal output templates leave nothing to interpretation. The notable gaps are the unaddressed pagination case and a mapping table with redundant rows.

Suggestions

Add a pagination step: after get_memories, if the result count equals page_size, continue fetching with subsequent page/cursor parameters (or raise page_size) so the 349-memories case in the example is actually reachable.

Collapse the duplicate mapping-table rows (technology/professional_details already fold into Tooling & Setup via the tooling_setup row) into one combined row to trim tokens.

State how to obtain active_user_id and active_project_id (e.g. from the platform context/session), since every filter payload depends on them but no source is given.

DimensionReasoningScore

Conciseness

The body is dense operational instruction with no explanations of concepts Claude already knows (exact filter JSON, display templates, empty-state copy). Minor tightening is possible: the filter JSON blocks are repeated nearly verbatim across sections and the category mapping table duplicates two rows that map to Tooling & Setup.

4 / 5

Actionability

Guidance is fully executable: exact `filters` JSON payloads, `page_size`/`top_k`/`rerank` values, deduplicate-by-ID rule, literal output templates with format specs (e.g. `<number>. [<type>] <content, 80 chars> (<date>) [mem0:<short_id>]`), and exact empty-state text to print.

5 / 5

Workflow Clarity

Mode dispatch (all-projects → peek → full tour) and Steps 1–6 are clearly sequenced with an explicit empty-state branch; the operation is read-only so no destructive-validation cap applies. However, pagination is unaddressed — the example output itself shows 349 memories against `page_size=100/200` with no instruction to fetch subsequent pages, so the 'fetch ALL memories' step may silently miss most of the store.

4 / 5

Progressive Disclosure

A single well-sectioned file with no bundle files (no references/, scripts/, or assets/ exist), so no nested references to score. At ~156 lines, the category mapping table and display-format templates are borderline candidates for a references/ file, but keeping one cohesive operational file is defensible.

4 / 5

Total

17

/

20

Passed

Description

78%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.

A well-formed description with a clear what, an explicit Use-when clause, and natural trigger phrases. Its main weakness is that it undersells the skill's actual capabilities, describing only the browsing tour and not the search or cross-project modes.

Suggestions

Add the supplementary capabilities to the what-clause, e.g. 'Browses all stored memories grouped by category, searches them by keyword, and supports cross-project overview' — this also strengthens the specificity score.

Include a search-oriented trigger term (e.g. 'search project memories' or 'find what we decided about') so the peek mode is discoverable from the description.

DimensionReasoningScore

Specificity

"Browses all stored memories grouped by category with full content display" names the domain and the concrete actions of one browsing flow, matching the '1-2 concrete actions, not comprehensive' anchor. It omits the search/peek mode and cross-project mode that the body actually supports, so it falls short of the 'several specific actions, minor gaps' anchor at 4.

3 / 5

Completeness

Explicitly answers both parts: the what is "Browses all stored memories grouped by category with full content display", and the when is an explicit "Use when..." clause listing four concrete trigger scenarios. This matches the anchor for clearly and explicitly answering both with concrete trigger phrases; a 4 would require the when to be weaker or less explicit than it is.

5 / 5

Trigger Term Quality

Natural phrases users would say are present: "reviewing all project memories", "exploring stored knowledge", "onboarding to a project", "overview of captured decisions, conventions, and learnings". A few natural variants are missing, e.g. searching or querying memories and 'what do we know about' phrasing, so it is good but not comprehensive.

4 / 5

Distinctiveness Conflict Risk

The stored-memories review framing carves a clear niche distinct from general project-onboarding or knowledge skills, with "memories" as a distinguishing trigger. Minor overlap risk remains because "onboarding to a project" and "exploring stored knowledge" are broad phrases that could match adjacent skills.

4 / 5

Total

16

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

mem0ai/mem0

Path

integrations/opencode-plugin/opencode-skills/mem0-tour/SKILL.md

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.