CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

memory-onboarding

Help a new user design a Basic Memory knowledge system and set up their assistant to load it. Use when someone is getting started, has an empty or messy project, or wants context kept across sessions.

Quality

90%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

Excellent instructional content: a clearly sequenced multi-phase workflow with explicit validation checkpoints and error-recovery loops, concrete copy-ready tool calls throughout, and a clean one-level-deep reference structure that keeps the overview lean. The only weakness is mild rhetorical padding in the rationale passages that could be trimmed without losing guidance value.

DimensionReasoningScore

Conciseness

The body is dense with skill-specific guidance and assumes Claude's competence (no explanations of markdown, knowledge graphs, or general concepts), but carries rhetorical justifications that exceed minimum instruction ("A pile of unstructured notes is barely better than a folder of text files", "fake ones are noise the user must delete"). This fits 'efficient; minor instances of over-explanation that could be trimmed' rather than the every-token-earns-its-place anchor.

4 / 5

Actionability

Fully executable instruction-only guidance: exact tool calls with parameters (bm_project(command="list"), bm_find(path="/", depth=2, project="<project>"), bm_schema(command="validate", project="<project>")), a concrete eight-domain menu, copy-ready example prompts, and a precise build order. Specific examples cover the common cases, matching the top anchor.

5 / 5

Workflow Clarity

Seven phases are clearly sequenced with an explicit approval gate between Phase 2 and 3, preflight tool verification, a validate-and-fix loop ("run bm_schema validate... fix anything it flags"), duplicate-permalink and refusal recovery guidance, and a Phase 4 verification test. The near-destructive migration path includes validation, so the missing-validation cap does not apply; this matches the anchor with explicit validation steps and feedback loops.

5 / 5

Progressive Disclosure

The body is a well-organized overview with a Reference files table specifying both file and 'Read when', inline citations at the point of use in each phase, and all four referenced files present in the bundle. References are exactly one level deep (reference files contain only intra-file anchors, no nested references), matching the top anchor for clear overview with well-signaled one-level-deep references.

5 / 5

Total

19

/

20

Passed

Description

82%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 strong description that clearly states both capability and trigger conditions in third person with concrete natural-language triggers. Its main weakness is that the capability statement covers only two of the skill's several activities, making the 'what' slightly under-specified relative to the skill's full scope.

Suggestions

Add one or two more concrete actions to the capability statement, e.g. interviewing the user, building schemas/templates, or teaching hands-on usage, so the 'what' reflects the full onboarding workflow rather than only design and assistant setup.

Include additional natural trigger synonyms such as 'set up Basic Memory', 'onboarding', or 'persistent memory across sessions' to widen the keyword coverage for users who phrase the need differently.

DimensionReasoningScore

Specificity

Names the domain ("Basic Memory knowledge system") and exactly two concrete actions — "design a Basic Memory knowledge system and set up their assistant to load it" — matching the anchor for 1-2 concrete actions without comprehensive coverage. It omits the interview, blueprint, build, and teach activities the skill actually performs, so it is not a 4.

3 / 5

Completeness

Explicitly answers both what ("design a Basic Memory knowledge system and set up their assistant to load it") and when ("Use when someone is getting started, has an empty or messy project, or wants context kept across sessions") with three concrete trigger conditions. Both halves are explicit and concrete, matching the top anchor rather than the 'when could be more specific' anchor below it.

5 / 5

Trigger Term Quality

Includes natural phrases users would actually say — "getting started", "has an empty or messy project", "wants context kept across sessions" — plus the product name. A few natural terms are missing (e.g. "set up", "onboarding", "persistent memory"), which fits good-but-not-comprehensive keyword coverage.

4 / 5

Distinctiveness Conflict Risk

Names a specific tool (Basic Memory) and a distinct onboarding/setup niche with trigger conditions (getting started, empty/messy project) that would not fire for companion note-writing or maintenance skills. Clear niche with distinct triggers and minimal conflict risk.

5 / 5

Total

17

/

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

basicmachines-co/basic-memory

Path

skills/memory-onboarding/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.