CtrlK
BlogDocsLog inGet started
Tessl Logo

memory-onboarding

Guide someone new to Basic Memory through designing and building a personal knowledge system: interview them, propose a structure, build it with schemas and instruction notes, teach them to use it, and set up their assistant to load it every session. Use when a user is new to Basic Memory or wants help getting started, asks how to structure a project (folders, schemas, conventions), has an empty or messy project that needs structure, or wants their assistant to remember context between sessions.

73

Quality

90%

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

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.

A well-executed multi-phase onboarding skill: concrete and actionable at every step, with explicit validation checkpoints and approval gates, and clean one-level-deep progressive disclosure into a real reference bundle. The only minor improvement is trimming a handful of rhetorical flourishes.

DimensionReasoningScore

Conciseness

Largely lean with no explanations of concepts Claude already knows, but a few rhetorical flourishes ("a sprawling empty scaffold dies", "fake ones are noise the user must delete") and duplicated restatements of the non-negotiables could be trimmed.

4 / 5

Actionability

Instruction-only skill with fully concrete guidance: exact tool names (write_note, list_memory_projects, schema_validate, schema_diff), scripted user questions ("tell me about a task on your plate right now"), live documentation URLs, and a per-phase read-when table for the reference files.

5 / 5

Workflow Clarity

Seven clearly sequenced phases with an explicit approval gate ("Do not skip the approval gate between Phase 2 and the Phase 3"), validation with a fix-and-retry loop in Phase 3 (schema_validate on seed and migrated notes, fix anything flagged), preflight failure handling in Phase 0, and a fresh-session verification test closing Phase 4.

5 / 5

Progressive Disclosure

The body is a well-organized overview and all four referenced files (references/conventions.md, schema-guide.md, domain-playbooks.md, assistant-setup.md) exist, are one level deep, signaled at the right phase, and indexed in a read-when table.

5 / 5

Total

19

/

20

Passed

Description

88%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 in third-person voice that clearly states what the skill does and when to use it, with a well-delineated product-specific niche. Trigger coverage and conflict-delineation against sibling memory skills are the only areas with room to improve.

DimensionReasoningScore

Specificity

Lists five concrete actions spanning the full lifecycle — "interview them, propose a structure, build it with schemas and instruction notes, teach them to use it, and set up their assistant to load it every session" — with comprehensive coverage; no minor gaps that would place it at 4.

5 / 5

Completeness

Explicitly answers both "what" (the design/build/teach/assistant-setup lifecycle) and "when" via an explicit "Use when..." clause listing four concrete trigger conditions.

5 / 5

Trigger Term Quality

Natural phrases like "new to Basic Memory", "getting started", "structure a project (folders, schemas, conventions)", "empty or messy project", and "remember context between sessions" are strong, but common synonyms such as "second brain", "note-taking", or "knowledge management" are missing.

4 / 5

Distinctiveness Conflict Risk

Anchored to a named product and a clear onboarding niche, but the broad trigger "wants their assistant to remember context between sessions" creates minor overlap risk with closely related memory/persistence skills.

4 / 5

Total

18

/

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
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.