CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

memory-start

Help a new user's first Basic Memory session: save one short note, show it, and explain how to get it back. Use when getting started, or when a project is new, empty, or holds only starter notes.

Quality

89%

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

90%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 highly actionable, token-efficient instruction skill: complete tool-call examples, exact user-facing phrasing, and sensible safety guards (search-first, overwrite=False, guarded undo). The only gaps are the absence of an error-recovery loop for failed tool calls and a fully inline structure that modestly exceeds the simple-skill size threshold.

DimensionReasoningScore

Conciseness

Lean, imperative guidance throughout with no explanations of concepts Claude already knows — it explicitly instructs "Don't explain schemas, observations, or the knowledge graph." Non-obvious host-behavior facts ("You can't check memory at the start of a new chat unless the user's instructions or message prompt you to") earn their tokens. Every line matches anchor 5's "every token earns its place".

5 / 5

Actionability

Provides complete, copy-paste-ready tool calls for the core loop — a full `bm_write(...)` with realistic note content, `bm_open(...)`, and `bm_delete(...)` — plus exact one-line scripts for user-facing messages and concrete guards (`overwrite=False`, search-first). The common first-session cases are fully covered, matching anchor 5.

5 / 5

Workflow Clarity

Clear numbered sequence (save, see it, get it back, add to it) with real checkpoints: search-before-write to avoid duplicates, a delete guard ("If the save updated an existing note, don't delete it"), and the undo path. However, there is no error-recovery feedback loop for failed tool calls, so it sits at anchor 4 (most checkpoints, minor gaps) rather than 5.

4 / 5

Progressive Disclosure

Well-organized single file with clear section headers, appropriately deferring fuller setup to the separate memory-onboarding skill. At ~123 lines it exceeds the under-50-line threshold under which a self-contained skill could score 5 on sections alone, so it fits anchor 4 (good structure, content appropriately placed, minor organization gaps).

4 / 5

Total

18

/

20

Passed

Description

83%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 the capability (save, show, and retrieve a first note) and explicit trigger conditions scoped to new users and new/empty projects. Keyword coverage is good though it misses a few natural variants like "set up" or "first time".

DimensionReasoningScore

Specificity

Lists three concrete actions ("save one short note, show it, and explain how to get it back") with minor gaps — updating or adding to an existing note, covered in the body, is unmentioned. This matches anchor 4 (several specific actions, minor gaps) rather than 3 (only 1-2 actions) or 5 (comprehensive coverage).

4 / 5

Completeness

Explicitly answers both what ("save one short note, show it, and explain how to get it back") and when ("Use when getting started, or when a project is new, empty, or holds only starter notes") with concrete trigger conditions, matching the anchor 5 example structure.

5 / 5

Trigger Term Quality

Includes natural phrases users would say: "getting started", "first session", "new", "empty", "starter notes". A few common variants like "set up", "first time", or "onboarding" are missing, matching anchor 4 (good coverage, a few natural terms missing).

4 / 5

Distinctiveness Conflict Risk

Names the specific tool ("Basic Memory") and scopes triggers to the new-user/empty-project scenario, giving a clear niche. Minor overlap risk remains with the closely related memory-onboarding skill the body defers to, matching anchor 4.

4 / 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-start/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.