CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

memory-quest

Finish Memory Quest Mission 8: confirm this assistant reaches Basic Memory Cloud and starts from Basic Memory, then, with approval, save a Memory Master note with the user's verification code.

Quality

83%

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

88%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 tightly engineered, single-purpose workflow: exact tool invocations, a verbatim note template, hard stops with recovery instructions, and a checksum-protected overwrite loop. The only notable weakness is mild verbosity in the intro and project-scope sections; no dimension requires structural change.

DimensionReasoningScore

Conciseness

Nearly every passage covers tool-specific behavior Claude cannot know (cloud-vs-local project shadowing in step 5, the checksum overwrite protocol, "::bm-*" live views); minor instances could be trimmed — the opening paragraph re-derives what the frontmatter description already states, and the "Project scope" section front-loads parameter rules that reappear in the steps.

4 / 5

Actionability

Guidance is fully executable for an instruction-only skill: exact tool calls (`bm_project(command="list", output_format="json")`), a complete `bm_write` parameter list including `overwrite: false`, the literal note template, a concrete code example (`MQ-7HX2-K9QD-4TRM`), the app URL, and coverage of common edge cases (existing note, declined approval, expired code).

5 / 5

Workflow Clarity

Six ordered steps with "Stop at the first step that fails, explain what's missing, and say how to fix it"; validation appears at every checkpoint (connection source check, guidance check, re-asking on a malformed code, approval gate) and the overwrite path is a genuine feedback loop — read with `expected_checksum`, fail if the note changed, "Read it again and repeat the check".

5 / 5

Progressive Disclosure

No bundle files exist and the single SKILL.md is well-sectioned (Project scope, When to Use, Steps, template, Guidelines) with the template inline — defensible since it is the payload of the skill's one write; it stays at 4 rather than 5 because at ~105 lines, the 35-line template block could plausibly live in a references/ file, and the >50-line simple-skill exception does not apply.

4 / 5

Total

18

/

20

Passed

Description

70%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 is concrete, distinctive, and written in an action-oriented voice appropriate to its niche, but it answers only "what". Adding an explicit trigger clause ("Use when the user runs /memory-quest, asks to finish Mission 8, or wants to become a Memory Master") would make it complete and lift both completeness and trigger coverage.

Suggestions

Append a "Use when..." clause naming the explicit triggers, e.g. "Use when the user runs /memory-quest or $memory-quest, asks to finish Mission 8, verify their assistant, or become a Memory Master."

Include a few natural synonyms or variations users would say ("verify", "Memory Master", "setup check") alongside the canonical mission names.

Make the first action as concrete as the save action, e.g. "confirm a Basic Memory Cloud connection and that session guidance makes Basic Memory the starting point".

DimensionReasoningScore

Specificity

"confirm this assistant reaches Basic Memory Cloud and starts from Basic Memory, then, with approval, save a Memory Master note with the user's verification code" lists several specific, sequenced actions; it stays at 4 rather than 5 because "reaches Basic Memory Cloud" and "starts from Basic Memory" name goals rather than the actions behind them, and secondary actions (asking for the code, reporting next steps) are omitted.

4 / 5

Completeness

The "what" is clear (confirm cloud connection and Basic Memory as starting point, then save the Memory Master note with the code), but there is no "Use when..." clause or equivalent trigger guidance, so "when" is only weakly implied by "Finish Memory Quest Mission 8" — per the rubric guideline this caps completeness at 3.

3 / 5

Trigger Term Quality

"Memory Quest Mission 8", "Basic Memory Cloud", "Memory Master note", and "verification code" are the natural phrases a user mid-quest would say, giving good keyword coverage; it falls short of 5 because natural variations the body itself uses ("verify their assistant", "become a Memory Master", the /memory-quest command) are missing.

4 / 5

Distinctiveness Conflict Risk

"Memory Quest Mission 8" and the "Memory Master" note with a verification code form a clear niche with distinct triggers; only the bare term "Basic Memory" could brush a general memory skill, which is minimal conflict risk.

5 / 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

basicmachines-co/basic-memory

Path

skills/memory-quest/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.