CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bm-remember

Quickly save a small fact, reminder, or user preference into Basic Memory from Codex without turning it into a full decision or checkpoint.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/codex/skills/bm-remember/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 tight, well-structured instruction-only skill: configuration resolution, drafting delegation, tool parameters, and confirmation are all specified concretely with zero padding. The only gaps are the absence of an example bm_write call or sample output and any failure-path handling.

DimensionReasoningScore

Conciseness

The body is ~30 lean lines with no explanations of concepts Claude already knows; every line is instruction ('Read ~/.codex/basic-memory.json, then the nearest project .codex/basic-memory.json; project keys override user keys'). The guidance 'do not pad a small fact into an essay' keeps it focused, matching the anchor for lean, efficient content where every token earns its place.

5 / 5

Actionability

Guidance is mostly executable: specific config paths, keys with defaults ('rememberFolder, default codex/remember'), a concrete bm_write parameter spec (title trimming rule, directory, tags ["codex", "manual-capture"]) and routing rule. It falls short of anchor 5 because there is no example bm_write invocation or sample note output, leaving the exact call format and confirmation format to inference.

4 / 5

Workflow Clarity

A clear 4-step sequence with a disambiguation checkpoint ('If the user said "remember that" and the referent is unclear, ask one short question') and a verification step ('Confirm in one line with the permalink'). Not anchor 5 because there is no failure handling if bm_write fails or the config is missing, though the operation is low-risk so no validation cap applies.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external reference files (only assets/icon.svg exists and is unreferenced), and content is organized into a clear heading and numbered steps. The one external pointer ('Apply the bm-writing skill') is clearly signaled and one level deep, satisfying the short-skill guideline for a top score.

5 / 5

Total

18

/

20

Passed

Description

61%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 clear, concise, third-person description with a well-defined niche and explicit separation from sibling skills, but it is missing the 'when' half of the equation: no explicit trigger guidance. The body contains strong trigger phrases ('remember that', 'save this', 'note this') that never surface in the description where they would do the most good.

Suggestions

Add an explicit 'when' clause to the description, e.g. 'Use when the user says "remember that", "save this", or "note this", or mentions a small fact or preference that should persist.'

Surface the natural trigger phrases from the body ('remember that', 'save this', 'note this') in the description itself to strengthen trigger term coverage.

Add one or two more concrete actions to the description (e.g. confirming with a permalink, routing to a configured project) to lift specificity beyond a single named action.

DimensionReasoningScore

Specificity

The description names the domain and one concrete action — 'save a small fact, reminder, or user preference into Basic Memory' — with the object types enumerated but no additional distinct actions, matching the anchor for 'names domain and 1-2 concrete actions'. It is not anchor 4, which expects several specific listed actions.

3 / 5

Completeness

The 'what' is clear ('Quickly save a small fact... into Basic Memory'), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines; the 'when' is only weakly implied. The negative clause 'without turning it into a full decision or checkpoint' is a boundary statement, not trigger guidance, so it does not raise this to anchor 4.

3 / 5

Trigger Term Quality

Natural user phrasing is present ('save', 'fact', 'reminder', 'user preference'), giving good keyword coverage, but the most common trigger phrases — 'remember that', 'note this' — appear only in the body, not the description, so a few natural terms are missing (anchor 4 rather than 5). It exceeds anchor 3 because the terms included are ones users actually say rather than generic ones.

4 / 5

Distinctiveness Conflict Risk

'into Basic Memory from Codex without turning it into a full decision or checkpoint' carves out a distinct niche and explicitly separates it from sibling skills (bm-decide, bm-checkpoint), leaving only minor overlap risk with generic note-saving skills — anchor 4. It stops short of anchor 5 because it lacks distinct trigger phrases in the description itself.

4 / 5

Total

14

/

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

plugins/codex/skills/bm-remember/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.