CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

85%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 skill that wastes no tokens and gives concrete guidance for each step. The only meaningful gap is the lack of an explicit post-write verification step beyond the one-line permalink confirmation.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it jumps straight to config keys, a write_note call with concrete fields, and one-line confirmation, with no padding or explanation of concepts Claude already knows.

5 / 5

Actionability

Provides concrete executable guidance (config file paths, override semantics, write_note with explicit title/directory/content/tags fields), but write_note is referenced as a tool rather than with copy-paste-ready invocation, leaving a minor gap.

4 / 5

Workflow Clarity

A clear four-step sequence with a confirmation checkpoint at the end and a clarifying-question guard for ambiguous referents; the only gap is a lack of an explicit verify-after-write feedback loop, though the permalink confirmation partially covers it.

4 / 5

Progressive Disclosure

Under 50 lines with no need for external references; content is well-organized into clear sections (intro, Steps, boundary guidance), satisfying the simple-skill exception for a top score.

5 / 5

Total

18

/

20

Passed

Description

55%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 specific and well-bounded, clearly carving out a lightweight-capture niche distinct from related skills. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which leaves the 'when' only weakly implied.

Suggestions

Add an explicit trigger clause such as 'Use when the user says "remember that", "save this", or "note this", or asks to capture a small fact.'

Move one or two natural trigger phrases from the body into the description so the 'when' is explicit in the frontmatter.

Confirm voice is third person (it is) and avoid adding first/second person phrasing when revising.

DimensionReasoningScore

Specificity

Names the domain (saving facts/preferences into Basic Memory) and concrete actions (save a fact, reminder, or preference) with specifics like routing to primaryProject, though it describes one core action rather than a comprehensive list.

4 / 5

Completeness

It clearly states 'what' (save a small fact/reminder/preference into Basic Memory) but the 'when' is only weakly implied via the negative boundary ('without turning it into a full decision or checkpoint'); there is no explicit 'Use when...' clause, which caps completeness at 3 per the guidelines.

3 / 5

Trigger Term Quality

Includes relevant terms like 'fact', 'reminder', 'preference', and 'Basic Memory', but the natural trigger phrases users would say ('remember that', 'save this') live in the body rather than the description, leaving common variations absent from the frontmatter.

3 / 5

Distinctiveness Conflict Risk

The 'lightweight capture' niche and explicit contrast with bm-decide/bm-checkpoint distinguish it from sibling skills, with only minor overlap risk between saving a fact versus a decision.

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.

Validation16 / 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.