bm-remember

Quickly capture a thought, fact, or reminder into Basic Memory as a lightweight note. Use when the user says "remember that…", "note this", "save this to memory", or runs /basic-memory:bm-remember. For quick deliberate capture — not full decision or session records.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./plugins/claude-code/skills/bm-remember/SKILL.md

Quality

Content

78%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 concise, well-organized instruction-only skill that gives field-level executable guidance and a clearly sequenced workflow with sensible guards. The main gaps are minor: a restated anti-padding note, no worked example, and no explicit feedback loop (which the simple task does not demand).

Suggestions

Consolidate the "keep the user's wording / don't pad" guidance so it appears once (e.g., in step 2) rather than being restated in the intro and Notes, freeing token budget.

Add one short worked example showing the title derivation and write_note call for a typical input (e.g., "remember that… the API key is xyz"), which would lift actionability from concrete-spec to copy-paste-ready.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence (no explanations of MCP, Basic Memory, or slugs), and every step earns its place. It is a 4 rather than 5 because the "keep the user's wording / don't pad" guidance is restated across the intro, step 2, and the Notes section, a minor redundancy that could be tightened.	4 / 5
Actionability	Guidance is concrete and executable: exact write_note fields (title, directory, content, tags=["manual-capture"]), a precise title-derivation rule (≤80 chars, append …), and explicit project-vs-project_id UUID routing. It is a 4 rather than 5 because no concrete worked example ties these together for the common case.	4 / 5
Workflow Clarity	A clear four-step sequence (resolve config → derive note → write → confirm) with explicit guards ("ask one short question" if unclear; "don't overwrite an existing note unless the user explicitly asks"). It is a 4 rather than 5 because there is no validate→fix→retry feedback loop or checklist, though the simple single-capture task does not strictly require one.	4 / 5
Progressive Disclosure	The skill is self-contained in SKILL.md (~50 lines) with well-organized ## Steps and ## Notes sections and no bundle files, fitting the simple-skill exception where well-organized sections alone score 5. Peer-skill references (bm-writing, bm-decide, bm-checkpoint) are named at one level, not nested.	5 / 5
	Total	17 / 20 Passed

Description

78%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, well-structured description that clearly states the skill's purpose and gives explicit natural-language trigger phrases plus a scope boundary against sibling skills. The only weakness is single-action specificity and slight genericness of two trigger phrases.

Dimension	Reasoning	Score
Specificity	"Quickly capture a thought, fact, or reminder into Basic Memory as a lightweight note" names the domain and one concrete action (capture a note), matching the anchor that lists 1-2 concrete actions without being comprehensive. It is not a 2 (the action is specific, not generic like "Processes PDF files") and not a 4 (only one action is named, not several).	3 / 5
Completeness	It explicitly answers both what ("Quickly capture a thought, fact, or reminder into Basic Memory as a lightweight note") and when ("Use when the user says…") with concrete trigger phrases, and adds a scope boundary ("not full decision or session records"). This matches the anchor that clearly and explicitly answers both what and when with concrete triggers.	5 / 5
Trigger Term Quality	"Use when the user says \"remember that…\", \"note this\", \"save this to memory\", or runs /basic-memory:bm-remember" supplies several natural phrases users would actually say plus the slash command. It falls just short of 5 because common synonyms like "jot this down" or "make a note of this" are absent, fitting the "good coverage, a few terms missing" anchor.	4 / 5
Distinctiveness Conflict Risk	The Basic Memory framing, the /basic-memory:bm-remember command, and the "not full decision or session records" boundary give it a clear niche with mostly distinct triggers. It is a 4 rather than 5 because phrases like "note this" and "save this to memory" are generic enough to carry minor overlap risk with sibling memory skills.	4 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: basicmachines-co/basic-memory
Path: plugins/claude-code/skills/bm-remember/SKILL.md
Commit: a5fb68e

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.