bm-writing

Apply the user-customizable writing standard for Basic Memory notes created or substantially revised by Claude. Use with bm-remember, the basic-memory output style's decision captures, and other Basic Memory note-writing workflows.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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 well-crafted, lean instruction-only writing standard: concrete formatting patterns, a clear voice, and an explicit evidence boundary, organized into clean sections within a single appropriately sized file. Its weaknesses are minor — a non-enumerated observation-category vocabulary and a few trimmable justificatory phrases.

Suggestions

Enumerate the valid [category] values for observations (or point to where the schema defines them) so writers do not have to guess the vocabulary.

Trim justificatory asides like 'That is the part that turns a status report into project memory' to tighten the narrative sections.

Consider a brief ordering note (which section's constraints apply first when they conflict, e.g., schema requirements vs. evidence boundary) to make application order explicit.

Dimension	Reasoning	Score
Conciseness	The body is lean and directive with no padding or explanation of concepts Claude already knows ('Be clear, direct, warm, and technically honest', 'Do not invent intent, impact, verification, decisions, or drama'). A few justificatory asides ('That is the part that turns a status report into project memory') could be trimmed, matching anchor 4 ('Efficient; minor instances of over-explanation').	4 / 5
Actionability	Concrete copy-paste patterns are given: '- [branch] feat/bm-writing', '- [pr] #1123', '## Observations' with '- [category] fact', '## Relations' with '- relation_type [[Target Note]]', and required frontmatter fields ('repository', 'branch', 'git_sha'). Minor gaps remain — the valid [category] vocabulary beyond [decision]/[branch]/[pr] is not enumerated — so it is anchor 4 rather than 5.	4 / 5
Workflow Clarity	This is an instruction-only standard rather than a multi-step process; its sections (Voice, Tell The Story, Anchor The Work, Preserve The Semantic Layer, Evidence Boundary) are clearly organized and each directive is unambiguous, sitting between anchors 4 and 5. It lacks explicit sequencing/checkpoints across sections, so it does not clearly match anchor 5.	4 / 5
Progressive Disclosure	The skill is self-contained with no bundle files; all guidance fits appropriately in the single SKILL.md with well-organized, well-named sections and no buried or nested references. Per the rubric's simple-skill guidance, well-organized sections suffice for anchor 5 when no external references are needed.	5 / 5
	Total	17 / 20 Passed

Description

82%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 with an explicit 'Use with...' trigger clause, clear what/when coverage, and distinct ecosystem-specific terms. Its only weakness is that it states a single generic action ('apply the writing standard') without summarizing what the standard actually prescribes.

Suggestions

Enumerate 2-3 concrete aspects the standard governs (e.g., voice, git anchors, observations/relations format) so the 'what' goes beyond 'apply the standard'.

Add one or two natural user phrasings as trigger synonyms (e.g., 'project memory', 'remember this work') to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Basic Memory notes created or substantially revised by Claude') and one concrete action ('Apply the user-customizable writing standard'), but does not enumerate the several specific capabilities the standard covers, matching the '1-2 concrete actions, not comprehensive' anchor. It is not score 4 because no list of specific actions is provided.	3 / 5
Completeness	It explicitly answers both questions: the 'what' ('Apply the user-customizable writing standard for Basic Memory notes created or substantially revised by Claude') and the 'when' via an explicit 'Use with...' clause naming concrete trigger workflows. This matches the anchor-5 example structure.	5 / 5
Trigger Term Quality	Concrete, natural trigger terms are present: 'bm-remember', "the basic-memory output style's decision captures", and 'Basic Memory note-writing workflows'. Coverage is good but misses common variations a user might say (e.g., 'remember this', 'memory notes'), placing it at anchor 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	It carves out a clear niche tied to a specific ecosystem (Basic Memory notes) and names sibling triggers (bm-remember, basic-memory output style), making confusion with unrelated skills unlikely — minimal conflict risk per anchor 5.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: basicmachines-co/basic-memory
Path: plugins/claude-code/skills/bm-writing/SKILL.md
Commit: 194afe1

Reviewed: 7 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.