bm-writing

Apply the user-customizable writing standard for Basic Memory notes created or substantially revised by Codex. Use with bm-checkpoint, bm-decide, bm-remember, 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

Fix and improve this skill with Tessl

tessl review fix ./plugins/codex/skills/bm-writing/SKILL.md

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.

An exemplary lean, opinionated writing standard: every rule is concrete and instructional with exact output formats, and nothing pads the token budget. The only notable gap is the absence of a consolidated note skeleton or one complete worked example that shows all sections applied together.

Suggestions

Add one short worked example note (frontmatter anchors, an [observation] line, a Relations line) showing all rules applied together, which would close the actionability gap.

Consolidate the implied note structure into a single skeleton (frontmatter anchors → ## Observations → ## Relations) so writers see the full layout in one glance instead of assembling it from four sections.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence throughout — it never explains concepts Claude already knows and each rule earns its place ("Prefer exact behavior, component names, paths, and commands over phrases such as 'made progress' or 'updated the implementation.'"). Matches anchor 5: every token earns its place.	5 / 5
Actionability	Concrete, executable formats are given for the key mechanics: "`- [category] fact`", "`- relation_type [[Target Note]]`", "`- [branch] feat/bm-writing`", and named sections `## Observations` / `## Relations`. It falls short of anchor 5 only because there is no complete worked example note showing all rules applied together — anchor 4 (mostly executable guidance with minor gaps).	4 / 5
Workflow Clarity	This is an instruction-only standard (no destructive or batch operations, so no validation cap applies), and its sections — Voice, Tell The Story, Anchor The Work, Preserve The Semantic Layer, Evidence Boundary — are unambiguous. However, the complete note skeleton (frontmatter anchors → Observations → Relations) is implied across sections rather than consolidated in one place, a minor gap placing it at anchor 4 rather than 5.	4 / 5
Progressive Disclosure	The skill is a self-contained ~65-line standard with no external references needed (no references/ or scripts/ exist and the body cites none) and well-organized headed sections. Per the rubric's guidance for skills with no need for external references, well-organized sections alone warrant anchor 5.	5 / 5
	Total	18 / 20 Passed

Description

73%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 a precise domain, explicit trigger guidance via named companion skills, and low conflict risk. Its main weakness is that the capability statement is a single abstract action — "Apply the user-customizable writing standard" — without listing what the standard actually shapes.

Suggestions

Enumerate 2-3 concrete capabilities the standard covers, e.g. "Apply the user-customizable writing standard — voice, narrative structure, git anchors, and observation/relation formatting — for Basic Memory notes..."

Add natural user-facing trigger phrases beyond sibling skill names, such as "Use when writing or remembering a Basic Memory note" to catch users who don't invoke the bm-* skills by name.

Dimension	Reasoning	Score
Specificity	"Apply the user-customizable writing standard for Basic Memory notes created or substantially revised by Codex" names the domain and scope precisely but states only one action — what the standard covers (voice, structure, anchors, semantic layer) is never enumerated. This matches anchor 3 (domain plus 1-2 concrete actions); it is not 4 because no several specific actions are listed, and not 2 because the scope qualifiers are concrete rather than generic.	3 / 5
Completeness	The when is explicit and concrete ("Use with bm-checkpoint, bm-decide, bm-remember, and other Basic Memory note-writing workflows") and the what is stated ("Apply the user-customizable writing standard for Basic Memory notes..."), but "writing standard" is abstract without naming the sub-capabilities it covers. Both halves are present yet the what could be more concrete — anchor 4, not 5.	4 / 5
Trigger Term Quality	Natural phrases like "Basic Memory notes", "note-writing workflows" and explicit sibling-skill triggers "bm-checkpoint, bm-decide, bm-remember" give good keyword coverage. A few natural variations (e.g. "memory", "journal", "remember this") are missing, so it sits at anchor 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	"Basic Memory" plus the named companion skills form a clear niche with distinct triggers, and the "Use with..." clause explicitly frames cooperation with siblings rather than competition. Minimal conflict risk — anchor 5.	5 / 5
	Total	16 / 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/codex/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.