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

79%

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

82%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, instruction-only writing standard: concise, concrete with exact output tokens, clearly sequenced with verification guardrails, and appropriately self-contained. Minor tightening of stylistic clauses and one or two sharper examples would lift conciseness and actionability to full marks.

Suggestions

Tighten a couple of stylistic clauses (e.g. 'It is fine to call a change elegant, messy, risky, boring, or satisfying when you explain why') into shorter directives to save tokens without losing the point.

Give one fully worked example note snippet showing the sections in concert, so the format examples (observations, relations, anchors) are demonstrated end-to-end rather than only token-by-token.

Clarify the link-vs-code boundary with a one-line rule example, e.g. an inline criterion for 'canonical URL verified', to remove ambiguity in actionability.

Dimension	Reasoning	Score
Conciseness	Lean, instruction-only prose that assumes competence and avoids explaining concepts Claude already knows; a few clauses ('It is fine to call a change elegant...', 'Keep personality in service of memory, not performance') are stylistic guidance that could be trimmed, but nothing is padded filler.	4 / 5
Actionability	Concrete, specific guidance with example tokens like `- [branch] feat/bm-writing`, `- [pr] #1123`, `## Observations`, and `- relation_type [[Target Note]]` that show exact formats to produce; as an instruction-only skill it lacks code but the examples are copy-paste-ready, with minor gaps around when to render links vs. code.	4 / 5
Workflow Clarity	Sequenced by labeled sections (Voice -> Tell The Story -> Anchor The Work -> Preserve The Semantic Layer -> Evidence Boundary) with explicit checkpoints like 'Render GitHub-backed anchors as links when URLs are verified; keep unpushed SHAs as code' and 'Never claim a test or deployment passed unless it ran' — clear validation-style guardrails for a non-destructive writing task.	5 / 5
Progressive Disclosure	A self-contained, well-organized standard under ~50 lines with clearly headed sections and no external file references; the only bundle file (assets/icon.svg) is decorative, so the simple-skill exception applies and the section structure provides easy navigation.	5 / 5
	Total	18 / 20 Passed

Description

76%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, specific description that names its domain and its composition with sibling bm-* skills, with minimal conflict risk. It could reach a perfect score by converting the implicit 'Use with...' composition note into an explicit 'Use when...' trigger clause and enumerating the concrete writing actions it governs.

Suggestions

Add an explicit 'Use when...' trigger clause naming the plain situations that call for this standard (e.g. writing or substantially revising a Basic Memory note), rather than relying on sibling-skill names.

List the concrete writing actions the standard governs (voice, narrative/story, anchoring, semantic layer) so the 'what' is comprehensive rather than single-action.

Include natural synonyms a user might say beyond skill names — e.g. 'project memory', 'memory note', 'note revision' — to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (writing standard for Basic Memory notes) and concrete actions ('created or substantially revised'), plus the related skills it composes with, but stops short of listing the multiple distinct writing actions it governs (voice, narrative, anchoring, semantic layer).	4 / 5
Completeness	It states both what it does ('Apply the user-customizable writing standard for Basic Memory notes...') and when to use it ('Use with bm-checkpoint, bm-decide, bm-remember, and other Basic Memory note-writing workflows'), but the 'when' is framed as composition with named skills rather than an explicit 'Use when...' trigger phrase.	4 / 5
Trigger Term Quality	'Basic Memory notes', 'bm-checkpoint', 'bm-decide', 'bm-remember', and 'note-writing workflows' are natural terms a user of this ecosystem would say, though it leans on sibling-skill names as triggers more than on plain natural-language synonyms.	4 / 5
Distinctiveness Conflict Risk	The niche is narrow and specific to Basic Memory notes written/revised by Codex, with explicit sibling-skill triggers that distinguish it from generic writing or memory skills, giving minimal conflict risk.	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/codex/skills/bm-writing/SKILL.md
Commit: a5fb68e

Reviewed: 3 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.