bm-decide

Capture a durable engineering decision in Basic Memory with rationale, alternatives, consequences, and affected work. Use when the user makes or asks to record a real choice — "let's go with X", "record this decision", or runs /basic-memory:bm-decide.

Quality

86%

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

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.

A well-structured, token-efficient instruction skill with concrete, specific guidance and a clear five-step workflow. Its main gaps are the absence of an example note and any explicit error-recovery or verification loop beyond the final permalink confirmation.

Suggestions

Add a short example of the resulting decision note (title plus a few frontmatter/body lines) to make the guidance copy-paste ready for the common case and lift actionability.

Include an explicit verification or error-recovery step after writing the note (e.g., re-read the note via its permalink and fix fields that failed to render) to strengthen the workflow's feedback loop.

Name the concrete write mechanism or command for creating the note (or state explicitly that the bm-writing/basic-memory tooling handles it) so step 3 is fully executable without inference.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence throughout — no concept explanations, no padding — and even the dense config-resolution detail ('append settings.json to the literal value of CLAUDE_CONFIG_DIR... do not trim it, expand ~, or treat an empty value as unset') encodes genuinely non-obvious edge-case rules, so every token earns its place.	5 / 5
Actionability	Concrete field names ('type: decision', 'status: open', 'decided', 'project', 'supersedes'), explicit file paths, and precise precedence rules make the guidance mostly executable, but there is no example decision note and no concrete command for writing the note, leaving minor gaps versus the copy-paste-ready anchor 5.	4 / 5
Workflow Clarity	The five steps are clearly sequenced with a clarify gate in step 2 and a confirmation checkpoint in step 5 ('Confirm with the permalink'), but there is no error-recovery feedback loop (e.g., what to do if the note write fails or the permalink is wrong), keeping it below anchor 5.	4 / 5
Progressive Disclosure	The skill is under 50 lines, single-purpose, needs no external references (none exist in the bundle), and is organized into a clear intro plus a numbered Steps section, satisfying the simple-skill guideline for a top score on organization.	5 / 5
	Total	18 / 20 Passed

Description

87%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 that clearly and explicitly covers both capability and triggers, with concrete quoted trigger phrases and a well-delineated niche. Its only gaps are the single-verb action framing and a few missing natural synonyms such as 'ADR' or 'decision log'.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Capture a durable engineering decision in Basic Memory') and several concrete specifics ('rationale, alternatives, consequences, and affected work'), but expresses this as a single capture action rather than the multiple distinct concrete actions that anchor 5 requires, while clearly exceeding anchor 3's '1-2 concrete actions'.	4 / 5
Completeness	It explicitly answers both what ('Capture a durable engineering decision in Basic Memory with rationale, alternatives, consequences, and affected work') and when ('Use when the user makes or asks to record a real choice') with concrete trigger phrases, matching anchor 5 exactly.	5 / 5
Trigger Term Quality	Natural quoted phrases ('let's go with X', 'record this decision') plus an explicit slash-command trigger give good keyword coverage, but common synonyms like 'ADR', 'decision log', or 'we decided to' are missing, placing it between anchor 4 (a few natural terms missing) and anchor 5.	4 / 5
Distinctiveness Conflict Risk	A clear niche (durable engineering decision capture in Basic Memory, explicitly distinguished from 'a casual preference') with distinct, specific triggers including the /basic-memory:bm-decide command means minimal conflict risk with other skills.	5 / 5
	Total	18 / 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-decide/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.