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

83%

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 tight, well-structured instruction skill with concrete field and config guidance and a clear sequence. Could tighten the opener and add an explicit validation/feedback step for the confirm phase.

Suggestions

Trim the opening line about the output-style reflex, or move it to a short note, to reduce non-essential framing tokens.

Add an explicit validation checkpoint after writing the note (e.g., verify the permalink resolves and the note type/status fields are set) before declaring success.

If status is anything other than open, have the skill state the expected follow-up so the confirm step doubles as a verification loop.

Dimension	Reasoning	Score
Conciseness	The Steps section is lean and concrete, with only a mildly over-explanatory opener about the output-style reflex that could be trimmed.	4 / 5
Actionability	Gives concrete config paths, key/UUID handling, and exact note field names; instruction-only so no code, but the guidance is specific and actionable.	4 / 5
Workflow Clarity	Five clearly sequenced steps with a confirm-with-permalink checkpoint; lacks an explicit error-recovery feedback loop, keeping it just below a 5.	4 / 5
Progressive Disclosure	Under 50 lines, single-purpose, no external references needed, and well-organized into intro and numbered Steps with sub-bullets.	5 / 5
	Total	17 / 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 well-crafted description that crisply states purpose and trigger conditions with natural user phrases. Minor room to broaden keyword/synonym coverage and frame multiple distinct actions.

Dimension	Reasoning	Score
Specificity	Names the domain and enumerates concrete captured elements (rationale, alternatives, consequences, affected work), but centers on a single verb (Capture) rather than multiple distinct actions.	4 / 5
Completeness	Explicitly states both what it does (capture a durable decision with its components) and when to use it, with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes highly natural trigger phrases ("let's go with X", "record this decision", the slash command); missing only domain-noun synonyms or extensions.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (durable engineering decisions in Basic Memory) with distinct triggers, giving minimal overlap 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: 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.