CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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 lean, well-structured instruction-only skill with concrete tool parameters and unusually precise config-resolution rules. It falls just short of top marks on actionability and workflow clarity for lack of an example note structure and error-recovery guidance.

Suggestions

Add a short example note skeleton (title format plus section headings for decision/context/rationale/alternatives/consequences) so the 'Include' list maps directly to the written note.

Add one error-recovery line for step 5, e.g. what to do when the superseded decision note cannot be found (search by title, or link the new note's permalink back instead).

Trim the output-style provenance sentence in the intro ('This is the deliberate version of the basic-memory output style's decision-capture reflex...') to save tokens without losing actionable guidance.

DimensionReasoningScore

Conciseness

The body is dense and step-ordered with no explanations of concepts Claude already knows, but a couple of sentences could be trimmed — e.g. 'This is the deliberate version of the basic-memory output style's decision-capture reflex — it works whether or not that style is enabled.'

4 / 5

Actionability

Guidance is mostly executable: it names the tool (`bm_write`), exact parameters (`note_type: decision`, `status: open`, `decided`, `project`), and precise config-precedence rules. Minor gaps: no example note title/skeleton, and the 'Include' list is not mapped to note sections or frontmatter keys.

4 / 5

Workflow Clarity

A clear 5-step sequence with explicit conditionals (status defaults, clarify-only-if-ambiguous, supersedes handling), but there are no error-recovery checkpoints — e.g. what to do if `bm_write` fails or the superseded note cannot be found. This is a single non-destructive write, so the destructive/batch cap does not apply.

4 / 5

Progressive Disclosure

The skill is under 50 lines, well organized into a short intro and a Steps section, needs no external reference files (none exist in the bundle), and its one cross-skill pointer ('Apply the `bm-writing` skill') is clearly signaled — matching the simple-skill top anchor.

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 strong description: concrete about what gets captured, explicit about when to trigger with natural quoted phrases, and clearly distinct within its niche. The only shortfall is modest keyword synonym coverage and not advertising the supersede/update capability.

DimensionReasoningScore

Specificity

The description names the domain (Basic Memory decision capture) and enumerates concrete captured elements — 'rationale, alternatives, consequences, and affected work' — but the action list itself is a single verb ('Capture'), leaving minor coverage gaps such as updating/superseding prior decisions.

4 / 5

Completeness

It explicitly answers both 'what' (capture a durable engineering decision with rationale, alternatives, consequences, affected work) and 'when' (with concrete quoted trigger phrases and a slash-command trigger), matching the top anchor.

5 / 5

Trigger Term Quality

Natural trigger phrases like "let's go with X" and "record this decision" are quoted verbatim and would be said by real users, but common synonyms such as 'ADR', 'we decided', or 'log this choice' are absent.

4 / 5

Distinctiveness Conflict Risk

It is pinned to a clear niche — decision records in Basic Memory — with decision-specific triggers ('let's go with X', 'record this decision') that would not plausibly fire a generic note-taking or writing skill.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.