CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bm-orient

Orient Claude from Basic Memory before substantial repo work by reading active tasks, open decisions, recent checkpoints, and repo conventions. Use when resuming old work or when the user asks where things stand.

Quality

84%

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 compact, self-contained instruction skill with concrete query filters, explicit config precedence, and clear error-path handling for missing setup. Its few imperfections — mild repetition in step 2, an assumed tool interface, and no output-verification step — keep most dimensions at 4.

DimensionReasoningScore

Conciseness

The body is dense and operational with no explanations of concepts Claude already knows — even the tricky CLAUDE_CONFIG_DIR edge cases ("do not trim it, expand ~, or treat an empty value as unset") are load-bearing rules. Step 2 mildly restates rules already implied by its bullet list ("Never run an unscoped coding-session query"), keeping it just below the lean 5 anchor.

4 / 5

Actionability

Concrete, executable guidance throughout: literal filter values ("filters={\"type\": \"task\", \"status\": \"active\"}"), named config keys, explicit precedence order, and a specified output format. Minor gaps — the bm_search tool invocation itself and tool-availability fallback are assumed rather than shown.

4 / 5

Workflow Clarity

Five clearly sequenced steps with explicit fallback checkpoints ("If no config is present, continue against the default Basic Memory project and mention that setup has not been run"; "if the repository is missing, report that setup is incomplete"). As a read-only skill it needs no destructive-operation validation, but there is no final verification of the summary before presenting, matching the 4 rather than 5 anchor.

4 / 5

Progressive Disclosure

No bundle directories (references/, scripts/, assets/) exist and the body references no external files; at roughly 45 lines with well-organized sections (intro, Steps, output spec), this is the self-contained under-50-line case the guidelines say can score 5 on well-organized sections alone.

5 / 5

Total

17

/

20

Passed

Description

83%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 explicitly states both what the skill does and when to use it, anchored by a distinct tool name. The only weaknesses are the slightly abstract lead verb "Orient" and a few missing natural trigger synonyms.

DimensionReasoningScore

Specificity

"reading active tasks, open decisions, recent checkpoints, and repo conventions" lists several concrete read actions, but the headline verb "Orient Claude from Basic Memory" is slightly abstract, leaving minor gaps versus the fully concrete 5 anchor.

4 / 5

Completeness

The what is explicit ("Orient Claude from Basic Memory... by reading active tasks, open decisions, recent checkpoints, and repo conventions") and the when is explicit with concrete trigger phrases ("Use when resuming old work or when the user asks where things stand"), matching the top anchor's structure exactly.

5 / 5

Trigger Term Quality

Natural phrases like "resuming old work" and "where things stand" plus the tool name "Basic Memory" give good coverage, though common variants users might say (e.g., "catch me up", "what's the status") are missing.

4 / 5

Distinctiveness Conflict Risk

The "Basic Memory" tool name carves out a clear niche, but generic status triggers like "where things stand" carry minor overlap risk with a general session-briefing or status-update skill.

4 / 5

Total

17

/

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-orient/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.