bm-orient

Resume from an exact Basic Memory checkpoint or orient Codex from current graph and repository evidence.

Quality

76%

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-orient/SKILL.md

Quality

Content

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-sequenced, highly actionable read-only orientation workflow with explicit drift-verification checkpoints and clean sectioning; its only real weakness is mild redundancy across sections that slightly hurts conciseness.

Suggestions

Consolidate the repeated unscoped coding-session prohibitions into one stated rule to reduce redundancy and tighten the token budget.

Consider factoring the per-route detail (exact checkpoint, topic discovery, current repository) into a short reference file so the top-level SKILL.md reads as a leaner overview.

Dimension	Reasoning	Score
Conciseness	The body is procedural and assumes Claude's knowledge without explaining basic concepts, but it repeats several prohibitions (e.g., the unscoped coding-session warning and the no-arbitrary-path rule appear across sections) and could be tightened.	2 / 3
Actionability	It gives concrete, executable guidance — specific tool calls ("read_note", "project=<configured primaryProject>"), exact metadata filters ("metadata_filters={\"repository\": \"<configured repository>\"}"), and precise query parameters and comparison fields — which for an instruction-only skill is fully actionable.	3 / 3
Workflow Clarity	A clear top-level sequence (Resolve Configuration → Choose One Recall Route → Check Current State → Present and Continue) is paired with explicit verification — the drift-check step enumerates material-drift cases — and explicit checkpoints such as waiting for the user when multiple matches are found.	3 / 3
Progressive Disclosure	The skill is a single self-contained file with clearly sectioned headers and no nested or missing references (only an unused icon.svg in assets); the organization is clean and easy to navigate, consistent with the simple-skill allowance for a 3 without external references.	3 / 3
	Total	11 / 12 Passed

Description

67%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and occupies a clear, distinct niche, but it relies on product jargon and omits an explicit "when to use" trigger clause, leaving the natural-trigger and completeness dimensions at the mid level.

Suggestions

Add an explicit trigger clause such as "Use when resuming a past thread, before substantial work in a repo, or when the user asks where things stand" to satisfy the completeness "when" requirement.

Include natural-language variations users would actually say (e.g., "where were we", "what's the status", "resume the session") alongside the technical terms to improve trigger-term quality.

Soften the jargon ("graph", "repository evidence") with plain-language equivalents so the description reads as a natural request rather than internal terminology.

Dimension	Reasoning	Score
Specificity	Two concrete actions are named directly — "Resume from an exact Basic Memory checkpoint" and "orient Codex from current graph and repository evidence" — matching the anchor that lists multiple specific concrete actions.	3 / 3
Completeness	The what is clearly stated, but there is no "Use when..." clause or equivalent explicit trigger guidance for when to invoke it, which caps completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Terms like "checkpoint", "resume", and "orient" are relevant, but the phrasing leans on product jargon ("Basic Memory", "Codex", "graph", "repository evidence") and omits natural user-language variations a person would actually say.	2 / 3
Distinctiveness Conflict Risk	The scope is tightly bound to a specific niche — Basic Memory checkpoints and Codex orientation — making it clearly distinguishable and unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 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-orient/SKILL.md
Commit: 60408ad

Reviewed: 11 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.