bm-setup

Set up Basic Memory for Codex at user or project level by mapping a Basic Memory project and seeding schemas.

Quality

73%

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-setup/SKILL.md

Quality

Content

88%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 strong, highly executable instruction document: every step is concrete, the workflow is well sequenced with genuine validation and confirmation checkpoints, and it assumes Claude's competence throughout. The main weaknesses are localized redundancy in the sessionProfile/repository persistence rules and a monolithic single-file structure where some detail could be offloaded to reference files.

Suggestions

Consolidate the three overlapping statements of where sessionProfile and repository must be persisted (user-level vs project-level coding setups) into a single rule or small decision table.

Move the detailed interview option catalog and the MCP TOML approval snippets into a reference file (e.g. references/apply.md), keeping SKILL.md as a lean overview with clearly signaled one-level-deep links.

Trim repeated reassurance phrases about the approval setting's limits (stated in both the Interview and Apply MCP sections) to a single canonical explanation.

Dimension	Reasoning	Score
Conciseness	The body is dense with tool-specific facts Claude could not know (config paths, CLI flags, TOML table names) and explains no general concepts, but the sessionProfile/repository persistence rules are stated nearly three times across the Apply section ("Persist sessionProfile explicitly in the chosen file, except for a user-level coding setup where it belongs in the project file alongside repository") and could be consolidated.	4 / 5
Actionability	Guidance is copy-paste ready throughout: a complete JSON settings template, exact TOML snippets for both plugin and standalone MCP routes, exact commands ("basic-memory hook status --harness codex --project-dir <repo-root>"), and concrete write_note parameters with directory and note_type. The few placeholders (<project-ref>, <plugin-root>) are appropriate parameterization, not pseudocode.	5 / 5
Workflow Clarity	The five phases (Preconditions → Interview → Apply → Seed Schemas → Verify) are clearly sequenced, with an explicit verification stage, error recovery ("If any check errors, fix the project ref or hook launcher before finishing"), and confirmation checkpoints before every risky write (config edits, schema seeding, repository identity).	5 / 5
Progressive Disclosure	Sections are well organized and the only external references (the <plugin-root>/schemas/ files, one level up) are clearly signaled with no nested reference chains. However, the ~215-line body inlines interview option catalogs and TOML approval details that could partly live in reference files, and the bundle provides no references/ or scripts/ files to distribute that load.	4 / 5
	Total	18 / 20 Passed

Description

57%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.

The description is specific to a well-defined niche and largely concrete, but it summarizes only part of the skill's actual scope and lacks any explicit trigger guidance. Adding a "Use when..." clause and reflecting the full workflow (interview, config write, MCP approvals, verification) would raise it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to set up, configure, or connect Basic Memory in Codex, or mentions bm, basic-memory.json, or memory checkpoints."

Mention the remaining concrete capabilities the body covers — the interview, writing user/project-level settings, MCP approval configuration, and hook verification — so the "what" is comprehensive rather than partial.

Include a couple of natural synonyms or file names users would actually say ("bm", "basic-memory.json", "checkpoint") to broaden trigger term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain and two concrete actions ("mapping a Basic Memory project and seeding schemas") plus config levels, but omits the interview, settings-file writing, MCP approval configuration, and verification steps the skill body actually performs, so coverage is more than minimally incomplete.	3 / 5
Completeness	It clearly answers "what" but contains no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	"Basic Memory", "Codex", and "schemas" are the natural terms a user would say when they want this skill, but common variations and related trigger phrases (e.g. "checkpoint", "bm", "config", "memory project setup") are absent.	3 / 5
Distinctiveness Conflict Risk	"Basic Memory for Codex" combined with "user or project level" config mapping carves out a clear niche with distinct triggers; no other plausible skill overlaps with these terms.	5 / 5
	Total	14 / 20 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-setup/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.