Name: init
Rating: 60 (1 reviews)
Author: MemPalace

Blog Docs Log inGet started

init

Initialize a new MemPalace — guided setup for your AI memory palace with ChromaDB backend.

Quality

70%

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 ./.codex-plugin/skills/init/SKILL.md

Quality

Content

86%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.

The body is a lean, well-structured single-command skill that respects token budget and needs no bundle files; its only weakness is that the real workflow is delegated to an external command's output rather than shown inline.

Dimension	Reasoning	Score
Conciseness	The body is extremely lean — one heading, one imperative sentence, and one executable command — with no padding or over-explanation, matching the lean/efficient anchor.	5 / 5
Actionability	Provides a concrete, copy-paste-ready command (`mempalace instructions init`), but delegates the remaining work to "follow the returned instructions step by step" without showing those steps, leaving a minor gap.	4 / 5
Workflow Clarity	The sequence is clear and the single entry action is unambiguous, but the subsequent multi-step process and any validation checkpoints are delegated to external instructions not shown here.	4 / 5
Progressive Disclosure	Under 50 lines, single-purpose, with no external references needed; the heading + command + code block are well-organized, so the simple-skill exception earns a 5.	5 / 5
	Total	18 / 20 Passed

Description

53%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 niche tool and conveys a clear purpose, but it omits an explicit use-when trigger clause, which the rubric penalizes by capping completeness.

Suggestions

Add an explicit trigger clause, e.g. "Use when setting up a new MemPalace or initializing an AI memory palace with ChromaDB."

List 1-2 more concrete setup actions (e.g. configuring the ChromaDB backend, creating the initial palace) to lift specificity.

Include common synonyms/variations users might say ("set up", "create", "configure") to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ("Initialize a new MemPalace") plus "guided setup", but does not enumerate the concrete setup steps, so it stops at the 1-2-actions anchor rather than 4.	3 / 5
Completeness	The "what" is clear (initialize/setup a MemPalace with ChromaDB), but there is no "Use when..." or equivalent trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Includes relevant natural terms ("Initialize", "setup", "AI memory palace", "ChromaDB") a user might say, but lacks synonyms/common variations that would push it to 4.	3 / 5
Distinctiveness Conflict Risk	Names a specific product (MemPalace) and backend (ChromaDB), giving a clear niche with minimal conflict risk; only minor overlap with general ChromaDB-setup skills keeps it below 5.	4 / 5
	Total	13 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: MemPalace/mempalace
Path: .codex-plugin/skills/init/SKILL.md
Commit: 5ea40d3

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.