Name: audit
Rating: 60.8 (1 reviews)
Author: MemPalace

Blog Docs Log inGet started

audit

Score how well organized the MemPalace palace is, then run a guided repair session — one decision at a time.

Quality

71%

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/audit/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.

This is a lean, deliberate wrapper skill: one exact command, one clear directive, zero padding. Its only weakness is total dependence on the external command's output — no example of the returned instructions, no validation or fallback guidance for the repair session it initiates.

Dimension	Reasoning	Score
Conciseness	The body is 4 lines with one heading and one fenced command — no padding, no concepts Claude already knows, nothing to trim. This matches 'Lean and efficient; assumes Claude's competence; every token earns its place'.	5 / 5
Actionability	The guidance is concrete and executable: an exact copy-paste-ready command (`mempalace instructions audit`) plus a directive to follow its returned instructions. It falls short of level 5 ('specific examples cover the common cases') because everything after step 1 is deferred to the command's output — there is no example of what the returned instructions look like, nor any fallback if the command is unavailable or fails. It is above level 3 because what is written is real, executable, and complete for the first action.	4 / 5
Workflow Clarity	The sequence is clear and unambiguous for a single-action skill: run the command, follow the returned steps. However, the skill describes a multi-step 'guided repair session' whose steps are entirely external, and there is no checkpoint or error-recovery guidance in the body itself (e.g. what to do if the command fails or instructions are unclear), matching 'Clear sequence with most checkpoints present; minor validation gaps' rather than 5.	4 / 5
Progressive Disclosure	Per the rubric's simple-skill note, a skill under 50 lines with no need for external references can score 5 with well-organized content. The body has no bundle files (no references/, scripts/, or assets/ directories exist) and nothing that belongs in a separate file, and the single heading plus command is appropriately structured with no nested or buried references.	5 / 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 communicates a clear niche (MemPalace palace auditing/repair) with two concrete actions, but it lacks any 'when to use' trigger guidance, which caps completeness and weakens trigger-term coverage. Users searching for this skill with natural phrasing like 'audit my memory palace' or 'fix my palace organization' may not match it.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to audit, tidy, or repair their MemPalace / memory palace, or asks about its organization.'

Include natural synonyms users would actually say — 'memory palace', 'memorypalace', 'tidy up', 'check organization' — alongside the current terms.

Briefly enumerate what the audit scores and what the repair session does (e.g. which aspects of organization are checked) to lift specificity from 1-2 actions toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	The description names its domain ("MemPalace palace" organization) and two actions — "Score how well organized" and "run a guided repair session" — matching the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'. It falls short of level 4 because it never enumerates what the scoring covers or what the repair session can do, and is above level 2 because the actions are concrete, not generic.	3 / 5
Completeness	The 'what' is stated clearly (score organization, run a guided repair session "one decision at a time"), but the 'when' is entirely absent — there is no 'Use when...' clause or equivalent trigger guidance, which the guidelines say caps completeness at 3. Not 2, because the 'what' is concrete rather than vague; not 4, because the 'when' is missing rather than merely under-specified.	3 / 5
Trigger Term Quality	Terms like "MemPalace", "palace", "organized", "repair", and "audit" (the skill name) are relevant and somewhat natural, but common variations a user might actually say ("memory palace", "memorypalace", "tidy up", "fix my palace", "check organization") are missing. This fits 'Some relevant keywords but missing common variations or synonyms' — not 4, since there is no explicit 'Use when' trigger phrasing with broader coverage.	3 / 5
Distinctiveness Conflict Risk	"MemPalace palace" is a distinct, named system with its own vocabulary (palace, audit, repair session), giving it a clear niche with minimal overlap against generic organization or file-management skills. The trigger terms are specific enough that confusion with other skills is unlikely, matching the level 5 anchor; it is not 4 because no closely-related competing skill surface is plausibly confusable with this description.	5 / 5
	Total	14 / 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/audit/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.