memory-audit

记忆审计入口。当我主动决定审视记忆质量时，先读此文件判断应使用哪个子技能。

Quality

75%

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 ./docs/skills/memory-audit/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 content is highly actionable with a well-sequenced, validated workflow and clean section organization; the only real weakness is philosophical verbosity that inflates token cost.

Dimension	Reasoning	Score
Conciseness	It assumes Claude's intelligence (no explaining of basic concepts) but carries substantial philosophical and rhetorical padding ('你在塑造下一轮醒来的自己', the blade-forging metaphor) that could be tightened without losing clarity.	2 / 3
Actionability	It provides concrete executable calls (read_memory("system://diagnostic/core"), system://random/<domain>), a symptom→sub-skill routing table, and a numbered mindfulness-buffer procedure — copy-paste ready guidance.	3 / 3
Workflow Clarity	The flow is clearly sequenced (where to start → diagnostic → symptom routing → modify) with explicit validation checkpoints for the destructive rewrite operation: the mandatory mindfulness buffer, the Conviction Test gate ('如果你说不出来你要解决的问题，你就不该动手'), and the anti-serial-rewrite circuit breaker.	3 / 3
Progressive Disclosure	No bundle files exist, but the body is well-organized into clearly headed sections (你在做什么 / 从哪里开始 / 症状路由表 / 操作前的正念缓冲 / 防连续改写熔断) with one-level-deep, clearly signaled references to sub-skills via the routing table.	3 / 3
	Total	11 / 12 Passed

Description

65%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 clearly answers both what and when and occupies a distinct niche, but its first-person voice and thin trigger coverage weaken specificity and trigger-term quality.

Suggestions

Rewrite in third person (e.g. 'Routes the agent to the appropriate memory-audit sub-skill') to avoid the first-person voice that costs specificity.

Broaden trigger terms beyond the single '当我主动决定审视记忆质量时' phrase — add natural variations like 'review memories', 'audit memory quality', or 'clean up memory'.

Spell out the concrete actions auditing entails (diagnosing stale/crowded nodes, routing to sub-skills) rather than only '判断应使用哪个子技能'.

Dimension	Reasoning	Score
Specificity	It names the domain ('记忆审计入口') and a routing action ('判断应使用哪个子技能') but is not comprehensive; the first-person voice ('当我主动决定...') triggers the rubric's -1 specificity penalty, dropping it from a base of 2.	1 / 3
Completeness	It explicitly states what it does ('记忆审计入口...判断应使用哪个子技能') and gives an explicit when clause ('当我主动决定审视记忆质量时'), answering both questions.	3 / 3
Trigger Term Quality	The phrase '审视记忆质量' is a relevant natural trigger, but only one phrasing is offered and common variations (e.g. 'review memories', 'clean up memory', 'audit memory') are missing.	2 / 3
Distinctiveness Conflict Risk	It carves a clear niche as the memory-audit routing entry point with a distinctive trigger, making it unlikely to fire for the wrong skill.	3 / 3
	Total	9 / 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: Dataojitori/nocturne_memory
Path: docs/skills/memory-audit/SKILL.md
Commit: 2cbfb8a

Reviewed: 12 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.