CtrlK
BlogDocsLog inGet started
Tessl Logo

memory-audit-discoverability

可发现性审计。当disclosure写法有问题、parent放错、alias缺失、子节点过多时使用。

57

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./docs/skills/memory-audit-discoverability/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 and well-structured with concrete rules and numeric limits, but it is framed as topical guidance rather than a sequenced audit workflow, and carries some metaphorical padding that could be trimmed. Adding an ordered audit checklist would lift workflow clarity.

Suggestions

Add a short ordered audit checklist (e.g. 1. 检查 parent_uri 是否在注意力必经节点 2. 检查 disclosure 是否为触发场景而非自我觉察 3. 检查 alias 覆盖 4. 检查 priority/子节点数量) to turn the topical guidance into a sequenced, checkpointed workflow.

Trim the repeated thesis in the intro and the decorative metaphors (涂毒药、锋利如刺、粗暴感) so every remaining token is strictly instructional.

Keep the concrete numeric limits and explicit prohibitions — these are the strongest, most actionable parts of the skill.

DimensionReasoningScore

Conciseness

The body is largely lean and assumes Claude's competence without explaining basic concepts, but it includes metaphorical padding (门把手上涂毒药、锋利如刺、粗暴感) and restates the central thesis in the intro, so it could be tightened further rather than earning the fully-lean anchor 3.

2 / 3

Actionability

As an instruction-only skill it provides concrete, copy-paste-ready rules: two explicit trigger-signal categories, a hard prohibition on '当我感到...' phrasings, and numeric limits (priority=0 ≤5, priority=1 ≤15, 子节点≤10), all specific and executable.

3 / 3

Workflow Clarity

The guidance is organized into clear topical sections but is never sequenced into an audit procedure with checkpoints; there is no ordered 'check parent → check disclosure → check alias → ...' walkthrough, so it sits at the 'sections present but no sequence' level rather than the validated-workflow anchor 3.

2 / 3

Progressive Disclosure

The body is a single cohesive conceptual guide with no need for external references, broken into well-labeled ## sections that make navigation easy and avoid a monolithic wall of text; no bundle files exist, so the well-organized-sections bar is met.

3 / 3

Total

10

/

12

Passed

Description

57%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 pairs a clear explicit trigger clause with a specific niche, but the 'what it does' is only a vague label noun and the action vocabulary is thin. Strengthening the capability statement would lift specificity and completeness.

Suggestions

Replace the bare label '可发现性审计' with a concrete action statement, e.g. '审计记忆树的可发现性:检查每条记忆的触发路径是否会在防线崩溃前被想起'.

Add the concrete actions the skill performs (e.g. 修正 disclosure 写法、重挂 parent_uri、补建 alias、拆分过密子节点) so the 'what' is as explicit as the 'when'.

Keep the existing explicit '当...时使用' clause; it already satisfies the trigger-guidance requirement.

DimensionReasoningScore

Specificity

The description names the domain (可发现性审计) and enumerates concrete trigger conditions (disclosure写法有问题、parent放错、alias缺失、子节点过多), but these are 'when' conditions rather than concrete capability actions like extract/fill/merge, so it does not reach the multi-specific-action level of anchor 3.

2 / 3

Completeness

It has an explicit 'Use when...' clause (当...时使用), but the 'what' side is only a single label noun (可发现性审计) with no concrete statement of what the skill does, so it does not clearly answer both what and when as required for a 3.

2 / 3

Trigger Term Quality

It lists several relevant trigger phrases a future-self user would encounter, but they rely on internal memory-system vocabulary (disclosure, parent, alias) rather than broadly natural terms, fitting the 'some relevant keywords but missing common variations' anchor.

2 / 3

Distinctiveness Conflict Risk

The niche is highly specific (memory-tree discoverability auditing) with distinct internal-vocabulary triggers (disclosure, parent_uri, alias, child-node count) that are unlikely to fire for the wrong skill.

3 / 3

Total

9

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Dataojitori/nocturne_memory
Reviewed

Table of Contents

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.