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。

61

Quality

71%

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

65%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 well-structured, instruction-only audit skill with concrete numeric thresholds and a clear forbidden-pattern rule, organized into clean sections. Its main weaknesses are metaphorical verbosity that could be tightened and the absence of any sequenced validation loop across the audit checks.

Suggestions

Tighten the extended metaphors (e.g., "在门把手上涂毒药", "锋利如刺") into terse directives to reduce token overhead without losing the rules.

Add an ordered audit sequence with an explicit verification step (e.g., 'after placing each memory, re-read its disclosure and confirm it names a trigger scenario, not a feeling') so workflow_clarity can rise above 3.

Consider a compact summary table of the hard limits (priority=0 ≤5, priority=1 ≤15, 子节点≤10) so the actionable thresholds are scannable at a glance.

DimensionReasoningScore

Conciseness

The body is mostly efficient and avoids explaining concepts Claude already knows, but recurring metaphorical padding ("在门把手上涂毒药", "锋利如刺") and repeated rationale add more than minor over-explanation, fitting score 3 rather than 4.

3 / 5

Actionability

As an instruction-only skill it gives concrete, actionable rules (priority=0 ≤5条, priority=1 ≤15条, 子节点≤10, the banned "感到/意识到/发现自己在" disclosure pattern, two allowed trigger-signal types) with only minor abstraction gaps, matching score 4; code absence is not penalized per the instruction-skill note.

4 / 5

Workflow Clarity

The audit checks (Parent URI, Disclosure, Alias, Trigger, Priority, 子节点数量, 巡检验证) are listed as parallel heuristics but lack an explicit sequence or any validation/verification checkpoint, fitting score 3; not capped by the destructive-operation rule since this is non-destructive.

3 / 5

Progressive Disclosure

No bundle files exist and none are needed; the body is a single well-organized file with clear section headers, so the under-50-lines/no-external-references exception allows score 5 for well-organized sections.

5 / 5

Total

15

/

20

Passed

Description

78%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.

A concise, third-person description that names a specific niche and gives an explicit use-when trigger with four concrete symptom conditions. It is distinctive and unlikely to conflict with other skills, with only minor room to expand trigger-term coverage.

DimensionReasoningScore

Specificity

Names the audit domain and enumerates four concrete triggering conditions ("disclosure写法有问题", "parent放错", "alias缺失", "子节点过多"), matching the score-4 anchor of several specific items with minor gaps; not a comprehensive list of the skill's actions, so not 5.

4 / 5

Completeness

Provides a clear what ("可发现性审计") and an explicit when clause ("当...时使用"), so it is not capped at 3; the when could be more specific, placing it at 4 rather than 5.

4 / 5

Trigger Term Quality

Includes domain-natural terms a memory-system user would say ("disclosure", "parent", "alias", "子节点过多") with good coverage, but missing common synonyms/variants, fitting score 4 rather than the comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (memory-tree discoverability audit) with distinctive, domain-specific triggers unlikely to fire for unrelated skills, matching the minimal-conflict score-5 anchor.

5 / 5

Total

17

/

20

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.