CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

memory-audit-node-decomposition

节点分解。当一个节点体积过大、或塞了多个不相关概念导致disclosure无法覆盖时使用。

Quality

77%

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-node-decomposition/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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 an exemplary instruction-only process skill: concrete decision criteria, a hard quality gate with blacklist phrases, explicit validation with a rewrite feedback loop, and tight cross-references to sibling skills instead of restating them. Its only real gaps are the lack of a worked split example and a small amount of rhetorical framing that could be trimmed.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — it delegates to sibling skills ('同 memory-audit-dead-data-purge 标准', '按 memory-audit-discoverability 中的注意力狙击原则') instead of re-explaining them, and every section carries operational weight. Minor over-explanation remains (the narrative framing '你面前有一条记忆,它不是死数据——里面装的东西确实有用'), keeping it just below level 5.

4 / 5

Actionability

Highly concrete guidance throughout: a >800 Token threshold, a crisp boundary test ('如果这两段话分别出现在两条不同的记忆里,它们的 disclosure 会完全不同吗'), an exact blacklist of hollow-node phrases, and a named tool command (`update_memory`). It falls short of level 5 only because there is no worked before/after example of an actual split.

4 / 5

Workflow Clarity

The 拆分流程 is a clear 5-step sequence with an explicit validation stage (step 5 质检, two named tests) and a real feedback loop — the parent-node stress test sends failures back to step 4 for rewriting ('必须回到步骤 4 重写'). The destructive operation (deleting the original node) is covered by validation, matching the top anchor.

5 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external reference files (none exist in the bundle), and is cleanly organized into 诊断信号 / 拆分流程 sections with sibling-skill references clearly signaled one level deep. Per the rubric's simple-skill guidance, this earns the top score.

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 has an explicit, well-conditionalized use-when clause and a distinct niche within its skill family, but it says almost nothing about what the skill actually does — '节点分解' is a bare label, and the trigger vocabulary is internal jargon rather than natural user phrasing.

Suggestions

State 2-3 concrete actions the skill performs after '节点分解', e.g. '识别概念边界、为每个概念新建独立节点与disclosure、用 update_memory 瘦身或删除原父节点' — this would lift specificity from naming the domain to listing concrete capabilities.

Add natural trigger phrases a reader would actually use, such as '记忆太长'、'一条记忆混了多个主题'、'disclosure 只覆盖一半内容', alongside the existing jargon to broaden trigger-term coverage.

Name the concrete outcome ('把一个臃肿节点拆成多个聚焦的独立节点') so the 'what' is a capability statement rather than a bare two-word label.

DimensionReasoningScore

Specificity

The description only names the domain ('节点分解' / node decomposition) with no concrete capability actions — phrases like '当一个节点体积过大' describe the trigger condition, not what the skill does. It matches the anchor 'Names the domain but actions are minimal or generic' rather than level 3, which requires 1-2 concrete actions.

2 / 5

Completeness

Both parts are present: 'what' via the terse label 节点分解, and an explicit 'when' clause ('当一个节点体积过大、或塞了多个不相关概念导致disclosure无法覆盖时使用') with two concrete conditions. Not level 5 because the 'what' is a bare title with no capability detail; not level 3 because the use-when clause is explicit and specific.

4 / 5

Trigger Term Quality

Terms like '体积过大', '多个不相关概念', and 'disclosure无法覆盖' are relevant to the trigger scenario, but they are jargon internal to the memory-audit skill family and lack natural variations or synonyms. This sits at 'Some relevant keywords but missing common variations', not level 4's 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

It carves a clear niche — splitting oversized memory nodes, explicitly the inverse of the merge/pattern-extraction operation — with distinct triggers. Not level 5 because 'node too large' style triggers could still overlap with sibling memory-audit skills (dead-data-purge, discoverability).

4 / 5

Total

13

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

Dataojitori/nocturne_memory

Path

docs/skills/memory-audit-node-decomposition/SKILL.md

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.