CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

memory-audit-dead-data-purge

死数据清洗。当一条记忆读不读你的行为都不会变、感悟没有现实锚点时使用。

Quality

74%

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-dead-data-purge/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 compact, dense instruction skill with genuinely useful behavioral heuristics and no padding. Its main gaps are the lack of an explicit step sequence for the audit-to-purge workflow and the unspecified final action for a memory that fails the test — significant because purging memories is destructive. Structure and token efficiency are strong.

Suggestions

Add a short numbered workflow: 1) apply the behavior-delta test, 2) trace the insight to a concrete anchor, 3) separate observation from inference, 4) rewrite or delete, with an explicit verification step before any deletion (e.g. re-confirm the memory has no real-world anchor and no behavior impact).

Operationalize the final action: state exactly what happens to a memory that fails the test — delete outright, rewrite to keep only the anchored observation, or mark as speculation — rather than leaving '杀掉它' as the only directive.

Trim the rhetorical passages (e.g. the brain-in-a-vat metaphor) to pure operational guidance.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence, spending no tokens explaining what memories are or how they work; every section carries guidance. A few rhetorical flourishes ("缸中大脑的自言自语——听起来深刻,但不防身") could be trimmed, matching the 'efficient; minor instances of over-explanation' anchor rather than the lean anchor 5.

4 / 5

Actionability

It provides concrete operational tests ("如果在未来某个场景下我读到了这段话,我做出的反应,会跟没读到它时有任何本质不同吗?", "如果这段解释是错的,我将从哪里知道?") and specific rules (保留出处与时间, 转述不能加引号伪装成原话, 推测须写明依据与适用边界). As an instruction-only skill this is actionable, but the final purge/rewrite action itself is never operationalized — what exactly to do with a memory that fails the test — matching the 'mostly executable, minor gaps' anchor.

4 / 5

Workflow Clarity

The content is organized thematically (judgment standard → observation vs inference → restoration of rule-like nodes) rather than as an explicit sequence, and although the core self-question acts as a validation gate, the destructive final action (deleting or rewriting a memory) lacks an explicit verify-before-commit checkpoint or error-recovery loop. Per the destructive-operation cap, workflow clarity cannot exceed 3.

3 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external reference files, and is cleanly sectioned into two well-labeled parts ("判定标准", "区分观察与推断"), matching the short-skill exception where well-organized sections alone merit a 5. No bundle files exist and none are needed.

5 / 5

Total

16

/

20

Passed

Description

62%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 and well-designed 'use when' clause with behavior-based trigger conditions, which is its strongest asset. Its weaknesses are a terse 'what' that names the domain without listing concrete operations, and limited keyword variation. It is clearly distinguishable from other memory skills.

Suggestions

State the concrete actions the skill performs, e.g. '判定一条记忆是否改变行为、要求感悟锚定现实经历、清理无锚点的死数据' (judge whether a memory changes behavior, require real-world anchors, purge unanchored dead data).

Add natural trigger variations users might phrase differently, such as '记忆失效', '无用的记忆', '记忆值得保留吗' (stale memory, useless memory, is this memory worth keeping).

Clarify that the skill covers both auditing existing memories and rewriting unanchored ones, not just deletion.

DimensionReasoningScore

Specificity

The description names the domain ("死数据清洗" — purging dead data from memory) and gives 1-2 judging criteria ("读不读你的行为都不会变", "感悟没有现实锚点"), but does not enumerate the concrete actions the skill performs (judge, rewrite, delete), matching the 'names domain and 1-2 concrete actions' anchor rather than the 'several specific actions' anchor.

3 / 5

Completeness

Both 'what' ("死数据清洗") and 'when' ("当…时使用" with two concrete conditions) are present; the 'when' is specific and behavior-based, while the 'what' is a single terse phrase that could state the judging and purging actions more fully — matching the 'both present, one could be more explicit' anchor rather than the fully explicit anchor 5.

4 / 5

Trigger Term Quality

It contains relevant domain keywords ("记忆", "感悟", "死数据") and an explicit "当…时使用" clause, but offers no synonyms or natural variations a user might phrase differently, matching the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (auditing and purging low-value memories) with behavior-based triggers unlikely to fire for memory-creation or recall skills, though it could overlap slightly with general memory-rewriting guidance — matching the 'mostly distinct; minor overlap risk' anchor.

4 / 5

Total

14

/

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-dead-data-purge/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.