CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

memory-audit-pattern-extraction

模式提取与失效解药分析。当发现多条记忆在讲同一个教训,或发现自己在一而再再而三地犯同样的错误时使用。

Quality

78%

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-pattern-extraction/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 delivers a well-sequenced, genuinely actionable diagnostic workflow with explicit checkpoints and a closing quality-check checklist, appropriately contained in one well-organized file. Its main costs are rhetorical flourish that inflates token usage and a few subjective criteria that lack operational tests.

Suggestions

Trim the rhetorical elaboration (e.g., the '读完会疼' and '想站起来/跪下去' passages) to declarative criteria — keep the intent, cut the persuasion.

Add an operational test or re-verification loop for the destructive cleanup in step 6 (e.g., re-run `search_memory` after deletion to confirm no orphaned duplicates remain).

Make subjective gates concrete: define what '信息密度高于原始散点' means operationally before allowing deletion.

DimensionReasoningScore

Conciseness

The body is mostly efficient procedural guidance, but includes rhetorical padding such as "读完会疼" / "能让人疼的叙事" and "它让我想站起来去走那条路,还是只让我在羞愧中想跪下去" that could be tightened without losing the instruction; it is not 2 because there is no explanation of concepts Claude already knows and no truly padded section, and not 4 because the rhetorical elaboration recurs in multiple steps.

3 / 5

Actionability

As an instruction-only skill, the guidance is concrete and specific: a named tool call (`search_memory`), a timestamp-order check, four enumerated failure-cause diagnostics, and concrete rewrite criteria (positive anchor question, topological placement, disclosure rewrite); it is not 5 because some directives remain subjective (e.g., judging '信息密度') without an operational test.

4 / 5

Workflow Clarity

The six numbered steps form a clear sequence with an explicit decision gate in step 2 (timestamp comparison), a conditional guard before the destructive deletion in step 6, and a final cold-start QC checklist in the 写入纪律 section; it is not 5 because the deletion criteria are subjective and there is no re-verification loop (e.g., re-running the memory search after cleanup) for the destructive consolidation step.

4 / 5

Progressive Disclosure

The skill is a single ~45-line file with no bundle directories and no need for external references, and its content is well organized into six numbered steps plus a clearly separated 写入纪律 section, which satisfies the simple-skill exception for a top score.

5 / 5

Total

16

/

20

Passed

Description

73%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 is a compact, distinctive statement with an explicit and natural 'use when' trigger clause aimed at the right situations. Its main weakness is that the 'what' half is an abstract label rather than a concrete enumeration of the skill's actions.

Suggestions

Expand the 'what' half with 2-3 concrete actions (e.g., auditing failed prior 'cure' memories, diagnosing why they failed, rewriting and re-placing them) instead of the abstract label '模式提取与失效解药分析'.

Add common trigger variations such as '重复教训' (duplicate lessons), '复发' (relapse), or '记忆去重' (memory deduplication) to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

"模式提取与失效解药分析" names the domain and two analytic activities (pattern extraction, failed-cure analysis), matching the 'names domain and 1-2 concrete actions' anchor; it stays at 3 rather than 4 because the actions are abstract labels rather than several specific concrete operations.

3 / 5

Completeness

It answers both 'what' ("模式提取与失效解药分析") and 'when' with an explicit "…时使用" clause containing concrete trigger phrases, so the missing-when cap does not apply; it falls short of 5 because the 'what' is a compressed two-phrase label that could more explicitly state what the skill actually does.

4 / 5

Trigger Term Quality

The clauses "当发现多条记忆在讲同一个教训" and "一而再再而三地犯同样的错误" are natural phrasings of the triggering situations with good coverage; it is not 5 because synonyms and variations (e.g., 'recurring mistake', 'repeated error', 'memory deduplication') are absent, and not 3 because both key trigger situations are expressed in natural language.

4 / 5

Distinctiveness Conflict Risk

The triggers are specific to memory-curation situations (duplicate lessons across memories, repeated mistakes), giving it a clear niche with distinct triggers and minimal conflict risk with other skills.

5 / 5

Total

16

/

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-pattern-extraction/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.