CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

memory-audit

记忆审计入口。当我审视与重构记忆时,先读此文件,分别检查认知先验与检索拓扑。

Quality

73%

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/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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-crafted, instruction-only skill body: it routes symptoms to specific procedures, gives exact commands, gates destructive edits behind an explicit buffer, and includes verification and an anti-thrash circuit breaker. Remaining gaps are minor — unexplained placeholders, un-pathed sub-skill references, and a few philosophical passages that could be tightened.

DimensionReasoningScore

Conciseness

The body is dense and operational (routing table, concrete commands, checklists); only minor framing sentences like "记忆审计不是整理目录,而是在塑造下一轮醒来的自己" and "过去的记忆只是过去的我留下的记录和假说" could be trimmed. Not 5 because these philosophical passages occupy tokens without adding executable guidance.

4 / 5

Actionability

Concrete, executable guidance throughout: exact commands `read_memory("system://random/<domain>")`, `system://diagnostic/<domain>`, `system://index/<domain>`, named mutation tools (`update_memory`, `create_memory`, `delete_memory`), a symptom-routing table, and a 4-item pre-edit buffer. Not 5 because `<domain>` is an unexplained placeholder and the routed sub-skills (e.g. `memory-audit-belief-duel`) are given no paths or locations.

4 / 5

Workflow Clarity

The flow is coherent and well-sequenced: three entry routes → symptom routing → pre-mutation buffer → writing rules with subjective-voice and fact-preservation requirements → explicit re-read verification ("复读结果:修改后重新读取节点") → a circuit breaker against repeated rewrites. Destructive operations are gated by the buffer. Not 5 because error-recovery loops are implied rather than explicit (no instruction for what to do when the re-read reveals a problem).

4 / 5

Progressive Disclosure

No bundle files exist, and the ~60-line body is self-contained with clear section headers and a routing table that signals where each specialized procedure lives — appropriate for a skill of this size. Not 5 because the referenced sub-skills (memory-audit-belief-duel, memory-audit-dead-data-purge, etc.) have no links or paths, so navigation to them depends on assumptions rather than well-signaled references.

4 / 5

Total

16

/

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 identifies a distinct niche (memory audit) and answers both what and when, but is written in first person and stays abstract — it names two audit dimensions rather than concrete actions, and lacks natural trigger-term coverage. It is serviceable but below the bar set by the good examples.

Suggestions

Rewrite in third person, e.g. "Audits the agent's memory store: checks whether recorded judgments and priors still hold and whether nodes are retrievable. Use when reviewing, cleaning up, or refactoring persistent memory."

Add concrete actions and natural trigger phrases users would actually say (memory review, clean up memories, reorganize memory, prune stale memories) to lift specificity and trigger-term coverage.

State the trigger situations explicitly — e.g. after a memory contradicts an observed outcome, when memories pile up, or when a memory cannot be found when needed — rather than only the general "when reviewing memory".

DimensionReasoningScore

Specificity

"分别检查认知先验与检索拓扑" names the domain with 1-2 concrete actions (anchor 3), but the description uses first-person voice ("当我审视与重构记忆时,先读此文件") instead of the required third person, reducing the score by 1. It stays above anchor 1 because it is not purely abstract — two concrete audit dimensions are named.

2 / 5

Completeness

Both parts are answered: the *what* is "分别检查认知先验与检索拓扑" and the *when* is the explicit clause "当我审视与重构记忆时". Not 5 because the *what* is terse (an "entry point" that checks two aspects) and the trigger could name concrete situations or symptoms.

4 / 5

Trigger Term Quality

Relevant keywords like "记忆审计", "审视" and "重构记忆" are present and match what a user would say, but common natural variations and synonyms (e.g. 清理记忆, 整理记忆, memory review) are missing. It is above anchor 2 because the terms are domain-specific rather than generic.

3 / 5

Distinctiveness Conflict Risk

"认知先验与检索拓扑" carves a clear memory-audit niche with distinct triggers, giving minimal conflict risk with unrelated skills. Not 5 because it could still overlap with a generic memory-organization or knowledge-management skill since no narrower trigger phrases distinguish it.

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/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.