CtrlK
BlogDocsLog inGet started
Tessl Logo

memory-organizer

智能对话分析与记忆整理助手。获取并压缩指定 Agent 的对话记录,用于在用户授权/触发条件满足时,将信息分类写入 USER.md / AGENT.md / MEMORY.md(含索引与 memory/ 日志)/ IDENTITY.md / SOUL.md。

54

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./app/skills/memory-organizer/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.

The body is highly actionable with executable commands and templates and is well-structured, but it inlines template detail that could live in reference files, has some redundant emphasis, and lacks an explicit validation checkpoint for the destructive memory-writing step.

Suggestions

Add an explicit validation/verification checkpoint after the 写入更新 step (e.g. re-read each target file to confirm the entry landed and dedup actually succeeded) with a fix-and-retry loop.

Move the per-category detailed templates (A/B/C/D write templates) into a reference file and link to it from SKILL.md to improve progressive disclosure.

Trim redundant emphasis blocks (repeated '必须遵守'/'重要修订' markers and ⚠️ sections that restate the 核心原则) to improve token efficiency.

DimensionReasoningScore

Conciseness

Mostly efficient and does not over-explain basic concepts, but has several redundant emphasis blocks (重复的 '重要修订'/'必须遵守' 提示、⚠️ 注意事项重复核心原则) and templates shown with heavy restating that could be tightened.

3 / 5

Actionability

Provides fully executable bash commands with concrete --agent-id examples, a parameter reference, a compression strategy table, and detailed copy-paste-ready write templates covering the common cases.

5 / 5

Workflow Clarity

The execution flow (获取→分类→去重→写入→记录来源) is sequenced, but writing to multiple memory files is a destructive/batch operation with no explicit validation/verification checkpoint or error-recovery loop after writes, so the rubric caps this at 3.

3 / 5

Progressive Disclosure

Structure is well-organized with clear headers and the referenced scripts/fetch_conversations.py exists, but the detailed per-category write templates are all inlined rather than split into separate reference files, fitting the 'content that should be separate is inline' anchor.

3 / 5

Total

14

/

20

Passed

Description

56%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 clearly states what the skill does with concrete named target files, but lacks natural user-facing trigger phrases and an explicit 'Use when' guidance, leaving the 'when' only weakly implied.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases users would actually say (e.g. '整理记忆', '压缩对话记录', '更新 USER/AGENT/MEMORY').

Include common synonyms / variations of trigger terms to improve natural keyword coverage.

Trim the long file enumeration into a tighter formulation so the trigger guidance stands out more clearly.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (获取并压缩对话记录, 分类写入) across five named target files (USER.md/AGENT.md/MEMORY.md/IDENTITY.md/SOUL.md), giving comprehensive coverage rather than minimal generic actions.

5 / 5

Completeness

Provides a clear 'what' (fetch/compress conversations and write to memory files) but only a weakly implied 'when' via '用户授权/触发条件满足时' with no explicit 'Use when...' trigger clause, so completeness is capped per the guideline.

3 / 5

Trigger Term Quality

Contains only domain/technical terms like 'Agent 的对话记录' and '触发条件满足时' with no natural user-sayable phrases such as '整理记忆' or '压缩对话', fitting the 'generic keywords, missing natural phrases' anchor.

2 / 5

Distinctiveness Conflict Risk

The specific five-file categorization scheme is mostly distinct with only minor overlap risk against generic memory skills, though it is not maximally niche-specific.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ZHangZHengEric/Sage
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.