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。

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

67%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 content is a well-structured, actionable guide with real executable commands, clear trigger conditions, safety guardrails, and a sequenced workflow with dedup validation. Weaker spots are mild redundancy (duplicated file descriptions, a version/date stamp, a leftover conversational phrase) and inline templates that could be externalized for better progressive disclosure.

Suggestions

Remove the duplicated file descriptions in 文件路径 (they repeat sections A-D) and drop the version/date footer or move it to a changelog file.

Delete the conversational artifact "你提出的 4 类" and rewrite the heading neutrally, e.g. "四类记忆信息".

Move the detailed write templates (A/B/C2/C3/D) into a references/templates.md file and keep one-line summaries in SKILL.md to improve progressive disclosure and token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational (commands, parameter tables, templates) but includes tightening opportunities: file descriptions are duplicated between sections A-D and 文件路径, a conversational artifact "你提出的 4 类" references a prior chat, and a time-sensitive footer "版本：1.5 \| 最后更新：2026-03-16" sits outside any deprecated section. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the minor-trim level of a 4.	3 / 5
Actionability	Concrete, copy-paste bash commands with full flag documentation, a real bundled script (scripts/fetch_conversations.py, verified to exist), a compression policy table, and write templates per file type give mostly executable guidance. Not a 5 because the memory-writing half lacks a worked example of a filled-in template output.	4 / 5
Workflow Clarity	The 执行流程 section gives a clear 5-step sequence with an explicit dedup checkpoint ("去重校验：检查目标文件中是否已有同类信息"), trigger gates, and a troubleshooting section, matching 'clear sequence with most checkpoints present'. Not a 5 because validate-then-fix feedback loops are implicit rather than spelled out.	4 / 5
Progressive Disclosure	The body is well-sectioned and its single bundle reference (scripts/fetch_conversations.py) is clearly signaled, exists, and is one level deep with no nesting. Not a 5 because the long inline write templates (C2/C3, A/B/D) would be better placed in reference files, leaving SKILL.md as a leaner overview.	4 / 5
	Total	15 / 20 Passed

Description

58%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 communicates a clear, specific capability set around fetching, compressing, and classifying agent conversations into named memory files, with good distinctiveness. Its main weakness is the absence of explicit 'when to use' trigger phrasing — the trigger condition is stated only abstractly — which caps completeness and leaves natural trigger terms uncovered.

Suggestions

Append an explicit trigger clause, e.g. "当用户说'整理记忆'、'更新记忆文件'、'把这个记住'或要求沉淀信息到 USER/AGENT/MEMORY/IDENTITY/SOUL 文件时使用".

Include natural trigger keyword variations (整理记忆, 记住这个, 更新记忆, 沉淀) so users' phrasing matches the description.

State the default behavior (conversation compression only, no automatic writes) explicitly in the description to sharpen the 'what'.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions with named targets ("获取并压缩指定 Agent 的对话记录", "将信息分类写入 USER.md / AGENT.md / MEMORY.md…IDENTITY.md / SOUL.md"), matching the 'several specific actions; minor gaps' anchor. It is not a 5 because coverage stops at file-level actions without mentioning compression policy or retrieval details, and not a 3 because it goes beyond 1-2 actions.	4 / 5
Completeness	The 'what' is clear (fetch and compress conversations, classify and write to named memory files), but the 'when' is only the vague "在用户授权/触发条件满足时" with no explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not a 2 since the 'what' is concrete and a weak 'when' is present.	3 / 5
Trigger Term Quality	Relevant domain keywords exist ("对话记录", "记忆整理", the memory file names) but natural user phrasings such as "整理记忆" / "把这个记住" and any 'Use when' equivalent are absent, matching 'some relevant keywords but missing common variations or synonyms'. It is above a 2 because the keywords are domain-specific rather than generic.	3 / 5
Distinctiveness Conflict Risk	The named target files (USER.md/AGENT.md/MEMORY.md/IDENTITY.md/SOUL.md) and agent-scoped conversation fetching define a clear niche with minor overlap risk against generic note-taking skills, matching 'mostly distinct; minor overlap risk'. Not a 5 because the trigger surface is not distinct enough to fully separate it from general memory/notes skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

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: ZHangZHengEric/Sage
Path: app/skills/memory-organizer/SKILL.md
Commit: 81bddde

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.