session-optimizer

OpenClaw Session 优化器 - 监控 session 状态，在需要时提醒用户切换 session。包括 session 长度监控、已完成任务数量统计、时间显示等功能。

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.trae/openclaw-skills/session-optimizer/SKILL.md

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with executable commands and a well-structured, properly-referenced bundle script, but it repeats redundant principles and lacks an explicit validated workflow sequence. Tightening the principles section and adding a checkpoint after reset would lift it further.

Suggestions

Consolidate the redundant "重要原则" bullets into one or two statements (e.g. a single non-invasive principle) to remove near-duplicate phrasing.

Add an explicit reset workflow with a validation step, e.g. "1. run `check`; 2. if warned, run `reset`; 3. run `check` again to confirm state cleared."

Avoid restating the 3-task threshold in both 阈值配置 and 重要原则; reference the config section once.

Dimension	Reasoning	Score
Conciseness	The body is largely lean with concrete commands and thresholds, but the "重要原则" section repeats near-duplicate ideas ("不侵入内部代码", "不修改 OpenClaw 源代码", "不修改 OpenClaw 配置文件", "仅使用 OpenClaw 已提供的功能") and restates the 3-task threshold, so not every token earns its place.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands with exact paths ("cd /root/.openclaw/.../scripts/ && python3 session-optimizer.py check") plus concrete thresholds and state-file path.	3 / 3
Workflow Clarity	The check/history/reset commands are listed and clear, but there is no sequenced workflow with validation checkpoints or feedback loop (e.g. verifying state was cleared after reset), leaving checkpoints implicit.	2 / 3
Progressive Disclosure	Under 50 lines with well-organized sections and a single one-level-deep bundle reference (scripts/session-optimizer.py) that is a real file and correctly pathed in the body.	3 / 3
	Total	10 / 12 Passed

Description

50%

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 conveys the skill's purpose and several monitoring capabilities but lacks an explicit trigger clause and natural keyword coverage. It is specific to a niche yet would benefit from clearer "when to use" guidance.

Suggestions

Add an explicit trigger clause, e.g. "Use when monitoring OpenClaw session length or when archived task counts grow and a session reset may be needed."

Include more natural trigger terms users would say (e.g. "session too long", "reset session", "too many tasks completed") to improve keyword coverage.

Tighten the function list into distinct concrete capabilities (e.g. "checks session runtime, counts archived tasks, warns at thresholds") instead of restating monitoring sub-functions.

Dimension	Reasoning	Score
Specificity	Names the session-monitoring domain and several actions ("session 长度监控", "已完成任务数量统计", "时间显示"), but these are monitoring sub-functions rather than multiple distinct concrete operations.	2 / 3
Completeness	Clearly states what the skill does ("监控 session 状态...提醒用户切换 session"), but the "when" is only vaguely implied ("在需要时") with no explicit "Use when..." clause, capping completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant keywords ("session", "切换 session") but offers no natural trigger phrasing and no common variations a user would say when needing the skill.	2 / 3
Distinctiveness Conflict Risk	The OpenClaw session-switching niche is fairly specific, but narrow tool-bound terms and absent explicit triggers mean it could still overlap with generic session-management skills.	2 / 3
	Total	8 / 12 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: huangruiteng/CS-Notes
Path: .trae/openclaw-skills/session-optimizer/SKILL.md
Commit: a2e95c0

Reviewed: about 15 hours 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.