CtrlK
BlogDocsLog inGet started
Tessl Logo

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。

47

Quality

48%

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 ./.trae/openclaw-skills/session-optimizer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

47%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 a compact, well-structured overview backed by a real bundled script, but its workflow lacks the validation checkpoints required for a reset/switch operation and the executable examples have inconsistent paths. It is usable but not robust.

Suggestions

Add an explicit validation/verification step before reset (e.g. run `check`, confirm the warning threshold is met, then prompt the user before invoking `/reset`).

Make the command path consistent and portable — either always `cd` into the scripts dir or invoke by a stable relative path, so all three examples are copy-paste ready.

De-duplicate the threshold info between 阈值配置 and 重要原则 so each fact appears once.

DimensionReasoningScore

Conciseness

The body is mostly lean and avoids explaining concepts Claude already knows, but the 阈值配置 and 重要原则 sections repeat information (e.g. '超过 3 个建议切换' appears twice) and could be tightened.

3 / 5

Actionability

It provides concrete executable commands (`python3 session-optimizer.py check/history/reset`) but the path in the first example is hardcoded to an absolute machine path while later examples omit the cd, leaving incomplete copy-paste-ready guidance.

3 / 5

Workflow Clarity

The reset operation is effectively destructive (session switching/reset) and batch-oriented, yet there is no validation checkpoint or feedback loop — the rubric caps destructive/batch skills without validation at 3, and here the sequence only loosely listed without verification steps puts it below the midpoint.

2 / 5

Progressive Disclosure

Content is well-organized into clear sections with the detailed logic moved into the bundled scripts/session-optimizer.py, and the skill is small enough that one-level-deep separation is appropriate; minor gaps are the hardcoded paths that should be generalized.

4 / 5

Total

12

/

20

Passed

Description

50%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 conveys a clear purpose but omits any explicit 'Use when' trigger guidance and relies on generic phrasing, leaving activation cues weak. It is functional but not optimized for skill discovery.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers (e.g. 'Use when the session has run long or many tasks are archived and a reset may be needed').

Replace generic verbs like '监控' with concrete operations (counts archived tasks in TODO_ARCHIVE.md, measures elapsed session time, surfaces reset warnings).

Include natural user phrases and tool/file references (session length, /reset, TODO_ARCHIVE.md) so the skill matches how users actually ask for it.

DimensionReasoningScore

Specificity

Names the domain (session 状态监控) and a couple of concrete actions (session 长度监控, 已完成任务数量统计, 时间显示) but each is described generically without enumeration of distinct operations; coverage is partial rather than comprehensive.

3 / 5

Completeness

The 'what' is clear (监控 session 状态并提醒切换) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which the rubric caps at 3.

3 / 5

Trigger Term Quality

It uses relevant terms like 'session 状态' and '切换 session' but misses the natural phrasings a user would actually say ('session too long', 'when to reset') and any file/tool synonyms, so coverage is partial.

3 / 5

Distinctiveness Conflict Risk

The OpenClaw session niche is fairly specific, yet '监控 session 状态' is generic enough that it could overlap with other session/status skills and lacks distinct, unambiguous trigger phrases.

3 / 5

Total

12

/

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
huangruiteng/CS-Notes
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.