CtrlK
BlogDocsLog inGet started
Tessl Logo

knowledge-steward

AI工作经验知识库管理。适用于用户明确要求'保存到Obsidian'、'记录这个'、'save this insight'、'memo this'、'capture this'等知识沉淀场景。将对话中的提示词、模式、问题修复、想法和效率优化保存到Obsidian知识库,并自动同步到GitHub。

68

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

65%

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 concrete scripts, paths, and worked examples, but it is verbose and monolithic — duplicating content across sections and keeping advanced material inline that belongs in references, with no explicit validation feedback loop in the sync workflow.

Suggestions

Collapse the Examples section or merge it with Quick Reference to remove the duplicated step-by-step content and reclaim tokens.

Move the GitHub Sync Feature and ToolSearch Auto-Discovery sections into dedicated reference files, leaving SKILL.md a lean overview with one-level-deep links.

Add an explicit validation checkpoint to the save workflow (e.g. verify the note file was created and confirm the GitHub sync succeeded before reporting success, with a retry/recover path on failure).

DimensionReasoningScore

Conciseness

Mostly efficient and actionable, but the three full Examples duplicate the Quick Reference patterns and the inline ToolSearch Auto-Discovery and GitHub Sync sections are padded prose that could be tightened or offloaded.

2 / 3

Actionability

Provides concrete executable scripts with specific flags (e.g. save_to_obsidian.py --title --type --content --no-sync), exact file paths, a config.yaml example, and copy-paste-ready expected outputs.

3 / 3

Workflow Clarity

Steps are clearly sequenced in the examples, but the save-and-sync workflow lacks explicit validate→fix→retry checkpoints for the GitHub push (a remote/batch-affecting operation), capping it at 2.

2 / 3

Progressive Disclosure

References are real and one level deep with clear signaling, but SKILL.md is a ~250-line monolith with the full GitHub Sync and ToolSearch sections inline rather than split into the referenced bundle files.

2 / 3

Total

9

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-crafted description that states concrete capabilities, provides natural bilingual trigger terms, and explicitly covers both what the skill does and when to use it in appropriate third-person voice.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — saving prompts, patterns, bugfixes, ideas, and efficiency tips to an Obsidian knowledge base and auto-syncing to GitHub — rather than vague abstractions.

3 / 3

Completeness

Explicitly answers both what (save insights/prompts/bugfixes/ideas/efficiency to Obsidian + GitHub sync) and when via the explicit "适用于...等知识沉淀场景" trigger clause, so it is not capped at 2.

3 / 3

Trigger Term Quality

Includes natural bilingual phrases users would actually say ("保存到Obsidian", "记录这个", "save this insight", "memo this", "capture this") with good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

The Obsidian-knowledge-base plus GitHub-sync niche is clearly framed with distinct triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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
foryourhealth111-pixel/Vibe-Skills
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.