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。

Quality

72%

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 ./bundled/skills/knowledge-steward/SKILL.md

Quality

Content

53%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 well-structured with real bundle files and concrete executable commands, but it is padded with redundant trigger taxonomy and verbose ToolSearch protocol narration. The lack of explicit validation/verification checkpoints before auto-syncing to GitHub caps workflow clarity.

Suggestions

Add an explicit validation/verification checkpoint before auto-pushing to GitHub (e.g., confirm the note rendered correctly and the file path is sane, then sync) to lift workflow clarity past the destructive-operation cap.

Trim the duplicate trigger-term taxonomy and the motivational 'digital accountant' prose that restates the description, leaving only triggers Claude cannot already infer.

Move the large ToolSearch task-plugin mapping table and the full config.yaml block into a reference file, keeping SKILL.md to a concise overview pointer.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: the body re-states the trigger taxonomy already in the description, includes lengthy ToolSearch pseudo-protocol blocks, motivational prose, and config/exception narration that Claude largely does not need, padding the context budget.	2 / 5
Actionability	Provides concrete, executable commands (python scripts/save_to_obsidian.py invocations with flags, setup steps, troubleshooting commands) and worked step-by-step examples; minor gaps such as missing exact CLI argument signatures for all script variants.	4 / 5
Workflow Clarity	Sequenced steps are present in the examples, but this skill performs batch/destructive-adjacent operations (writing files to an Obsidian vault and auto-pushing to GitHub) with no explicit validation/verification checkpoints before sync, capping clarity at 3 per the destructive-operation rule.	3 / 5
Progressive Disclosure	Good structure: SKILL.md is an overview with clearly signaled one-level-deep references to real bundle files (references/index.md, assets/.md, scripts/.py) that exist on disk; minor gaps where some inline config and ToolSearch mapping tables could live in references.	4 / 5
	Total	13 / 20 Passed

Description

91%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.

A strong description that clearly states both the capability and explicit trigger conditions with rich bilingual natural-language phrases. It is specific and distinct, with only minor coverage gaps keeping specificity from the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain (AI work-experience knowledge base management) and several concrete actions (save prompts, patterns, bugfixes, ideas, efficiency optimizations to Obsidian and sync to GitHub), with minor gaps in coverage rather than a comprehensive enumeration.	4 / 5
Completeness	Explicitly answers both 'what' (save prompts/patterns/bugfixes/ideas/efficiency optimizations to Obsidian and sync to GitHub) and 'when' (use when user says '保存到Obsidian', '记录这个', etc.) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive bilingual coverage of natural trigger phrases including synonyms and variants ('保存到Obsidian', '记录这个', 'save this insight', 'memo this', 'capture this') that users would plausibly say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (Obsidian knowledge capture with GitHub sync) with distinct bilingual triggers; minor overlap risk with general note-taking or journaling skills.	4 / 5
	Total	18 / 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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/knowledge-steward/SKILL.md
Commit: d5ae560

Reviewed: 1 day 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.