CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-creator-skill

当用户想要创建、编辑、改进或调试 OpenLoaf 自定义技能(Skill)时触发。典型说法:"帮我创建一个技能"、"做一个新 skill"、"把刚才的操作封装成技能"、"写一个能自动 XX 的技能"、"改一下这个 skill"、"这个 skill 为什么不触发"、"编辑我的自定义技能"、"加个全局技能"、"给当前项目加个技能"。任何涉及 `.openloaf/skills/` 目录下 `SKILL.md` 的创建 / 修改 / 调优请求都应加载本技能。也适用于用户想理解技能格式、排查触发问题、或把对话里的工作流固化成可复用能力的场景。不用于:内置技能(如 file-ops、email-ops 等)的修改——那些是平台随版本发布的只读能力。

73

Quality

91%

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

88%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.

A well-structured, highly actionable instruction skill with a clear multi-step workflow and built-in validation/feedback loops. The main opportunity is conciseness trimming and the absence of any progressive-disclosure references for the longer reference-style sections.

DimensionReasoningScore

Conciseness

Mostly efficient — uses decision trees, tables, and templates rather than prose padding — with only minor over-explanation (e.g., restating the Skill concept definition) that could be trimmed; falls short of anchor 5's fully lean bar.

4 / 5

Actionability

Fully actionable guidance: concrete write paths, `Glob:` conflict-check commands, a complete openloaf.json template, colorIndex table, and a troubleshooting matrix — copy-paste-ready despite being an instruction-only skill.

5 / 5

Workflow Clarity

Clearly sequenced 第一步→第五步 flow with explicit validation checkpoints (创建前 Glob 查冲突) and a feedback loop (有问题回来修改 SKILL.md,再开新对话重试) plus a 验证与迭代 section.

5 / 5

Progressive Disclosure

Well-organized into clearly labeled sections with good navigation, but the ~215-line body is entirely inline with no one-level-deep external references; no bundle files exist, so structure is good but lacks reference-based disclosure.

4 / 5

Total

18

/

20

Passed

Description

95%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, trigger-rich description that clearly states what the skill does and when to load it, with abundant natural trigger phrases and an explicit exclusion boundary. The only minor gap is action specificity, where the listed verbs are broad.

DimensionReasoningScore

Specificity

Names the domain (OpenLoaf custom skills) and several concrete actions — 创建、编辑、改进、调试 — tied to a specific path `.openloaf/skills/` SKILL.md; falls just short of anchor 5 because the verbs are somewhat generic rather than enumerating granular sub-operations.

4 / 5

Completeness

Explicitly answers both 'what' (create/edit/improve/debug custom skills, SKILL.md creation/modification/tuning) and 'when' (当用户…时触发 + 典型说法 + scenarios + 不用于 boundary) with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive quoted natural phrases users would actually say — '帮我创建一个技能', '做一个新 skill', '把刚才的操作封装成技能', '这个 skill 为什么不触发' — covering formal, colloquial, and troubleshooting phrasings.

5 / 5

Distinctiveness Conflict Risk

Clear niche scoped to OpenLoaf custom skills under `.openloaf/skills/` with an explicit '不用于:内置技能' boundary clause, minimizing overlap with other meta/platform skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
itsablabla/openloaf-web
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.