CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

expert-prompt-migrator

将任意专家/角色提示词规范化为可移植格式并迁移到任意 AI(DeepSeek、豆包、Kimi、Claude、Ollama 等)的实用工具。内置「清理平台语法 / 单专家单任务 / 补背景信息」三大原则、五段式提示词结构、迁移自检清单,以及 6 个原创领域专家示例(文案/简历/数据/法律/财务/英语)。

Quality

75%

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 ./skills/expert-prompt-migrator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 well-structured, actionable overview: a clear three-step migration workflow with a checklist, concrete platform-syntax cleanup rules, a working script whose documented usage matches its real interface, and example experts properly externalized into separate files. The main defects are the broken reference to the nonexistent template file and noticeable redundancy between the method, principles, checklist, and duplicated compliance notes.

Suggestions

Create the referenced `template/migration-template.md` fillable five-part template (or remove the 空白模板 section) — it is currently a dead reference in the bundle.

Deduplicate content: merge the top compliance blockquote into the 合规提醒 section, and state the platform-syntax cleanup rules once in 三步迁移法 with the checklist and principles referencing rather than restating them.

Add an explicit error-recovery step to the workflow, e.g., if placeholders remain after running the script, replace them manually; if the target AI misreads the migrated prompt, re-clean and re-paste before sending the task.

DimensionReasoningScore

Conciseness

The body is lean with no explanations of concepts Claude already knows, and every section carries actionable content. It is not 5 because the platform-syntax cleanup rules are stated three times (三步迁移法 step 2, 三大原则, and the 迁移自检清单) and the compliance notice is duplicated (top blockquote and 合规提醒 section), which is more than the 5-anchor's 'every token earns its place'; it is above 3 because the repetition is structural reinforcement rather than padding.

4 / 5

Actionability

Guidance is concrete and executable — an exact command that matches the script's actual interface (`python scripts/strip_platform_syntax.py input.md -o cleaned.md`), specific cleanup rules with real syntax examples (`{{用户输入}}`、`{var}`、「调用 XX 工具」), and six real, ready-to-use example files under assets/experts/. It falls short of 5 because the referenced fillable template `template/migration-template.md` does not exist in the bundle, a concrete dead-end for users following that instruction.

4 / 5

Workflow Clarity

The 核心方法论 (提取→清理→落地) is a clearly sequenced three-step workflow with an explicit validation checkpoint (等 AI 确认「明白了」后再发具体任务) and a 6-item self-check checklist — matching 'clear sequence with most checkpoints present'. It is not 5 because no error-recovery path is specified (e.g., what to do if placeholders remain after cleaning or if the target AI misinterprets the prompt).

4 / 5

Progressive Disclosure

Scored against the actual bundle: the SKILL.md is a concise overview with well-signaled, one-level-deep references, and 7 of 8 referenced paths resolve (all six assets/experts/*.md files and scripts/strip_platform_syntax.py exist and are accurately described). It is not 5 because `template/migration-template.md` is referenced in the body but missing from the bundle — a broken navigation path that constitutes a minor organization gap.

4 / 5

Total

16

/

20

Passed

Description

66%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 clearly and specifically states what the skill does, with strong platform-name trigger terms and a detailed inventory of bundled components. Its main weakness is that the 'when to use' guidance sits in the separate assign_when field rather than in the description itself, capping completeness, and it lacks a few common synonym terms.

Suggestions

Add an explicit trigger clause inside the description field itself (e.g., 「当用户想把专家/角色提示词迁移或搬到 DeepSeek、豆包、Kimi、Claude、Ollama 等其它 AI,或想整理自己的可移植提示词库时使用」) instead of relying solely on the separate assign_when field.

Include common synonyms users would naturally say — 系统提示词、智能体、Prompt 库 / 提示词库 — to broaden trigger-term coverage toward the top anchor.

DimensionReasoningScore

Specificity

Names the domain and concrete actions (「将任意专家/角色提示词规范化为可移植格式并迁移到任意 AI」) and inventories specific bundled assets (「清理平台语法 / 单专家单任务 / 补背景信息」三大原则、五段式提示词结构、迁移自检清单、6 个原创领域专家示例), matching the 'several specific actions; minor gaps' anchor. It is not 5 because the action verbs are limited to normalize/migrate while the rest is an inventory of contents rather than comprehensive action coverage.

4 / 5

Completeness

The 'what' is clear and concrete (normalize and migrate expert prompts, with bundled principles, structure, checklist, and examples), but the description field itself contains no 'Use when...' trigger clause — that guidance lives only in the separate assign_when field. Per the rubric guideline, a missing explicit trigger clause in the description caps completeness at 3; it is above 2 because the 'what' is fully explicit.

3 / 5

Trigger Term Quality

Includes natural terms users would actually say — platform names (DeepSeek、豆包、Kimi、Claude、Ollama) plus 专家/角色提示词 and 迁移 — giving good keyword coverage. It falls short of 5 because common variations such as 系统提示词, 智能体, and 提示词库/Prompt 库 are missing.

4 / 5

Distinctiveness Conflict Risk

The niche — migrating expert/role prompts across named AI platforms — is distinct with platform-name triggers, matching 'mostly distinct; minor overlap risk'. It is not 5 because it could still overlap with generic prompt-engineering or prompt-library-management skills.

4 / 5

Total

15

/

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.

Validation — 15 / 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

anbeime/skill

Path

skills/expert-prompt-migrator/SKILL.md

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.