historical-interview-scripts

生成历史名人现代访谈短视频文案，通过古今反差与网络热梗的爆笑结合，创作具有传播力的虚构趣味内容

Quality

63%

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 ./skills/historical-interview-scripts/historical-interview-scripts/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with a concrete output template and well-sequenced workflows that include validation and feedback loops, supported by a real, one-level-deep reference bundle. Its main weakness is redundancy: sizable agent-architecture and role detail is duplicated inline in SKILL.md rather than kept in the reference files, hurting both conciseness and progressive disclosure.

Suggestions

Move the full 4-agent and 9-agent role/architecture detail out of SKILL.md and keep only brief pointers to agent-roles.md, multi-agent-collaboration.md, and full-pipeline-multi-agent.md to reduce redundancy and improve progressive disclosure.

Consolidate overlapping guidance between the 标准流程, 核心技能, and 输出格式 sections into a single canonical source.

Tighten the 注意事项/约束条件/语气风格 sections, which restate similar constraints, into one concise constraints block.

Dimension	Reasoning	Score
Conciseness	The body is largely instructional and avoids lecturing on concepts Claude knows, but it is notably redundant: the 4-agent and 9-agent role descriptions, the standard flow, and the output format overlap with the 核心技能 section and restate material also present in the reference files, so it could be tightened significantly.	2 / 3
Actionability	Provides a concrete, copy-paste-ready Markdown output template with exact section structure, plus specific examples of titles/hashtags, a named meme list, named historical figures, and a quality-check checklist — highly actionable for an instruction-only creative skill.	3 / 3
Workflow Clarity	The standard flow is clearly sequenced (理解需求→素材准备→文案创作→质量检查) with an explicit validation step and a feedback loop ('如不达标，返回至创作阶段微调'), and the single-agent and full-pipeline modes add timing checkpoints and retry behavior.	3 / 3
Progressive Disclosure	SKILL.md offers a clear overview with well-signaled one-level-deep references (all referenced files and agent-roles.md anchors resolve to real content) plus a 资源索引 navigation section, but substantial reference-grade detail (the full 9-agent architecture and role descriptions) is inlined rather than split out, so content is not cleanly separated.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 conveys the skill's creative purpose in third person, but it reads as a capability summary rather than a trigger-oriented description: it lacks an explicit 'when to use' clause and natural trigger phrasings, capping completeness and trigger quality at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks for historical-figure interview scripts, fun history short-video content, or 短视频文案 blending history with internet memes.'

Reframe to surface the natural phrases users actually say ('历史人物访谈', '趣味历史短视频', '古今反差文案') as trigger keywords.

List a couple more concrete actions (e.g. 'design titles/hashtags, draft host Q&A segments, add shot/expression cues') to lift specificity toward 3.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete outputs ('生成历史名人现代访谈短视频文案', '创作具有传播力的虚构趣味内容'), but does not enumerate multiple distinct concrete actions like a level-3 anchor would.	2 / 3
Completeness	Clearly states what the skill does (generates interview short-video scripts), but there is no 'Use when...' clause or equivalent explicit trigger guidance, so 'when' is missing and completeness is capped at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Contains relevant natural-ish terms ('历史名人访谈', '短视频文案', '趣味历史内容'), but they are framed as a capability description rather than natural user trigger phrasings, and common variations are missing.	2 / 3
Distinctiveness Conflict Risk	The niche (historical-figure modern-interview comedy scripts with memes) is fairly specific, but the generic '虚构趣味内容' framing and absence of explicit distinct triggers leave it somewhat overlap-prone rather than a clearly distinct niche.	2 / 3
	Total	8 / 12 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: anbeime/skill
Path: skills/historical-interview-scripts/historical-interview-scripts/SKILL.md
Commit: f595e96

Reviewed: about 13 hours 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.