viral-video-copywriting

专业的爆款短视频文案创作工具。通过对标抖音爆款视频，智能提取视频内容，深度拆解爆款因素，并结合用户需求创作出符合爆款规律的新文案。适用于短视频创作者、运营人员提升内容质量。

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/viral-video-copywriting/viral-video-copywriting/SKILL.md

Quality

Content

62%

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

The body delivers a clear, well-sequenced multi-step workflow with genuine error-recovery and checklists, but it is token-heavy, reuses a hardcoded script path, and duplicates the analysis framework that already exists as a reference file.

Suggestions

State the ±5% length rule once and reference it; remove the repeated restatements in the length list, comparison table, and originality statement.

Use a relative script path consistent with the resource index (scripts/extract_douyin_video.py) instead of the hardcoded /workspace/projects/... absolute path so commands are copy-paste ready.

Slim Step 2 to a brief pointer ('See references/analysis-framework.md for the six analysis dimensions') instead of reproducing the full dimension list inline, removing the duplication with the reference file.

Dimension	Reasoning	Score
Conciseness	Mostly specific domain guidance, but verbose: the ±5% length rule is restated in four places (Step 4 principle, the length list, the comparison table, and the originality statement) and the multi-blank output template could be tightened, so it is not the lean score-3.	2 / 3
Actionability	Provides a concrete script command, explicit input fields (方式A/B), a worked example, and a copy-paste output template, but the example command hardcodes an absolute path (/workspace/projects/...) that does not match the bundle location, so it is not fully copy-paste ready as a 3 requires.	2 / 3
Workflow Clarity	A clearly sequenced 五步法 with an explicit error-recovery feedback loop in Step 1 (auto-extract → fall back to manual 方式B) and an originality-check gate in Step 4, matching the 'clear sequence with validation steps and feedback loops' anchor.	3 / 3
Progressive Disclosure	References are real, one-level-deep, and well-signaled in the resource index with '何时读取' cues, but the full six analysis dimensions are duplicated inline in Step 2 while also living in references/analysis-framework.md — content that should be separate is inline, so it is not the appropriately-split 3.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 states concrete capabilities and occupies a distinct niche, but it lacks an explicit 'Use when…' trigger and relies on some marketing buzzwords, so the 'when to use' guidance stays implied rather than explicit.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to write viral short-video copy or wants to benchmark a Douyin/抖音 video to learn its爆款 structure.'

Replace buzzword padding like '智能提取视频内容' with plain phrasing ('extract video metadata and subtitles') so trigger terms read as what a user would naturally say.

Surface natural keyword variants users actually say (e.g. '短视频文案', '抖音文案', '口播稿', '爆款脚本') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names three concrete actions — "提取视频内容", "深度拆解爆款因素", "创作出符合爆款规律的新文案" — matching the 'lists multiple specific concrete actions' anchor rather than the score-2 'some actions but not comprehensive'.	3 / 3
Completeness	Clearly answers 'what' (extract, deconstruct, create copy) but 'when' is only implied via the audience clause "适用于短视频创作者、运营人员提升内容质量"; per the guideline a missing explicit 'Use when…' trigger caps completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant natural domain terms ("爆款短视频文案", "抖音爆款视频", "运营人员") but leans on marketing jargon ("智能提取", "爆款规律") and omits common conversational variations a user would actually say, so it is not the full coverage of a 3.	2 / 3
Distinctiveness Conflict Risk	The niche is highly specific — Douyin/short-video viral copywriting — so it is clearly distinguishable and unlikely to trigger the wrong skill, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: anbeime/skill
Path: skills/viral-video-copywriting/viral-video-copywriting/SKILL.md
Commit: f595e96

Reviewed: about 12 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.