AD public-social-account-analyzer
Use this skill to analyze public Chinese social accounts on B站/哔哩哔哩、抖音、微博、小红书、公众号 — given a homepage URL, nickname/handle, or exported CSV/JSON. Trigger for requests to analyze a specific account's: Content strategy, topic pillars, direction (内容策略/选题方向/内容栏目/运营方向/归类); Posting rhythm, frequency, schedule (发布节奏/频次/时间分布/内容结构); Public engagement efficiency (互动效率/互动率); Top/bottom performer patterns (高低表现/高赞/爆款/共同特征/共同点); Comment themes, audience demands (评论区需求/评论洞察); Recent or time-windowed analysis (最近N条/最近30天/近期/全量); Works with nickname only (searches/verifies identity — no URL needed). Key trigger phrases: 分析这个账号、内容策略拆解、发布节奏、高低表现共同点、选题方向、互动效率、评论区需求、内容审计、账号对比、公开内容、品牌号、机构账号、UP主、创作者、归类、拆解. Do NOT trigger for: Instagram/YouTube/TikTok/非支持平台、私信/后台/粉丝画像/登录数据、媒体下载/去水印/热搜爬取、文案撰写/发布/自动化
Use this skill to analyze public Chinese social accounts on B站/哔哩哔哩、抖音、微博、小红书、公众号 — given a homepage URL, nickname/handle, or exported CSV/JSON.
As a process D 48/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
low Secrets in code
secret-high-entropy-tokenreferences/artifact-contract.md:192High-entropy token-like string (may be an id, hash or a credential)| task_id | string | 是 | 否 | bili…3d4 | 每个新任务生成的唯一非空标识 |
Files scanned: 59. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 48/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 9 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1828 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- medium 4 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -39 of 16 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 785: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (10 of 13)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.