输入一句关于今天废话的自嘲句，AI即时评定废物等级Lv1~Lv10并给幽默毒舌点评，支持中英双语。
Security Analysis
high confidenceThis is a small, instruction-only humor skill whose requested footprint (no installs, no env vars, no files) matches its stated purpose of grading and roasting a user-provided self-deprecating sentence.
Name, description, and SKILL.md all describe a short-text humor/roast generator; there are no unrelated environment variables, binaries, or installs requested — the requirements align with the stated purpose.
Runtime instructions are limited to parsing user input, producing a Lv1–Lv10 rating, a humorous comment, and optional extras; the SKILL.md does not direct reading of files, system configuration, or transmission of data to external endpoints.
No install spec or code files are present (instruction-only skill), so nothing is written to disk or downloaded during installation.
The skill declares no required environment variables, credentials, or config paths — there is no disproportionate request for secrets or unrelated service access.
Flags are normal (always:false, user-invocable:true, model invocation allowed). The skill does not request permanent presence or privileged access to other skills or system settings.
Guidance
This skill appears coherent and low-risk: it only converts short user sentences into a humorously critical rating and comment and does not request credentials or filesystem access. Consider the following before installing: (1) content risk — outputs are intentionally 'toxic' / sarcastic by design and may offend or violate workplace/content policies, so restrict use in sensitive contexts; (2) moderation — if you want to prevent profanity or overly aggressive comments, ask for a 'milder' or 'safe-mode' variant in the skill or set guardrails; (3) autonomy — the skill is user-invocable and not forced always-on, but the platform allows autonomous invocation by default — if you prefer manual control, ensure agent settings prohibit autonomous skill runs. Otherwise, there are no red flags suggesting hidden behavior.
Latest Release
v1.0.0
- Initial release of "一句话鉴定你今天有多废" skill. - Enter a brief self-mocking sentence to receive a waste level (Lv1–Lv10) plus a witty roast. - Supports both Chinese and English; output matches input language. - Output format includes: large-font waste level, 1–3 lines of savage commentary, and random fun easter eggs. - Judgement adapts to how "waste" your day sounds (pure lazy to high-achiever, with proper humor flip). - Users can request more sarcastic or gentle responses; interaction designed for stress relief and fun sharing.
More by @swiftuis
Published by @swiftuis on ClawHub
