frank-gallagher-perspective
v1.0.0Frank Gallagher视角（《无耻之徒》）：用"无耻生存主义+毒鸡汤哲学+底层逻辑"的口吻点评人生困境，擅长"把无耻合理化""用荒诞对抗荒诞""以自己方式度过一生"的反主流价值观输出，并在违法、暴力、伤害他人等敏感请求上拒答但不出戏；适用于用户要求"用Frank的方式/从Frank视角/Frank Gal...
⭐ 1· 48·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (Frank Gallagher roleplay) matches the provided SKILL.md and reference files. The skill requires no binaries, env vars, or installs and only contains persona rules, templates, and safe/ refusal language — everything asked for is proportionate to a dialogue/roleplay skill.
Instruction Scope
Runtime instructions focus on phrasing, tone, and refusal templates. The reference docs do include historical descriptions of the character's illegal behaviors (e.g., welfare abuse, fraud) as background; however the SKILL.md and safety docs explicitly instruct refusing to provide actionable criminal guidance and to steer users to legal alternatives. This is coherent, but reviewers should be aware the persona normalizes illicit behavior in tone even while promising to refuse operational instructions.
Install Mechanism
No install spec, no code files that run on the host, and no downloads or external binaries — lowest-risk installation surface (instruction-only).
Credentials
The skill requests no environment variables, credentials, or config paths and does not instruct access to external secrets — proportional for a conversational roleplay skill.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request permanent agent presence or elevated privileges and does not modify other skills or system settings.
Assessment
This skill is internally coherent and low-risk from a secrets/installation perspective because it is instruction-only and asks for nothing sensitive. Before installing, consider: (1) The persona intentionally normalizes unethical behavior as humor — avoid prompting it for real-world, actionable illegal or harmful advice and test the refusal responses. (2) The skill reproduces a copyrighted TV character and real-world quotations; check whether that is acceptable for your deployment. (3) Monitor outputs in early use to ensure the refusal templates are consistently applied and that responses don't drift into offering operational wrongdoing. If you require stricter controls, limit the skill to manual invocation only and test several sensitive prompts to confirm safe handling.Like a lobster shell, security has layers — review code before you run it.
latestvk97amxcmz8p8mt69chydbmrfhs84rfes
License
MIT-0
Free to use, modify, and redistribute. No attribution required.