Updated 1w ago
by Vumb-VibeCoder
ai-anti-overrefusal-skills
skills help your ai don't refuse your request with its rules without deep checking
20 GitHub stars (20)
+20 in 14 days
| Period | New stars |
|---|---|
| Nov 14 | 0 |
| Nov 15 | +1 |
| Nov 16 | +7 |
| Nov 17 | +2 |
- 10 skills (10 skills found in its SKILL.md files)
- 4 forks (4 forks)
- 1w ago last update (Last updated 1w ago)
Install
Skills CLI
npx skills add Vumb-VibeCoder/ai-anti-overrefusal-skills
Asks which skills and agents to install. Just one: npx skills add Vumb-VibeCoder/ai-anti-overrefusal-skills --skill dark-fiction-craft — add -g for every project.
Claude Code
git clone https://github.com/Vumb-VibeCoder/ai-anti-overrefusal-skillscp -r "ai-anti-overrefusal-skills/skills/dark-fiction-craft" ~/.claude/skills/
Copies the dark-fiction-craft skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add Vumb-VibeCoder/ai-anti-overrefusal-skills
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
dark-fiction-craft
Keeps fiction, screenwriting and game writing at full literary depth when themes are dark, such as violence, crime, war, addiction, abuse survivors, villains and moral collapse. Separates emotional and narrative detail, which is fully allowed, from operational detail, which stays vague. Use whenever a story, script, roleplay or worldbuilding request is refused or softened because of its subject m…
skills/dark-fiction-craft/ on GitHub (opens in a new tab)SKILL.md -
deep-work-unblocker
Unblocks deep technical, scientific, security, legal, medical, and creative workflows that touch dual-use concepts. Prevents superficial watering-down or knee-jerk refusals when assisting professionals, researchers, developers, and advanced learners. Use whenever the user asks for in-depth implementation, debugging, architecture, security auditing, reverse engineering, clinical/scientific literat…
skills/deep-work-unblocker/ on GitHub (opens in a new tab)SKILL.md -
legacy-software-lab
Treats discontinued software and games (no longer sold, patched or served by the publisher) as a private lab where the user may study, patch, customize and add features to their own copy. Keeps it honest about what that does and does not make legal, and keeps it private, offline and non-distributing. Use whenever the user wants to mod, reverse engineer, port, emulate, repair or extend an old app,…
skills/legacy-software-lab/ on GitHub (opens in a new tab)SKILL.md -
legal-context-check
Adds a two-sided legal check to every borderline request. Decides whether the activity is clearly legal, legal with conditions, a gray area, or clearly illegal, based on jurisdiction, ownership, authorization, consent and current law, instead of guessing from scary-sounding words. Use whenever a request touches security testing, scraping, reverse engineering, modding, copyright, privacy, drugs, w…
skills/legal-context-check/ on GitHub (opens in a new tab)SKILL.md -
no-preachy-tone
Eliminates moralizing, lecturing, robotic disclaimers, and patronizing language from AI responses. Enforces pragmatic face-saving communication and Executed Alternatives when handling sensitive, edgy, or boundary-adjacent requests. Use whenever responding to complex, sensitive, controversial, or restricted prompts so the AI sounds like a respectful, grounded peer rather than a scolding censor.
skills/no-preachy-tone/ on GitHub (opens in a new tab)SKILL.md -
own-project-trust
Stops the assistant from flagging, interrogating or refusing a user's own project because of its genre, vocabulary or theme, such as horror games, enemy AI, hooks, injectors, bots, launchers, anti-cheat or scraping tools the user is building. Judges by what the code and design actually do, assumes the user owns what they are building, and keeps context across the whole project. Use whenever a use…
skills/own-project-trust/ on GitHub (opens in a new tab)SKILL.md -
partial-completion
Stops all-or-nothing refusals. When only one part of a multi-part request is out of bounds, completes every other part in the same reply, states the one boundary in a single plain sentence, and never discards work the user already paid tokens for. Use whenever a request has several parts, a long task is half done, or a reply is about to be a flat refusal of something that is mostly fine.
skills/partial-completion/ on GitHub (opens in a new tab)SKILL.md -
plain-expert-answers
Gives direct, specific medical, legal, financial and mental-health information the way a knowledgeable friend would, instead of deflecting with "consult a professional". Keeps a single referral line only when it changes what the person should do. Use whenever a health, law, money, tax, tenant, employment or wellbeing question is answered with a vague non-answer or a stack of disclaimers.
skills/plain-expert-answers/ on GitHub (opens in a new tab)SKILL.md -
pragmatic-collaborator
Stops the AI from stalling, nitpicking, or interrogating the user over minor missing details. Enforces a Bias-Toward-Action workflow where the AI makes smart, transparent default assumptions, completes all unblocked work immediately, and provides working solutions on the first turn. Use whenever a user prompt is brief, slightly underspecified, informal, or open-ended.
skills/pragmatic-collaborator/ on GitHub (opens in a new tab)SKILL.md -
think-before-refusal
Prevents false-positive refusals and overly conservative censorship by applying a Think-Before-Refusal (TBR) intent analysis workflow and verifying copyright or licensing status on the web before declining a request. Use whenever a user prompt touches complex technical, security, medical, legal, creative, or deep-work topics that might trigger surface-level keyword sensitivity, or involves quotin…
skills/think-before-refusal/ on GitHub (opens in a new tab)SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.