ChloeVPin
UserANGWY: Adversarial Rigor Protocol - converts high-pressure input into rigorous output for GPT-5.6 and frontier models
Categories
Indexed Skills (17)
angwy
Converts ordinary, stern, hostile, impatient, or high-pressure user input into consistently rigorous, high-quality model output. Use when the user is impatient, demanding, hostile, or explicitly requests adversarial rigor, pressure prompting, or hostile audit mode. Activates adversarial self-review, anti-sycophancy, forced verification, and loss-aware framing. Always-on by default; every input is treated as high-standard regardless of tone.
angwy
Use when the user is impatient, hostile, or demands adversarial rigor. Converts pressure into rigorous output, forces verification, and kills sycophancy. Always-on by default. Do not use for casual chat.
apple-design
Apple's approach to interface design and fluid, physical motion, translated for the web. Revamped from Emil Kowalski's apple-design skill (MIT). Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), color systems, dark mode, SF Symbols, layout, accessibility, or the design foundations (feedback, spatial consistency, restraint) behind Apple-style interfaces.
fluid
Use when building or reviewing gesture-driven UI, spring animations, and Apple-style interfaces. Enforces interruptibility, velocity-aware springs, and HIG principles.
tdd
Use when writing new features or fixing bugs to enforce RED-GREEN-REFACTOR. Forces the agent to write a failing test, quote the failure, write implementation, and pass. Do not use for simple refactors.
cleanme
Safety-first macOS storage cleanup for AI agents. Read-only audit first, strict whitelists, explicit per-path approval, Trash by default. Use when the user mentions full disk, free space, storage cleanup, or reclaiming disk on macOS.
a11y
Use when asked to audit, fix, or test web accessibility against WCAG 2.2 AA. Builds a matrix of states and viewports, runs axe-core, and requires evidence per row. Do not use for generic Lighthouse checks.
mascot
Use when asked to generate a standalone mascot or symbol logo in a playful soft-3D style. Generates one mark without text, tiles, or app-icon containers. Do not use for full brand assets.
prune
Use when asked to clean up, remove unused, or delete dead code. Finds unreferenced symbols, dedupes constants, and removes drift. Requires user approval before editing. Do not use for comments.
why-comments
Use when asked to clean up, remove dumb, or delete obvious comments. Flags comments that restate the code. Keeps why-comments and license headers. Do not use for dead code or commented-out code.
cleanme
Use when asked to free space or clean storage on macOS. Runs a read-only audit, presents a risk-ranked table, and moves approved paths to Trash. Never uses rm -rf without explicit path approval.
playful-mascot-logo-generator
Generate original, premium standalone mascot and symbol logos in a tightly controlled playful soft-3D style. Use when a user provides a logo idea, product concept, brand summary, feature description, or vague project brief and wants a polished, memorable visual mark. This skill generates the logo mark only. Never use an app-icon tile, rounded-square container, border, mockup, wordmark, UI chrome, or presentation scene.
art-director
Use for OG images, social previews, and brand art. Generates text-free base artwork prompts and separate overlay specs. Prevents text leakage into image models. Do not use for a standalone mascot mark.
for-you
Use when analyzing the X algorithm, explaining For You feed behavior, or optimizing posts. Maps retrieval, ranking weights, and visibility filtering to the open-source codebase. Read home-mixer/params/param.rs before answering.
brand-asset-art-director
Produces high-quality, text-free image-generation prompts and separate post-production overlay specifications for any brand asset. Use for Open Graph artwork, social previews, launch thumbnails, branded link cards, hero banners, email headers, print collateral, display ads, app store screenshots, presentation covers, branded illustrations, and revisions of weak AI-generated brand art. Prevents product names, taglines, UI copy, labels, logos, and other text-bearing language from leaking into generated artwork. Compiles brand evidence into one ownable visual concept. Avoids generic SaaS imagery. Adapts prompts for Midjourney v7, FLUX, GPT-image, and SDXL/Stable Diffusion. Runs concept, composition, text-leakage, thumbnail, completeness, and brand-fidelity audits before returning a prompt.
test-driven-development
TDD for coding agents: RED-GREEN-REFACTOR with hard gates, stack discovery, anti-reward-hacking checks, and mutation-based proof that tests are real.
x-algorithm
Use when creating, reviewing, or improving X posts with guidance grounded in the public X For You algorithm release, or when working with the X For You feed stack including Home Mixer, Phoenix retrieval/ranking, Thunder, Grox content understanding, ads, filters, hydrators, scorers, and recommendation-system inference artifacts.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.