| Skill | Added | Review |
|---|---|---|
debug-companions-prod .agents/skills/debug-companions-prod/SKILL.md Read-only production debugging for the Companions runtime on Railway and box.ascii.dev. Use when production box launches fail, a chat dies or stalls while waiting for input, turns sit queued or interrupted, a Companion appears to reply forever, /healthz is unhealthy, or an operator needs Railway deployment status, redacted runtime logs, provider Box inventory, or named read-only PostgreSQL runtime queries. Every script redacts credentials; the only mutation is a double-gated service restart. | 71 71 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 8d000e5 | |
codebase-design .agents/skills/codebase-design/SKILL.md Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary. | 65 65 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 8d000e5 | |
code-review .agents/skills/code-review/SKILL.md Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X". | 76 76 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 8d000e5 | |
capture-learning-tools .agents/skills/capture-learning-tools/SKILL.md Turn technical conversations, bugs, CI failures, review comments, and repeated agent mistakes into durable project improvements. Use when the user asks what should be automated, documented, tested, added to AGENTS.md/CLAUDE.md, wired into CI, or changed so the same issue does not happen again. This skill is for both non-technical and technical users: it explains the learning in plain English, inspects the repository, chooses the right prevention layer, proposes changes first, and only edits project files when explicitly asked. | 79 79 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 8d000e5 | |
ask-matt .agents/skills/ask-matt/SKILL.md Ask which skill or flow fits your situation. A router over the skills in this repo. | 54 54 Impact — No eval scenarios have been run Securityby High Do not use without reviewing Version: 8d000e5 | |
teach-impeccable archived/legacy-companion/.agents/skills/teach-impeccable/SKILL.md One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines. | 86 86 2.32x Agent success vs baseline Impact 100% 2.32xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: 90804d3 | |
quieter archived/legacy-companion/.agents/skills/quieter/SKILL.md Tone down overly bold or visually aggressive designs. Reduces intensity while maintaining design quality and impact. | 76 76 1.05x Agent success vs baseline Impact 91% 1.05xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: 90804d3 | |
polish archived/legacy-companion/.agents/skills/polish/SKILL.md Final quality pass before shipping. Fixes alignment, spacing, consistency, and detail issues that separate good from great. | 82 82 1.26x Agent success vs baseline Impact 91% 1.26xAverage score across 6 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: 90804d3 | |
optimize archived/legacy-companion/.agents/skills/optimize/SKILL.md Improve interface performance across loading speed, rendering, animations, images, and bundle size. Makes experiences faster and smoother. | 85 85 0.98x Agent success vs baseline Impact 88% 0.98xAverage score across 6 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: 90804d3 | |
onboard archived/legacy-companion/.agents/skills/onboard/SKILL.md Design or improve onboarding flows, empty states, and first-time user experiences. Helps users get started successfully and understand value quickly. | 81 81 1.10x Agent success vs baseline Impact 94% 1.10xAverage score across 6 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: 90804d3 | |
normalize archived/legacy-companion/.agents/skills/normalize/SKILL.md Normalize design to match your design system and ensure consistency | 74 74 1.00x No change in agent success vs baseline Impact 98% 1.00xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: 90804d3 | |
harden archived/legacy-companion/.agents/skills/harden/SKILL.md Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready. | 76 76 1.27x Agent success vs baseline Impact 83% 1.27xAverage score across 6 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: 90804d3 | |
frontend-design archived/legacy-companion/.agents/skills/frontend-design/SKILL.md Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications. Generates creative, polished code that avoids generic AI aesthetics. | 92 92 1.59x Agent success vs baseline Impact 94% 1.59xAverage score across 6 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: 90804d3 | |
extract archived/legacy-companion/.agents/skills/extract/SKILL.md Extract and consolidate reusable components, design tokens, and patterns into your design system. Identifies opportunities for systematic reuse and enriches your component library. | 77 77 1.04x Agent success vs baseline Impact 99% 1.04xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: 90804d3 | |
distill archived/legacy-companion/.agents/skills/distill/SKILL.md Strip designs to their essence by removing unnecessary complexity. Great design is simple, powerful, and clean. | 76 76 1.00x No change in agent success vs baseline Impact 94% 1.00xAverage score across 6 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: 90804d3 | |
delight archived/legacy-companion/.agents/skills/delight/SKILL.md Add moments of joy, personality, and unexpected touches that make interfaces memorable and enjoyable to use. Elevates functional to delightful. | 65 65 0.94x Agent success vs baseline Impact 73% 0.94xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: 90804d3 | |
critique archived/legacy-companion/.agents/skills/critique/SKILL.md Evaluate design effectiveness from a UX perspective. Assesses visual hierarchy, information architecture, emotional resonance, and overall design quality with actionable feedback. | 79 79 2.32x Agent success vs baseline Impact 100% 2.32xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: 90804d3 | |
colorize archived/legacy-companion/.agents/skills/colorize/SKILL.md Add strategic color to features that are too monochromatic or lack visual interest. Makes interfaces more engaging and expressive. | 69 69 1.10x Agent success vs baseline Impact 93% 1.10xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: 90804d3 | |
clarify archived/legacy-companion/.agents/skills/clarify/SKILL.md Improve unclear UX copy, error messages, microcopy, labels, and instructions. Makes interfaces easier to understand and use. | 74 74 1.01x Agent success vs baseline Impact 91% 1.01xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: 90804d3 | |
bolder archived/legacy-companion/.agents/skills/bolder/SKILL.md Amplify safe or boring designs to make them more visually interesting and stimulating. Increases impact while maintaining usability. | 70 70 1.03x Agent success vs baseline Impact 94% 1.03xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: 90804d3 | |
audit archived/legacy-companion/.agents/skills/audit/SKILL.md Perform comprehensive audit of interface quality across accessibility, performance, theming, and responsive design. Generates detailed report of issues with severity ratings and recommendations. | 84 84 1.51x Agent success vs baseline Impact 100% 1.51xAverage score across 6 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: 90804d3 | |
animate archived/legacy-companion/.agents/skills/animate/SKILL.md Review a feature and enhance it with purposeful animations, micro-interactions, and motion effects that improve usability and delight. | 84 84 1.42x Agent success vs baseline Impact 91% 1.42xAverage score across 6 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: 90804d3 | |
adapt archived/legacy-companion/.agents/skills/adapt/SKILL.md Adapt designs to work across different screen sizes, devices, contexts, or platforms. Ensures consistent experience across varied environments. | 74 74 1.16x Agent success vs baseline Impact 94% 1.16xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: 90804d3 |