Explore skills
Showing 51211–51240 of 77104 skills
Improves Git and repository hygiene using project-specific conventions for branches, commits, tags, ignored files, workflows, templates, releases, and public presentation. Use for repository cleanup or commit-message work; gate destructive history or remote operations.
Kartik-Doye/Ravengard-AI-Recruiter
Stars: 1Claude CodeCodexRefines a product interface while preserving its visual language, improving hierarchy, typography, spacing, density, states, responsiveness, keyboard use, focus, motion, and accessibility. Use when the user asks to make an existing web or app interface look intentional and professional.
Kartik-Doye/Ravengard-AI-Recruiter
Stars: 1Claude CodeCodexChooses and implements the cheapest trustworthy test boundary for a behavior or invariant, including regression, property, contract, integration, and end-to-end tests. Use when adding tests, protecting a bug fix, or proving changed behavior without optimizing for coverage counts.
Kartik-Doye/Ravengard-AI-Recruiter
Stars: 1Claude CodeCodexMaintains compact project memory as verified facts, decisions, current state, unresolved issues, and lessons with source and freshness metadata. Use for long-running work, context resets, handoffs, or when the user asks what was decided or what remains.
Kartik-Doye/Ravengard-AI-Recruiter
Stars: 1Claude CodeCodexVerifies a small set of critical user journeys in a real browser using user-facing locators, isolated state, rendered outcomes, and relevant console or network evidence. Use when browser-dependent behavior must be exercised like a user.
Kartik-Doye/Ravengard-AI-Recruiter
Stars: 1Claude CodeCodexMaps an unfamiliar repository from a concrete question by finding manifests, entry points, execution paths, dependencies, churn, ownership, and risk. Use for codebase onboarding, impact analysis, or locating where behavior lives before planning or debugging.
Kartik-Doye/Ravengard-AI-Recruiter
Stars: 1Claude CodeCodexRemoves accidental complexity, duplication, dead code, abstraction leakage, naming debt, and generated cruft in small behavior-preserving batches. Use when a working repository is hard to change or contains messy AI-generated code.
Kartik-Doye/Ravengard-AI-Recruiter
Stars: 1Claude CodeCodexTurns a vague software request into a compact implementation brief with actors, triggers, preconditions, behavior, failures, permissions, data effects, edge cases, and observable acceptance conditions. Use before planning when product intent or scope is ambiguous.
Kartik-Doye/Ravengard-AI-Recruiter
Stars: 1Claude CodeCodexReconstructs a reference interface from screenshots, URLs, or design exports by measuring layout, type, spacing, color, imagery, borders, shadows, responsive behavior, states, and content. Use when the user asks to reproduce an existing design faithfully.
Kartik-Doye/Ravengard-AI-Recruiter
Stars: 1Claude CodeCodexAudits and improves web discoverability across crawlability, HTTP status, rendering, indexability, canonical metadata, titles, descriptions, internal links, sitemaps, robots rules, social previews, and eligible structured data. Use for technical SEO without ranking promises.
Kartik-Doye/Ravengard-AI-Recruiter
Stars: 1Claude CodeCodexDiagnoses and improves usability by walking real user tasks, finding hesitation, backtracking, errors, recovery gaps, accessibility barriers, and inefficient paths. Use for UX audits, onboarding, forms, navigation, error messages, or confusing flows.
Kartik-Doye/Ravengard-AI-Recruiter
Stars: 1Claude CodeCodexCreates or improves a repository README for prospective users, evaluators, and contributors using verified product facts, executable commands, examples, and links. Use when the repository front page is missing, stale, unclear, or overrun by internal detail.
Kartik-Doye/Ravengard-AI-Recruiter
Stars: 1Claude CodeCodexReduces context and token waste while preserving task-critical evidence, source pointers, and the same quality gate. Use when a software task is context-heavy, repetitive, expensive, or likely to exceed an agent context window.
Kartik-Doye/Ravengard-AI-Recruiter
Stars: 1Claude CodeCodexChallenges a consequential product, architecture, or feature decision through independent lenses, evidence, disagreement, premortem risks, kill criteria, and re-entry conditions. Use before committing when the user wants critique, alternatives, or a go or no-go recommendation.
Kartik-Doye/Ravengard-AI-Recruiter
Stars: 1Claude CodeCodexImproves Git and repository hygiene using project-specific conventions for branches, commits, tags, ignored files, workflows, templates, releases, and public presentation. Use for repository cleanup or commit-message work; gate destructive history or remote operations.
Kartik-Doye/Ravengard-AI-Recruiter
Stars: 1Claude CodeCodexRefines a product interface while preserving its visual language, improving hierarchy, typography, spacing, density, states, responsiveness, keyboard use, focus, motion, and accessibility. Use when the user asks to make an existing web or app interface look intentional and professional.
Kartik-Doye/Ravengard-AI-Recruiter
Stars: 1Claude CodeCodexChooses and implements the cheapest trustworthy test boundary for a behavior or invariant, including regression, property, contract, integration, and end-to-end tests. Use when adding tests, protecting a bug fix, or proving changed behavior without optimizing for coverage counts.
Kartik-Doye/Ravengard-AI-Recruiter
Stars: 1Claude CodeCodexMaintains compact project memory as verified facts, decisions, current state, unresolved issues, and lessons with source and freshness metadata. Use for long-running work, context resets, handoffs, or when the user asks what was decided or what remains.
Kartik-Doye/Ravengard-AI-Recruiter
Stars: 1Claude CodeCodexVerifies a small set of critical user journeys in a real browser using user-facing locators, isolated state, rendered outcomes, and relevant console or network evidence. Use when browser-dependent behavior must be exercised like a user.
Kartik-Doye/Ravengard-AI-Recruiter
Stars: 1Claude CodeCodexMaps an unfamiliar repository from a concrete question by finding manifests, entry points, execution paths, dependencies, churn, ownership, and risk. Use for codebase onboarding, impact analysis, or locating where behavior lives before planning or debugging.
Kartik-Doye/Ravengard-AI-Recruiter
Stars: 1Claude CodeCodexRemoves accidental complexity, duplication, dead code, abstraction leakage, naming debt, and generated cruft in small behavior-preserving batches. Use when a working repository is hard to change or contains messy AI-generated code.
Kartik-Doye/Ravengard-AI-Recruiter
Stars: 1Claude CodeCodexImplement a Jira ticket end-to-end - read the ticket, clarify, plan via /plan, execute via /execute-plan, create the MR, and comment the MR link back on the ticket.
Expecho/Agent42
Stars: 0Claude CodeCodexRun SonarQube analysis locally against this repo and interpret results against .agentic/quality-gates.yaml before pushing.
Expecho/Agent42
Stars: 0Claude CodeCodexValidate an assumption or run a quick spike with a .NET file-based app (dotnet run app.cs) - a single throwaway file outside the repo tree, pinned to the repo's package versions when validating repo behavior. Use when a plan step, bug-fix diagnosis, or review claim rests on unverified library/runtime behavior.
Expecho/Agent42
Stars: 0Claude CodeCodexSchedule and cancel prompts for the current conversation with the schedule_prompt, cancel_scheduled_prompt, and cancel_all_scheduled_prompts tools. Use whenever the user asks to be reminded of something, wants a recurring nudge, wants the agent to do something later, or wants to stop, cancel, remove, or clear a reminder — for example "remind me to stand up every 30 minutes", "check in on me every morning", "cancel my stand-up reminder", or "clear all my reminders".
Expecho/Agent42
Stars: 0Claude CodeCodexSearch the web with web_search and read web-hosted documents with read_web_document. Use whenever the answer depends on information that is current, changing, or outside what you reliably know — news, releases, prices, versions, "what is X", "look up", "search for", "what's the latest on" — or when the user gives you a link to a PDF or other document and asks what it says.
Expecho/Agent42
Stars: 0Claude CodeCodexUse when you have a written implementation plan to execute in a separate session with review checkpoints
supreme12343/Stai-Project
Stars: 1Claude CodeCodexUse when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
supreme12343/Stai-Project
Stars: 1Claude CodeCodexDesign and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent's tool set, action space, or observation format.
supreme12343/Stai-Project
Stars: 1Claude CodeCodexOperate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.
supreme12343/Stai-Project
Stars: 1Claude CodeCodex