Skills, prompts, agents, automations, and files from people who use them in real work. Every listing is reviewed before it goes live.
15 listings for “ci”
A Node.js script that grades a JSONL file of model outputs against your written rubric with an OpenAI judge model, returning a 1-5 score and reasons per case, a pass rate, and CI-friendly exit codes.
ALAISkillHub Library
A dependency-free Python script and GitHub Actions workflow that find broken relative links and missing #heading anchors in Markdown files, without making any network calls.
ALAISkillHub Library
A strict JSON Schema plus extraction prompt that turns a meeting transcript into decisions, action items with owners and due dates, open questions and risks, each backed by a verbatim quote so readers can verify it.
ALAISkillHub Library
A custom GPT for support team leads and QA specialists: paste a ticket conversation and it scores the agent's replies against your QA rubric, quotes the evidence for each score, and writes short, specific coaching notes the agent can act on.
ALAISkillHub Library
Turns raw meeting notes or a transcript into a clean list of decisions, action items with owners and dates, open questions, and a ready-to-send recap. Unassigned work is called out, not quietly given to someone.
ALAISkillHub Library
Labeler guidelines for comparing two model responses side by side: a priority order for deciding (safety, correctness, instructions, helpfulness, clarity), label definitions, per-response flags, rationale examples and edge cases.
ALAISkillHub Library
A custom GPT for content editors, designers and developers: upload an image with its surrounding context and it decides whether the image is informative, functional or decorative, then writes or reviews the alt text and any longer description it needs.
ALAISkillHub Library
Reviews the text of a landing page for a specific visitor and goal: what a first-time visitor understands in five seconds, where they will get stuck, and prioritised rewrites for the sections that matter most.
ALAISkillHub Library
A configured assistant for support agents: paste a ticket, get a category, priority, sentiment, an escalation decision with the reason, and a reply draft in your tone. Works as a custom GPT, Claude Project or Gemini Gem.
ALAISkillHub Library
Synthesises notes or transcripts from several user interviews into findings that each cite the participants and quotes behind them, with strength ratings, contradictions and the limits of what was learned.
ALAISkillHub Library
Restructures a long update, email or memo so the decision or ask comes first, followed by only the context a busy reader needs. For anyone writing to executives, clients or cross-functional leads.
ALAISkillHub Library
A Claude Skill for product managers: give Claude notes, a problem statement or a feature request thread, and it produces a PRD in a consistent template with goals, non-goals, user stories, acceptance criteria and an explicit open-questions list instead of invented answers.
ALAISkillHub Library
A Gemini Gem for sales reps: it plays a realistic buyer who raises objections based on your product and deal context, then gives specific feedback on each answer you give, with a short debrief at the end.
ALAISkillHub Library
A Claude Project for analysts, students and product teams reading academic papers: upload a PDF and get a structured summary where each point cites the section or page it came from, with methods, limitations and what the paper does not show.
ALAISkillHub Library
Turns several resolved tickets about the same problem into a self-service help article with a symptom-based title, steps, troubleshooting and a clear contact path. For support leads reducing repeat tickets.
ALAISkillHub Library