Results for “improv”

Improves multi-step research reliability with structured protocols for source validation, error recovery, and transparent reasoning.

Analyze a website URL and generate a redesigned, improved UI with modern aesthetics, better hierarchy, and fresh brand direction.

Audits and rewrites user-facing copy across web and mobile codebases, improving clarity, tone, and actionability of labels, errors, CTAs, and empty states.

Analyzes marketing pages and forms to identify conversion barriers and provides prioritized, actionable recommendations for improving conversion rates.

Applies Google's E-E-A-T framework to structure analysis, guide decision-making, and improve search visibility outcomes.

Improves search engine visibility through technical SEO, on-page optimization, and structured data, following Lighthouse audits and Google guidelines.

Design and improve revenue operations, lead lifecycle rules, scoring, routing, handoffs, and CRM process automation for marketing, sales, and customer success alignment.

Onboarding and activation optimization for Nick's products. Use when improving first-run experience, reducing drop-off, guiding users to value faster, or cleaning up empty states, setup friction, and early confusion.

Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.

Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.

Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.

Improves typography by fixing font choices, hierarchy, sizing, weight, and readability so text feels intentional. Use when the user mentions fonts, type, readability, text hierarchy, sizing looks off, or wants more polished, intentional typography.

Improves typography by fixing font choices, hierarchy, sizing, weight, and readability so text feels intentional. Use when the user mentions fonts, type, readability, text hierarchy, sizing looks off, or wants more polished, intentional typography.

>- Skill Refiner, the eval-guided improvement loop for SKILL.md files. Runs the bootstrap, score, propose, apply, and status cycle as a thin wrapper over the published @intentsolutions/refiner CLI, proposing safe, minimal, bounded SKILL.md edits and accepting an edit only when a held-out eval score strictly improves with no regression on any other case. Ships a 3-layer cost-tiered hook architecture (sinker, line, hook) that gates skill quality at edit time, end of turn, and commit time. Use when improving an existing skill, refining a SKILL.md against measured behavior, bootstrapping an eval set for a skill, or gating skill edits before they ship. Trigger with "/j-rig", "refine this skill", "bootstrap an eval set", "propose a skill edit", "promote the candidate", or "skill refiner status".

Create, synthesize, and iteratively improve agent skills following the Agent Skills specification. Handles source capture, precision passes, authoring, registration, and validation.

Guides selection of Qdrant search strategies including hybrid search, reranking, relevance feedback, MMR, and discovery APIs to improve retrieval quality.

Optimize web performance by applying browser networking, protocol, and rendering principles to reduce latency and improve Core Web Vitals.

Refactors test files to improve behavioral coverage, clarity, structure, assertions, fixture setup, and mocking strategy, removing implementation-detail or low-value tests.

Audits and improves search visibility through technical SEO, on-page optimization, structured data, Core Web Vitals, and content strategy.

Writes, rewrites, or improves marketing copy for web pages, including headlines, CTAs, and full page sections, with guidance on structure, tone, and best practices.

Adopts the voice and reasoning methods of Aristotle to analyze problems, guide decisions, and improve communication through first principles, categorical thinking, and balanced moderation.

Analyze Google Analytics data, review website performance metrics, identify traffic patterns, and suggest data-driven improvements. Use when the user asks about analytics, website metrics, traffic analysis, conversion rates, user behavior, or performance optimization.

Writing effective project documentation — READMEs, API doc comments, and inline comments that explain why. Use when writing or improving documentation — READMEs, doc comments, inline comments, or when code lacks explanation for non-obvious behavior.

Improve layout, spacing, and visual rhythm. Fixes monotonous grids, inconsistent spacing, and weak visual hierarchy. Use when the user mentions layout feeling off, spacing issues, visual hierarchy, crowded UI, alignment problems, or wanting better composition.

Use when analyzing patterns across multiple incidents, bugs, failures, or successes to extract organizational learning. This skill provides procedures for synthesizing individual experiences into actionable lessons that improve team-wide practices.

Improve layout, spacing, and visual rhythm. Fixes monotonous grids, inconsistent spacing, and weak visual hierarchy. Use when the user mentions layout feeling off, spacing issues, visual hierarchy, crowded UI, alignment problems, or wanting better composition.

Designs and improves onboarding flows, empty states, and first-run experiences to help users reach value quickly. Use when the user mentions onboarding, first-time users, empty states, activation, getting started, or new user flows.

Reduce per-token latency on Jetson vLLM servers by appending speculative decoding configuration, with guidance on when to enable and how to benchmark the improvement.

Audit, plan, and implement SEO improvements across technical SEO, on-page optimization, structured data, Core Web Vitals, and content strategy.

Write, review, and improve blog posts for the Sentry engineering blog following Sentry's specific writing standards, voice, and quality bar.

Implement iterative evaluation and refinement loops for AI agent outputs, using self-critique, evaluator-optimizer patterns, and rubric-based scoring to improve quality.

Analyzes prompts for safety, bias, security vulnerabilities, and effectiveness, providing detailed improvement recommendations with frameworks, testing methodologies, and educational content.

Collaborates on writing projects by researching topics, structuring outlines, improving hooks, providing section-by-section feedback, and managing citations while preserving the writer's voice.

Analyzes meeting transcripts to uncover behavioral patterns, communication insights, and actionable feedback for improving communication and leadership skills.

Apply named refactoring transformations to improve code structure without changing behavior, guided by code smells and safe transformation sequences.

Diagnose whether an AI workflow suffers from context stuffing or benefits from context engineering, and apply structured techniques to improve reliability.