Results for “improv”

Generate, review, and optimize natural language instructions for Business Central agents (Designer or SDK). Triggers on: agent instructions, InstructionsV1.txt, InstructionsV2.txt, MEMORIZE, qualification rules, agent behavior, instruction keywords, agent task instructions, iterate instructions, or improve agent accuracy. Follows the Responsibilities-Guidelines-Instructions framework with official BC agent runtime keywords.

Run metric-driven iterative optimization loops -- define a measurable goal, run parallel experiments, measure each against hard gates or LLM-as-judge scores, keep improvements, and converge on the best solution. Use when optimizing clustering quality, search relevance, build performance, prompt quality, or any measurable outcome that benefits from systematic experimentation.

Build MCP tools that are sticky for vibe coders and powerful for developersUse when "Designing new MCP tools, Improving tool UX or DX, Writing error messages, Planning tool naming, Discussing user onboarding, Making tools "sticky", Vibe coder experience, mcp, product, ux, dx, vibe-coding, onboarding, developer-experience, tool-design" mentioned.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Use this skill when creating a new Claude skill from scratch, editing or improving an existing skill, or measuring skill performance with evals and benchmarks. Invoke whenever the user says things like 'make a skill for X', 'turn this workflow into a skill', 'test my skill', 'improve my skill', 'run evals', 'benchmark this', or 'optimize my skill description'. Also use proactively when the conversation has produced a repeatable workflow that would benefit from being captured as a skill. Covers the full lifecycle: capture intent, draft SKILL.md, run evals, review with user, iterate, optimize description, package. NOT for general coding help, debugging runtime errors, building MCP servers, writing Claude hooks, or creating plugins - use domain-specific skills for those.

Statistical fine-mapping of GWAS loci using SuSiE, SuSiE-inf, and Approximate Bayes Factors to identify credible sets and posterior inclusion probabilities (PIPs) for causal variant discovery. SuSiE-inf adds an infinitesimal polygenic component for improved calibration at well-powered loci.

Clade goal-driven autonomous improvement loop (Blueprint architecture — deterministic pre/post phases + LLM supervisor/worker nodes, converges when goal met or max-iter hit). NOT the Claude Code built-in /loop (which polls a prompt on an interval like `/loop 5m /foo`) — if the user wants interval polling, route to the built-in.

Guides creation of high-quality Agent Skills with domain expertise, anti-pattern detection, and progressive disclosure best practices. Activate on keywords: create skill, review skill, skill quality, skill best practices, skill anti-patterns, improve skill, skill audit. NOT for general coding advice, slash commands, MCP development, or non-skill Claude Code features.

Build and maintain a model book for Stockbee-style Momentum Burst setups by ingesting screener candidates, updating 3-day and 5-day forward outcomes with MFE/MAE and stop-hit status, and summarizing cohort statistics to improve setup recognition.

Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, macOS-specific APIs, and iOS 26+ Liquid Glass adoption. Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns.

Comprehensive customer success and retention expertise combining onboarding, health scoring, churn prevention, retention strategies, and LTV maximization. Use when designing customer onboarding flows, reducing churn, building health scores, creating retention systems, designing upsells, or improving customer lifetime value. Covers proactive engagement, cancel flows, dunning, re-engagement, and the full customer lifecycle.

Security audit orchestrator for agent skills — scans for prompt injection, data exfiltration, credential theft, supply chain risks, and instruction hierarchy violations before any skill is installed, created, improved, or read from a GitHub repo. Load when creating skills from external sources, when improve-skills reads from GitHub repos, when research-skill fetches community SKILL.md files, when a user installs a third-party skill, or when the user asks to audit skill security, scan for injection, check if a skill is safe, scan all skills, or run a security sweep. Orchestrates all secure-* skills in sequence. Content is SAFE only if ALL secure-* skills return SAFE. 36% of community skills contain flaws (Snyk ToxicSkills 2026). This skill is the first line of defense.

Audits an EXISTING UI/codebase for generic AI patterns and applies targeted craft fixes — layout, interactivity, content, iconography, and code quality — without discarding the project's own identity. Use when a UI looks flat, generic, or "AI-slop" and there is code to improve, not build from scratch. Triggers on: "improve the design", "looks generic", "not polished enough", "redesign this", "elevate the UI", "it looks boring", "make it better looking", "apply taste", "design review". Works with any CSS framework. For designing a NEW project's identity from a brief, use `taste-skill` instead — this skill only upgrades what's already built. Source: github.com/Leonxlnx/taste-skill (redesign-skill), restored to the full checklist + the project-identity rule the earlier port had dropped.

Design, create, audit, and improve Claude Agent Skills with expert-level progressive disclosure. Use when building new skills, reviewing existing skills, debugging activation failures, encoding domain expertise, designing skills for subagent consumption, or understanding platform constraints and distribution surfaces. NOT for general Claude Code features, runtime debugging, non-skill coding, or MCP server implementation.

自动捕获经验并安全进化的技能。触发条件：(1)命令/操作失败时→记ERRORS.md (2)被用户纠正('不对'/'应该是')时→记LEARNINGS.md (3)用户需要不存在的能力时→记FEATURE_REQUESTS.md (4)外部API/工具出错时→记ERRORS.md (5)发现自己知识过时/错误时→记LEARNINGS.md (6)发现更好做法时→记LEARNINGS.md (7)每个任务完成时→回顾过程，有新经验则记LEARNINGS.md。去重原则：如果没有新经验或已有条目已覆盖则跳过不写。每次写入同时在.learnings/CHANGELOG.md追加JSONL日志。经验反复出现≥3次时晋升到AGENTS.md/TOOLS.md/SOUL.md。详见正文。

Expert social media writing skill for creators, professionals, and brands who want to write posts that actually perform. Use this skill whenever the user wants to write, improve, or get help with any social media content — including LinkedIn posts, Twitter/X tweets or threads, Instagram captions, or TikTok captions. Also trigger for: "write a post about", "help me with my LinkedIn", "draft a tweet", "create a thread", "write a caption", "I want to post about", "turn this into a social post", "make this more engaging", or any request to create or improve content for a social platform. Do NOT limit to obvious requests — if the user has an idea, a story, or a piece of content and mentions a platform, use this skill.

Generate competitive SEO content briefs with per-section word counts, competitor scoring, keyword density guidance, and page-type templates. Supports both new page briefs and improve-existing-page briefs. Use when user says "content brief", "write a brief", "content outline", "blog brief", "service page brief", "brief for", "writing brief", "content plan", or "outline for".

Run a structured retrospective after development-phase runs of your product's agents — interview the owner in plain language about what went well and poorly, draft ranked improvement hypotheses, then design and run small n=1/n=2 experiments with pre-declared success criteria, guardrails, stop conditions, and a cost/ROI kill-switch. Load when the user says how did that run go, retro this run, the agent output was bad, what should we improve, draft hypotheses, run a small experiment, or after repeated dev runs of an agentic system produce uneven quality. Priority: output quality over performance over cost, each with diminishing-returns stops. NOT a product A/B test (experimentation), NOT coding-agent harness repair (harness-evolution), NOT production-scale learning (runtime-learning-loop).

Capture an Architecture Decision Record — what was decided, why, what alternatives were considered, and when to revisit. Writes a numbered ADR file to docs/adr/ in the active repo, with consistent formatting that downstream skills (improve-codebase-architecture, refactor-plan) can read. Use right after deciding something non-obvious so the reasoning isn't lost.

Continuous self-improvement through systematic logging, pattern detection, and behavioral updates. Use when: the owner corrects you, a task fails, you discover a better approach, or you notice a recurring pattern. Store raw learnings in .learnings/, update the specific skill or workflow that caused the issue when appropriate, and avoid vague promises to do better.

Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments. Triggers Greptile review, fixes all actionable comments, pushes/re-shelves, re-triggers review, and repeats. Use when the user wants to fully optimize a PR/MR/CL against Greptile's code review standards.

Use this skill when the user asks how to build, measure, or improve safety culture in a motor carrier — leading vs lagging safety indicators, blame-free reporting, near-miss programs, safety committee structure, monthly safety meetings, ATA Safety Management Program guidance, and how to evaluate cultural maturity. Reference ATA SMP + DOT safety culture research.

The art of reviewing code that improves both the codebase and the developer - sharing knowledge, maintaining standards, and building cultureUse when "code review, PR review, pull request, merge request, review comments, LGTM, review feedback, approve PR, request changes, review checklist, code quality, review standards, code-review, pull-request, PR, quality, standards, feedback, collaboration, mentoring" mentioned.

Use to design support incentives that improve behaviour without destroying the metric — pairing pay with guardrails, naming gaming modes, and choosing measures that survive Goodhart pressure. Trigger for "incentive plan", "agent bonus scheme", "SPIFF design", "pay for QA score", "what metric should we bonus", CSAT incentives, or reviewing whether a comp change is driving gaming.

Pre-send email quality review and scoring across 5 dimensions (subject line, copy quality, technical/HTML, deliverability, compliance). Analyzes subject lines, body copy, HTML structure, spam triggers, and CAN-SPAM compliance. Scores 0-100 with detailed recommendations for improvement. Use when user wants to review an email before sending, check email quality, or validate marketing email best practices.

Use when fixing, auditing, improving, or building any web UI — before reading or editing component code. Fires on contrast/a11y/overflow/responsive/hover- focus/layout complaints, polish, audit, or any visual change. Never diagnose a UI defect from code alone: render at real viewports, measure (axe / contrast / a11y tree / console / keyboard / reflow), then cite the measurement.

Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production. Use when "langfuse, llm observability, llm tracing, prompt management, llm evaluation, monitor llm, debug llm, langfuse, observability, tracing, llm-monitoring, evaluation, prompt-management, debugging, analytics" mentioned.

Use to quantify what support quality failures cost — rework, credits, escalation handling, complaints and churn — with the causal limits stated. Trigger for "what do our quality failures cost", "cost of rework in support", "business case for improving quality", "how much is bad support costing us", or a quality investment that needs a number attached.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Use this skill when the user requests to generate, create, or improve documentation for code, APIs, libraries, repositories, or software projects. Supports README generation, API reference documentation, inline code comments, architecture documentation, changelog generation, and developer guides. Trigger on requests like "document this code", "create a README", "generate API docs", "write developer guide", or when analyzing codebases for documentation purposes.

Generate or improve MATLAB help text (documentation comments) for a function, class, or script file following MathWorks standards (H1 line, syntax paragraphs, See Also, 75-char lines). Read BEFORE writing MATLAB help — default patterns (Inputs:/Outputs: lists, block comments, uppercase See Also) produce non-conforming output. Use when writing, rewriting, fixing, or reviewing MATLAB help comments or function documentation.

Use to design or audit a QA dispute and appeal workflow with timeboxes, adjudication standards, and second-level consistency so appeals improve trust instead of rewriting scores without rules. Trigger for "QA appeal process", "agents disputing scores", "who adjudicates QA disputes", "overturn rate too high", second-level review standards, or calibration erosion from ad-hoc score changes.

Analyze and improve the internal link structure of an AEM Edge Delivery Services site by building a link graph from the query index and page content, identifying orphan pages, hub pages, and content silos, and generating specific linking recommendations with suggested anchor text and placement.

Tend the Allium garden. Use when the user wants to write, edit, update, add to, improve, clarify, refine, restructure, fix or migrate Allium specs. Covers adding entities, rules, triggers, surfaces and contracts, fixing syntax or validation errors, renaming or refactoring within specs, migrating specs to a new language version, and translating requirements into well-formed specifications. Pushes back on vague requirements.

Helm chart development agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw — chart scaffolding, values design, template patterns, dependency management, security hardening, and chart testing. Use when: user wants to create or improve Helm charts, design values.yaml files, implement template helpers, audit chart security (RBAC, network policies, pod security), manage subcharts, or run helm lint/test.