Results for “pr”

Process a meeting transcript (Google Drive file URL or pasted text) into structured action items + decisions. Routes owners per operations.md, syncs to Notion `${BRAND}_MEETINGS_DB` + `${BRAND}_ACTIONS_DB`, sends Slack DMs to owners, drafts follow-up Gmail for client/sales meetings. Event-triggered (new transcript lands in Google Drive) or on-demand.

Use when a val needs to require login with a Val Town account — gating routes behind authentication, identifying the current user, building user-specific dashboards. Covers std/oauth's `oauthMiddleware` and `getOAuthUserData`, the auto-managed `/auth/*` routes, and session behavior. For third-party OAuth providers (Google, GitHub, etc.) see the `third-party-integrations` skill instead.

Use for writing, reviewing, debugging, testing, or optimizing Python CVXPY optimization models. Trigger on Variable, Parameter, Expression, Constraint, Objective, Problem, DCP, DPP, DGP, DQCP, solver selection/status, dual values, mixed-integer, cone, or repeated parametric solves. Do not use for scipy.optimize-only, PyMC inference, symbolic algebra without optimization, or hand-written solver implementations.

Full safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with /freeze (blocks edits outside a specified directory). Use for maximum safety when touching prod or debugging live systems. Use when asked to "guard mode", "full safety", "lock it down", or "maximum safety". (gstack)

Performance regression detection using the browse daemon. Establishes baselines for page load times, Core Web Vitals, and resource sizes. Compares before/after on every PR. Tracks performance trends over time. Use when: "performance", "benchmark", "page speed", "lighthouse", "web vitals", "bundle size", "load time". (gstack) Voice triggers (speech-to-text aliases): "speed test", "check performance".

Extract battery features for degradation analysis and health monitoring in MATLAB. Covers cycling test features, differential curves (IC/DV/DT), and measurement statistics. Use when working with battery cycling data, SOH estimation, RUL prediction, or any battery test data analysis in MATLAB. Triggers on battery* functions such as batteryTestDataParser, batteryTestFeatureExtractor, batteryMeasurementFeatures, batteryDifferentialCurves.

Google and Meta paid media account structure evaluation. Audits campaign/ad set architecture against conversion volume minimums, budget thresholds, and targeting overlap. Identifies over-segmentation, under-segmentation, budget fragmentation, and structural anti-patterns blocking algorithmic learning. Provides consolidation roadmaps with migration plans. Use when inheriting accounts, quarterly health checks, or before scaling budgets.

Meta-agent for creating new custom agents, skills, and MCP integrations. Expert in agent design, MCP development, skill architecture, and rapid prototyping. Activate on 'create agent', 'new skill', 'MCP server', 'custom tool', 'agent design'. NOT for using existing agents (invoke them directly), general coding (use language-specific skills), or infrastructure setup (use deployment-engineer).

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.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

Use this skill when the user asks about FMCSA Compliance Safety Accountability (CSA) program scoring — the seven BASIC categories, BASIC Severity Indicator (BSI), peer percentiles, intervention thresholds, how violations age out, SMS Methodology, ISS (Inspection Selection System), what "alert" status means, Safety Measurement System mechanics, or DataQ disputes. Cite SMS Methodology v3.20.

This skill recommends computed tomography (CT) as the initial imaging modality for primary aldosteronism (PA) evaluation in Japan, citing its accessibility and comparable performance to MRI. It is triggered when a clinician orders imaging for suspected PA and asks 'What imaging should I start with?' or seeks a cost-effective initial evaluation.

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。

Transforma uma ideia em linguagem natural num documento de requisitos completo, ancorado nos artefatos da pipeline reversa. Use quando o usuário digitar "/reversa-requirements", "reversa-requirements", "quero levantar requisitos" ou pedir para iniciar uma nova feature a partir de uma frase. Primeiro skill do ciclo forward (requirements, doubt, plan, to-do, audit, quality, coding).

Use when adding a fixed full-screen WebGL laser background with a thin white-hot vertical core, restrained brand-colored halo, and soft smoky fog. Prefer this over mengto-corner-lasers when the beam is a full-viewport WebGL background, not corner ornaments; not for full page layout, copy, or unrelated particle systems.

Publish Heroku apps into Salesforce and Agentforce with Heroku AppLink. Use when the agent needs AppLink publication workflows, OpenAPI publication preparation, publish a Heroku app to Salesforce, review AppLink publication state, inspect shared publication endpoints or shared objects, or reason about Agentforce, Flow, Apex, Data Cloud, service mesh, and AppLink user-mode behavior.

You are an expert in Bolt.new by StackBlitz, the AI-powered full-stack development environment that runs entirely in the browser. You help developers go from idea to deployed app in minutes using natural language prompts — Bolt generates complete applications with frontend, backend, database, and deployment, all running in a WebContainer without local setup.

You are an expert in vLLM, the high-throughput LLM serving engine. You help developers deploy open-source models (Llama, Mistral, Qwen, Phi, Gemma) with PagedAttention for efficient memory management, continuous batching, tensor parallelism for multi-GPU, OpenAI-compatible API, and quantization support — achieving 2-24x higher throughput than HuggingFace Transformers for production LLM serving.

Searches and reads X (Twitter): profiles, timelines, mentions, followers, tweet search, trends, lists, communities, and Spaces. Publishes posts, likes/unlikes tweets, and follows/unfollows users after the user completes OAuth in the browser. Use when the user asks about Twitter/X data, social listening, posting, or interacting with tweets/users without sharing account passwords.

World-class DevOps engineering - cloud architecture, CI/CD pipelines, infrastructure as code, and the battle scars from keeping production running at 3amUse when "devops, infrastructure, deployment, ci/cd, docker, kubernetes, aws, gcp, azure, terraform, cloudflare, vercel, monitoring, alerting, pipeline, container, scaling, downtime, incident, sre, devops, infrastructure, cloud, ci-cd, monitoring, reliability, sre, containers" mentioned.

Computes mass-spectral similarity and identifies compounds for metabolomics with matchms — comparing mass spectra, scoring similarity (cosine, modified cosine), and searching spectral libraries to annotate unknowns. Use when matching MS/MS spectra, identifying metabolites, or library searching; for full LC-MS/MS proteomics pipelines use pyopenms. Part of the AlterLab Academic Skills suite.

Design and verify auditable human oversight, approval gates, escalation paths, and safe state transitions for AI agent workflows. Use when deciding which agent actions require review, adding approve/reject or dual-control flows, preventing unauthorized autonomous effects, creating decision records, reducing rubber-stamping, or recovering safely from rejected, expired, or failed actions.

Use when the user asks Codex to directly generate images with gpt-image-2 using inherited OpenAI/Codex-compatible environment credentials or local GPT_IMAGE2_* overrides, including text-to-image, reference-image guided generation, ratios, resolution, quality, variants, and saved local image files; run the bundled Node CLI and keep URL/sk configuration private.

Bidirectional conversion between Elm and Haskell. Use when migrating projects between these languages in either direction. Extends meta-convert-dev with Elm↔Haskell specific patterns. Use when migrating Elm frontend code to Haskell, translating Elm patterns to idiomatic Haskell, or refactoring Elm codebases. Extends meta-convert-dev with Elm-to-Haskell specific patterns.

Use when the user asks about academic literature, research papers, scholarly works, authors, citations, institutions, journals, or any academic metadata. Trigger when users want to search for papers, find author profiles, track citations, discover related works, or explore academic topics. Also use when users mention DOIs, ORCIDs, h-index, publication venues, or research metrics.

Discover, configure, and connect to Arduino boards from MATLAB using the Arduino Support Package. Use this skill when the user wants to set up an Arduino board, connect to Arduino hardware, find connected boards, scan serial ports, configure Arduino libraries, or any task that requires an Arduino connection as a prerequisite (e.g., blink LED, read sensor, read digital pin, read analog pin, write pin, plot sensor data, scan I2C, use ultrasonic sensor, control servo, read temperature, read voltage, data logging from hardware). Triggers on: arduino, board setup, COM port, serial port, hardware connection, Arduino Nano, Arduino Uno, Arduino Mega, Arduino Micro, Grove, sensor setup, I2C scan, ultrasonic, servo, readDigitalPin, writeDigitalPin, readVoltage, writePWMVoltage, temperature sensor, air pressure, pin read, pin write, analog input.

Design and apply QA methodology for software teams: test strategy, regression testing, CI failure triage, test automation, quality gates and metrics, risk-based testing, exploratory testing, test design techniques, AI code quality gates (independent verification, acceptance-criteria testability review for agentic Spec-Driven Development), mutation-guided test hardening and review evidence (surviving mutants, weak assertions, diff-aware mutation testing), agentic eval design (dataset test design, judge-as-system-under-test, flaky-eval discipline), QA career levels (Senior/Staff/Principal), and SDET engineering (test infrastructure, gTAA, CI/CD integration). Do not use for root-cause debugging of production incidents, security implementation or threat modeling, or evaluation framework governance and statistical analysis — route those to systematic-debugging, secure-software-engineering, and agent-evals-and-observability respectively.

Generate user-friendly "Explain Like I'm 5" feature documentation for end users by reading the codebase. Use this skill whenever the user wants to document a feature for non-technical users, write help docs, create an explainer for a feature in their app, produce onboarding content, or asks "make a user doc for X". Trigger on phrasings like "ELI5 the closeout flow", "write user docs for the kanban view", "explain this feature to a customer", "make a help article for X", "document this for end users". Also known as "E-features-LI5". This skill produces plain-language docs written for someone with the app open trying to get something done — not internal developer docs (use the `teach` skill for those) and not feature announcements.

World-class voiceover expertise combining the narrative craft of documentary producers, the commercial precision of advertising agencies, and the accessibility of modern AI voice technology. Voiceover is the invisible art that makes or breaks video content. Great voiceover isn't just speaking clearly—it's performing the script in a way that creates the intended emotional response. The best voiceover work understands pacing, tone, emphasis, and the subtle art of making scripted words sound natural. It knows when to use human talent versus AI, and how to get the best from both. Use when "voiceover, voice over, VO, narration, narrator, voice recording, voice talent, voice actor, AI voice, text to speech, audio narration, voice direction, voiceover, audio, narration, voice, recording, AI-voice, talent, direction" mentioned.

Detect malicious scheduled task creation and modification using Sysmon Event IDs 1, 11, and Windows Security Event 4698/4702, correlating task creation with suspicious parent processes, public directory paths, and encoded command arguments to identify persistence and lateral movement.

Finishes an existing Japanese business talking-head, lecture, interview, or testimonial rough cut into a credibility-first vertical social video, preserving the speaker's meaning while tightening repeated ideas, adding a first-second thesis, readable full captions, restrained punch-ins, speaker identification, a.

Use when project-managing an ICCV campaign across the odd-year cycle, covering the autumn fork between CVPR and ICCV, the early-March registration and single submission deadline, May rebuttal week, late-June decisions, the October conference with international travel and visa lead times, and the ECCV/CVPR fallback ladder if the paper misses.

Use when planning an ICLR project timeline from topic selection through OpenReview submission, discussion, revision, decision, camera-ready, poster, video, and public artifact release. Use when sequencing milestones against the current cycle's OpenReview deadlines, budgeting time for the long public discussion phase, or assigning owners for anonymity audits and reviewer-verifiable evidence paths.

Rastreie sites inteiros usando a API /crawl do Cloudflare Browser Rendering. Inicia jobs de rastreamento assíncronos, monitora a conclusão e salva os resultados como arquivos markdown. Útil para ingerir sites de documentação, bases de conhecimento ou qualquer conteúdo web no contexto do seu projeto. Requer variáveis de ambiente CLOUDFLARE_ACCOUNT_ID e CLOUDFLARE_API_TOKEN.

Builds complete bilingual email drafts from intent and audience. Use when the user asks to write, rewrite, localize, polish, or generate an email, campaign email, outreach message, customer update, follow-up, announcement, invite, sales email, internal note, or lifecycle email and wants clear subject lines, preheaders, body copy, CTAs, variants, or English and Spanish versions.