Executes unattended batch processing of all pending tasks with autonomous decision-making. Use when running all tasks automatically, batch processing without supervision,…
Scaffold complete full-stack features with shared types between backend and frontend. Use when asked to scaffold a feature, create a new module, build a full-stack feature…
Verifica se o diff atual foge do escopo da feature ativa. Produz SCOPE_OK, SCOPE_WARNING ou SCOPE_UNKNOWN quando a feature não é identificável.
Scoping group skill. Translates the chosen solution direction and top risks into a tight, build-able scope with explicit in/out boundaries per area.
Use when frontend work needs a shareable folder of screenshots for design, product, QA, stakeholder, or non-technical team review.
Official Feature-Sliced Design (FSD) v2.1 skill for applying the methodology to frontend projects. Use when the task involves organizing project structure with FSD layers,…
Apply Feature-Sliced Design (FSD) architecture to frontend projects. Triggers on: FSD, feature slicing, frontend architecture, layer structure, module boundaries, scalable…
Creates a complete product feature specification with acceptance criteria, scope, dependencies, and risks. Delegates to the Prometeo (PM) agent.
Draft detailed engineering specs from an approved PRD. Use when generating or updating the engineering specification for a feature, before implementation begins.
Review and score engineering specs against a startup-focused quality rubric. Penalize over-engineering and reward simplicity.
Turn a feature request or bug cluster into a source-backed spec, impact map, acceptance criteria, and delivery plan before coding.
Apply critic feedback to improve an engineering spec. Use when revising a spec based on review comments to address issues and improve quality scores.
Create feature spec files from project docs, commit and push to main, and create matching feature branches from main. — from product/prd-spec
Create feature spec files from project docs, commit and push to main, and create matching feature branches from main. — from majiayu000/claude-skill-registry
Reviews feature specifications for completeness, testability, and implementation readiness. Validates acceptance criteria, edge cases, and technical constraints.
Feature specification structure, API contract patterns, and state definition templates. Use when writing implementation-ready feature specs that development agents can execute…
Creates focused feature specifications with user stories, acceptance criteria, and edge cases. Lighter than PRD, focuses on single feature implementation.
Инициализация работы над новой задачей (фичей) в репозитории e1c.aswe — создание feature-ветки от develop и генерация шаблонов документов и тестов.
Count features marked as @failing and write to status JSON file. Used to determine when the autonomous coding loop should end.
Feature Store Connector - Auto-activating skill for ML Deployment. Triggers on: feature store connector, feature store connector Part of the ML Deployment skill category.
Online/offline feature serving, point-in-time correctness, Feast patterns, and feature computation design.
Plan and communicate a feature or product end-of-life. Use when deprecating features, sunsetting products, or managing migration off legacy systems.
Plan the retirement of a product feature — the kill decision made honest, user migration, data handling, comms sequencing, and the code actually deleted.
Remove features with usage evidence, migration paths, and staged communication that preserves trust. Use when retiring product surface or making the case that something should die.
Feature switch system guide for gating new user-facing features behind feature flags
Use when you have aligned feature tables (CSV format) paired with MS2 spectral data (MGF or mzML files) and need to compare chemodiverse samples with poor feature overlap or…
Use when after executing an MZmine batch processing workflow on raw metabolomics
Use when you have an aligned feature table from untargeted LC-MS with missing intensity values (NA or zero entries) for features that are present in some samples but fell below…
Use when after retention-time and m/z-based peak alignment has been completed across a cohort of LC-MS samples, and you need to create a unified quantitative matrix for…
Use when when you need to generate a realistic LC/GC-MS feature table (peak intensity matrix) with controlled, quantifiable condition effects (e.g., differential metabolite…
Use when when processing a metabolomics feature table through multiple sequential transformations (e.g., imputation, normalization, batch correction, annotation) and you need to…
Use when after peak quality filtering has been applied to a composite map peak detection output using SNR (>2), goodness-of-fit (peakshape > 0.5), minimum peak height (default…
Use when after loading an MS-DIAL feature table when you need to separate features into two disjoint groups: one meeting a quantitative threshold (e.g., m/z decimal values outside…
Use when changing backend APIs or frontend features so the assistant adds or updates Jest/Node spec tests and validates the feature.
Use when you have an untargeted metabolomics feature table (m/z, retention time, p-value from statistical test) but lack comprehensive metabolite identifications or MS/MS…
Using runtime switches to enable or disable features without deploying new code, decoupling deployment from release and enabling gradual rollouts, A/B testing, and emergency…
Maintain durable feature-level memory across AI coding sessions with lightweight Markdown tracks for status, source-of-truth docs, decisions, risks, and changes.
Restores an archived feature from the archives directory back to the active features directory.
Set up an LLM-judge evaluation that extracts canonical use cases for a PostHog feature at scale and streams the results to a Slack channel as a live feed.
Use when you have millions of MS/MS spectra in mzML, mzXML, or MGF format and need to identify similar spectra for clustering, but exhaustive pairwise cosine-similarity…
System diagnosis skill (READ-ONLY). Verifies feature behavior through code analysis, data validation, and Codex deep confirmation.
A live demo or admin page shipped with every feature whose results the user would otherwise not see. Use when adding a backend endpoint or feature with no UI to see it, when…
Generate polished walkthrough videos from Playwright test suites. Runs thematically connected tests with video recording, creates title cards, slows footage for readability, and…
Use when when you have extracted concatenated MS/MS spectra for multiple features from replicate mzML files and need to verify that a TIC-based filtering step (e.g., top x% TIC…
Execute a complete feature development workflow from research to PR creation. Use when starting new feature development, implementing tasks, or when the user mentions…
End-to-end feature development orchestration from planning through deployment with quality gates
FRD(기능 요구서) 초안을 받아 정련된 FRD를 완성하고, 이를 추적 가능한 PLAN(작업 분해)으로 만든 뒤, 각 태스크를 의존성 순서대로 단계 실행하는 통합 워크플로. EARS Acceptance Criteria, REQ/AC/CTR/EDGE↔TASK 추적성, `[P]` 병렬 마커, PR 단위 분리, PLAN…
Feature-Planung und Brainstorming im Frage-Antwort-Stil. Liest Projektkontext automatisch, dann interaktives Gespraech ueber neue Features. Funktioniert mit jedem Projekt.
Generate hierarchical _FEATURES.md files that describe what a codebase DOES from a user/consumer perspective, anchored to source symbols via tree-sitting.
Execute focused implementation, review, SEO, responsive, or roadmap-phase work in the Federacion de Kendo website repository.
Help the user file a bug report or feature request for Nimbalyst. Activates when the user opens the in-app feedback flow or runs /feedback:bug-report or /feedback:feature-request.
Interpreta e aplica feedbacks exportados do Feedback Studio (arquivo .md) em landing pages, wireframes e criativos.
User feedback patterns for interactions - loading states, success/error messages, form validation, empty states. Ensures users understand system state and next steps.
Style rules and anti-patterns for writing PRDs — every acceptance criterion must name its verification artifact; paired good/bad examples for the common drift modes.
Use when receiving UAT feedback, bug reports, user testing results, stakeholder feedback, QA findings, or any batch of issues to investigate.
Produces a festival submission strategy brief for a documentary or short film, identifying target festivals by tier, submission windows, positioning priorities, and a recommended…
Use when consuming Server-Sent Events, LLM token streams, OpenAI-style streaming chat responses, Fetcher eventstream helpers, response prototype extensions, stream termination…
Figma ekranını erişilebilirlik açısından denetler. Renk kontrastı (WCAG AA/AAA), minimum dokunma hedefi, fokus sırası, metin boyutu ve platform-bazlı ekran okuyucu önerileri…
Design and prototype interfaces in Figma - create, edit, and manage design files, components, and collaborate on design projects
Generate structured developer handoff annotations for a Figma screen or component. Use when asked to write Figma annotations, create dev handoff notes, document a Figma design for…