Break work into atomic tasks. Sequence by risk. Add stakeholder touchpoints every 2-3 tasks.
Validate direction before committing. Prototype fast, show it, pitch the outcome.
프론트엔드 접근성 감사를 WCAG 2.1 기준으로 수행하고, 위반 항목과 구체적인 수정안을 제시한다.
Validation group skill. Time-boxed engineering investigation targeting the top feasibility assumptions from risk-assumption-map. Produces tech-spike-report.md and disposable code.
Use when ensuring tracking events and diagnostics are emitted at key user actions.
Guided feature development from requirements to deployed code. Combines codebase exploration, architectural design, parallel implementation via DAG orchestration, and quality…
Archives a completed feature to the archives directory with optional documentation validation.
Create feature branches for all work. Use when creating branches, checking out, or pushing. Prevents accidental push to develop.
Enforce feature work on a dedicated git branch and submission via pull request. Use when implementing any feature, fix, or refactor so work is isolated, reviewed, and merged via…
Orchestrator skill for the complete feature development lifecycle. Coordinates 5 phases - task selection, component design, build loop, analytics setup, and commit/documentation.
Add features by description. User says WHAT, AI figures out HOW. Use when: user wants to add functionality to existing app.
Archive feature working files after a PR has merged
Parallel batch coordinator for independent work units
Use when coverage percentage is treated as proof. Require named feature behavior tests, source fixtures, and anti-overfit checks alongside line coverage.
Guide for creating DevContainer features. Use when creating a new feature for devcontainer, implementing install.sh scripts (npm package, binary download, source build, dotnet…
Interview the user to define a new feature: problem, scope, approach, and tasks. Writes a feature-definition.md file that /feature-setup consumes.
Turn ideas into fully formed designs and specs through natural collaborative dialogue. Use when planning new features, designing architecture, or making significant changes to the…
Tool-agnostic feature design preflight that traces a requirement through production constraints, dependencies, user and system flows, edge cases, security, operations, and tests…
在 docs/designs/ 目录下用 markdown 文件记录计划开发的功能。当用户要求开发新功能、添加特性或修改现有功能时（如'为 xx 添加功能'、'开发 xx'、'实现 xx'）时调用。通过问答澄清需求并生成设计文档。全程中文，仅生成文档，不修改代码。
Complete feature development lifecycle from research to deployment. Uses Gemini Search for best practices, architecture design, Codex prototyping, comprehensive testing, and…
Execute feature lifecycle from beads issue to GitHub push without git locks or JSONL corruption. Triggers on "start feature", "implement issue", "feature workflow", "new feature".
Practical guide for building Fusebase Apps features. Use when: (1) Creating a new feature, (2) Setting up project structure, Vite config, or authentication, (3) Building or…
Feature development workflow with exploration, architecture, implementation, and review phases. Use for implementing new features or significant changes.
Orchestrate end-to-end feature development from requirements through implementation, testing, and review.
Autonomous feature research and gap analysis. Use when starting /add-new-feature or analyzing existing architecture documents.
Generation et maintenance de documentation technique a partir du code, avec modes full, update et audit
Use when the user asks to generate comprehensive feature documentation with verified test cases, create feature README with code evidence, or document a complete feature with test…
Generate single-file feature documentation with verified test cases. Use for quick feature docs, feature README, any project (not enterprise modules).
Эксперт feature documentation. Используй для документации функций, release notes, user guides и product documentation.
Create clear feature documentation for non-professional developers. Use PROACTIVELY when documenting new features, significant code changes, creating technical specifications, or…
Analyse the feature brief to identify relevant KB topics and ADRs
Incorporates mid-stream changes into feature documentation with validation and propagation.
Comprehensive feature engineering for ML pipelines: data quality assessment, feature creation, selection, transformation, and encoding.
Create and transform features using encoding, scaling, polynomial features, and domain-specific transformations for improved model performance and interpretability
Techniques de feature engineering pour améliorer les modèles ML. Se déclenche avec "feature engineering", "features", "transformation de données", "encoding", "normalisat — from…
Feature Engineering Helper - Auto-activating skill for ML Training. Triggers on: feature engineering helper, feature engineering helper Part of the ML Training skill category.
Auto-generate features with encodings, scaling, polynomial features, and interaction terms for ML pipelines.
[METHODOLOGY] Feature delivery orchestration (agent waves, review cycles max 3 rounds, commit-per-wave). Preloaded by dev-engineering-lead agent.
Discovers KrakenD features, checks edition availability (CE vs EE), and provides implementation examples
Use when building a non-trivial ChurchCore Ops feature end to end, especially when product rules, architecture, backend, frontend, tests, and validation are all involved.
Manage features.yml for tracking requirements and progress; use proactively ONLY when features.yml already exists, or invoke manually to create one; complements TodoWrite for…
Enables controlled rollout and instant rollback by configuring feature flags for every risky change. Use when asked to feature flag configurator. Suggest when relevant.
Implement environment-safe feature flags using Custom Metadata Types for Apex, LWC, and Flow. NOT for user-level entitlements or permission sets.
Write a feature flag management guide and lifecycle playbook for a service or team — covering flag taxonomy, creation checklist, rollout strategy, monitoring requirements, cleanup…
Automate the complete lifecycle of feature flags in Saberloop, following Epic 10 hygiene standards
機能フラグ（Feature Flag/Feature Toggle）による段階的リリースとA/Bテスト実装スキル。 リスク管理とカナリアリリースを可能にし、本番環境での安全な機能展開を実現します。
Plan feature flag rollout and cleanup. Use when a mid-level developer needs controlled release guidance.
Integrate feature flagging into the React component lifecycle for safe continuous delivery.
Use when introducing a feature flag system, choosing between release flags / experiment flags / operational flags / kill switches / permission flags, designing percentage…
PM-facing playbook for phased rollouts with feature flags -- taxonomy (release / experiment / ops / permission), rollout shapes, kill-switch decision tree, holdouts, flag debt…
Concevoir et implémenter un système de feature flags pour des déploiements progressifs, A/B testing, canary releases et kill switches.
Operational discipline for feature flags as production infrastructure. Flag types, naming, targeting rules, rollout strategy, lifecycle, governance, stale flag management, and the…
Use when implementing runtime feature toggles, emergency kill switches, or gradual rollout controls in Apex using Custom Metadata Types, Custom Permissions, or Hierarchical Custom…
Use when adding, retiring, or auditing feature flags. Triggers on "add a flag", "ship behind a flag", "rollout plan", "kill switch", "stale flags", "flag debt", "LaunchDarkly",…
Audit and inventory all feature flags declared in the Packmind codebase. Use when the user asks to list, audit, review, or inventory feature flags, asks which flags are active,…
Use when feature flag tests fail, flags need updating, understanding @gate pragmas, debugging channel-specific test failures, or adding new flags to React.
Database-backed feature flag systems in the Orient. Use when implementing feature flags, debugging flag-related issues, or understanding the flag hierarchy.
Gestion de feature toggles avec LaunchDarkly, OpenFeature et implémentations custom pour le déploiement progressif et l'A/B testing.
Implements feature flags and progressive delivery — kill switches, percentage/targeted rollouts, sticky hashed bucketing, fail-safe evaluation, 1→10→50→100 ramps with…
Guides a user through DDD → BDD → TDD → Git for a single feature, staying code-agnostic and interactive.