Use when implementing a feature or multi-file code change - provides structured implementation flow with persona selection, validation, and testing guidance.
Implements GigLedger features following Clean Architecture. Use when building out feature modules from GitHub issues.
Feature Importance Analyzer - Auto-activating skill for ML Training. Triggers on: feature importance analyzer, feature importance analyzer Part of the ML Training skill category.
Develop features in isolated git worktrees with autonomous testing and iteration. Use when the user asks to develop a feature in a separate worktree, wants isolated feature…
Use when the user wants to discover, brainstorm, or collect features before planning, OR when the user wants to clarify open questions on existing Planungsbüro tickets.
Use when after blank masking and sample dropping, when you have a feature table with intensity values that exhibit systematic variation across sample collection batches or…
Use when after sample alignment in untargeted LC-MS workflows, when the aligned feature table contains missing (NA or zero) intensity entries for features that are detected in…
Build a single-file interactive HTML walkthrough that explains a feature in ~30 seconds. Generates a 3-column prototype (input → artifact → step-by-step wizard) so engineers, PMs,…
Investigate and explain how existing features/logic work. READ-ONLY exploration. Triggers: how does, explain, what is the logic, investigate, understand, where is, trace, walk…
Use when the user asks to investigate, explore, understand, explain, or analyze how an existing feature or logic works.
Use when the user asks to investigate, understand, explore, or explain how a feature works, asks about existing logic, or wants to understand code flow.
Use when the user asks to investigate, explore, understand, explain, or analyze how an existing feature or logic works.
Evaluate feature investments using revenue impact, cost structure, ROI, and strategy. Use when deciding whether a feature deserves investment.
Quizlet-style quiz learning module with single choice questions, progress tracking, and persistent storage for interactive learning experiences
Take a new feature or product update and generate the full launch kit: changelog entry, email announcement, LinkedIn post variants, in-app banner text, Twitter/X thread, and…
Research and recommend community-vetted best-in-class libraries for each feature problem in the product (lists, camera, forms, keyboard, sheets), ranked by adoption signal…
Orchestrator-workers variant of feature-library-scout for deep per-feature-problem library research. The orchestrator derives the feature-problem list and dispatches one Sonnet…
Use when a user supplies a custom feature list from external feature-finding software (vendor tools, alternative open-source pipelines) instead of using pyOpenMS automatic…
Coding agent for the project-level harness — one feature per session, must verify, must be mergeable.
Manage feature manifests for code traceability. Use when creating new features, updating existing features, checking feature health, or exploring the feature-to-code relationship.
Convert PRD requirements into structured epics, features, and user stories with acceptance criteria and priority rankings
Use when you have a heterogeneous feature matrix combining molecular descriptors (from RDKit/mordred) and chromatographic metadata (column length, temperature, pH, flow rate,…
Use when you have loaded a feature-by-pixel intensity matrix from an MSI HDF5 container and need to perform dimension-preserving corrections (e.
Use when after RAMClustR clustering and do.findmain molecular weight inference have been completed on XCMS-detected metabolomics features.
Use when after completing sample alignment in JPA (Part 5) or when ingesting a peaklist or aligned feature matrix from prior peak-picking runs, parse feature metadata to enable…
Use when after loading and formatting raw peak-picked LC-MS metabolomics data frames (via metabData constructor) when you need to eliminate features with poor sample coverage…
Use when you have a preprocessed LC-MS feature table (m/z, retention time, intensity columns) and need to identify which features belong together as isotopes or adducts of the…
Use when you have a preprocessed feature table (tab-delimited: feature ID, m/z, retention time, intensity columns) from LC-MS data and need to annotate which observed features…
Implements a single task following the next → implement → check → done workflow with TDD support. Use when working on one specific task, implementing a single feature from the…
Use when after extracting and encoding molecular descriptors and structural features (atom types, bond connectivity, graph topology) from SMILES strings into a fixed-size…
Story orchestration with progress tracking, standardized directory structure, and validation
Research-backed feature implementation workflow enforcing gap analysis, incremental planning, agent coordination, and continuous integration best practices.
Use when after anchor selection and retention-time spline mapping have produced a candidate list of feature pair alignments, but before final scoring and reduction of the combined…
Multi-phase feature development with checkpoint gates, parallel agent streams, and phased artifact output
Use when operating the portable feature pipeline across any project: preflight, dry-run, execute, resume, monitor, recover, and verify runner evidence.
Use when implementing a new NeoHaskell feature end-to-end — from ADR draft through PR merge — and the work needs the structured 17-phase pipeline with ADR, security and…
Plan feature implementation with technical specifications and actionable steps for solo developers
정련된 FRD.md를 받아 실행 가능한 PLAN.md(작업 분해)로 만든다. 요구사항을 단일·검증가능·증분 Task로 쪼개고, TASK-ID·`[P]` 병렬 마커·`size` 크기 마커(실행 라우팅 신호)·`test` 테스트 필요 여부 마커·`file:`·`traces:`를 부여하며, PR 단위로 그룹핑하고 의존성…
PLAN.md(작업 분해)를 받아 각 태스크를 의존성 순서대로 단계 실행하고 진행 상태를 추적한다. 선행이 끝난 Task부터 `size` 마커로 라우팅해(S 직접·M 위임·L 분해 재검토) code-implementer 에이전트에 구현·검증을 위임(기본 경로) → done 리포트의 검증 근거·인계 노트 확인 → PLAN…
Creates phase-based feature plans with quality gates and incremental delivery structure. Use when planning features, organizing work, breaking down tasks, creating roadmaps, or…
Use after research (Z01 files exist) to create implementation plan - follow structured workflow
Break down feature requests into detailed, implementable plans with clear tasks. Use when user requests a new feature, enhancement, or complex change.
Draft a pull request title, description, and review checklist
Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.
Expert in feature prioritization - the art and science of deciding what to build and in what order. Covers prioritization frameworks, roadmap planning, stakeholder management, and…
RICE scoring framework for ruthless feature prioritization. Evaluates features against strategic objectives, customer value, and resource constraints.
Scores and ranks a product backlog with RICE, Kano, Value vs Effort, and WSJF so assumptions beat HiPPO.
Transform overwhelming client feature wish lists into structured MVP/Phase 2/Phase 3 plans with time estimates, preventing scope creep and creating profitable upsell opportunities.
Score a feature list using RICE (Reach, Impact, Confidence, Effort) and return a ranked table with recommendation.
Full feature development workflow — fill in feature name, Figma link, and Postman link, then follow all phases from audit to verify.
Use when you have a set of training LC-HRMS chromatograms (retention time × m/z matrix format) and a manually curated reference list of isolated single chromatographic peaks, and…
Use when after nontargeted peak detection and segmentation has generated a feature table from raw LC-MS data (mzML or vendor format), apply quality assessment when you need to…
Lightweight entry point for small, well-understood changes
Analyze implementation failures and generate recovery plans. Use when an issue fails and needs diagnosis for retry or escalation.
Review and refactor implemented code with quality checklist
Post-launch analysis and results documentation. Document what shipped and what we learned.
Show where a feature is and what to run next
Post-feature retrospective reviewing scope, assumptions, and lessons learned
Review and prioritize features using RICE, WSJF, or Kano scoring frameworks, then create GitHub issues for suggestions.
Tiefgehende Risikobewertung für ein einzelnes Feature oder einen Produktbereich wenn der Launch-Review etwas gefunden hat das mehr als eine Tabellenzeile braucht.