Decline a request, push back on scope, or protect priorities without burning the relationship. Use when asked how to say no, turn down a request, push back on your…
Iterate on a new or redesigned component in a sandboxed Explore story outside src/components/ (+ Figma), checked against a graduation gate.
Check design-system health for a React+Vite app — raw hex, undefined/unused tokens, scale gaps, and DESIGN.md drift (claims vs code).
Software architecture guidelines to maintain code readability (Clean Code, SOLID, DRY) and application scalability / Panduan arsitektur perangkat lunak untuk menjaga keterbacaan…
Use when AI is in the loop — generating copy/variants at scale, personalizing messaging, or summarizing customer calls/competitive intel, and as the anti-AI-tell scrub on any…
Apply the principle of avoiding the Scaling Fallacy — the assumption that a system that works at one scale will work at a different (smaller or larger) scale.
Run accessibility scans against target URLs, open trackable issues, and optionally hand remediation suggestions to Copilot instead of treating accessibility review as a manual…
Internal helper agent. Invoked by orchestrator agents via Task tool. Internal helper that bridges GitHub Accessibility Scanner CI data with the agent ecosystem.
Validate WCAG compliance and accessibility standards (ARIA, keyboard navigation). Use when auditing WCAG compliance or screen reader compatibility.
Map inclusive usage scenarios across ability spectrums for a product or feature. Chains: ability-spectrum-mapping, situational-impairment-mapping, assistive-technology-scenarios.
Use for the SchoolOS «0201 · أمين البلاغات» duty: reading users' messages to the developer in the production inbox via Chrome (owner's session, never log in), the gate.js…
Plan and rules for redesigning the SchoolOS frontend into a structured, premium "engineered" look based on the TailAdmin design language, with real images.
Schulungsprogramm und Accessibility-Champion-Modell in der Organisation aufbauen: Rollendefinition, Aufgaben, Zeitbudget, Trainingsplan fuer Design, Entwicklung, QA, Content,…
Prüft den Rechtsrahmen digitaler Barrierefreiheit: BFSG, BFSGV, BITV 2.0, Web Accessibility Directive, European Accessibility Act, öffentlicher Sektor, B2C-E-Commerce, Kl — from…
Prüft den Rechtsrahmen digitaler Barrierefreiheit: BFSG, BFSGV, BITV 2.0, Web Accessibility Directive, European Accessibility Act, öffentlicher Sektor, B2C-E-Commerce, Kl — from…
Record and route a deviation from PRODUCT-PIVOT, PIVOT-BACKLOG or an ADR: log the discrepancy, pick the decision consistent with the current order, update the owning document.
Expert in protecting projects from scope creep. Covers requirement management, stakeholder negotiation, saying no diplomatically, and keeping projects focused.
Für Scope: Behörden-, Gerichts- oder Registerweg: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Conduct a focused interview to gather complete requirements for a specific feature - what it does, who uses it, how it integrates with existing functionality, and technical…
Investigate the codebase to design a feature implementation - find integration points, identify patterns to follow, and design the approach.
Generate evidence-based feature ideas that improve UX for defined user audiences. Consumes project context, PRD, scope docs, and codebase to identify gaps, missing flows, and…
Inspect product-grounding artifacts, current implementation, and backlog state to choose one bounded next slice and emit canonical planning artifacts for scorpio-task-plan.
Generate PRD, MVP scope, and implementation plan documents from structured requirements. Use after completing a requirements interview or when the user has roles, stories, flows,…
Create or destroy a Salesforce scratch org from `config/project-scratch-def.json`, optionally deploy the project, optionally seed with the project's TestDataFactory.
Critique a rendered screen, screenshot, Figma frame, or built page across seven visual-quality dimensions and return a prioritised P1/P2/P3 fix list.
Use when building Screen Flows that must meet accessibility standards (WCAG 2.1 AA, Salesforce accessibility guidelines).
Generate a screen specification from a Figma frame using MCP tools (get_design_context, get_screenshot).
How to interpret accessibility tree elements and correlate them with screenshot regions for accurate GUI interaction.
Analyze product screenshots to extract feature lists and generate development task checklists. Use when: (1) Analyzing competitor product screenshots for feature extraction, (2)…
Expert UI/UX design review of screenshots. Acts as a picky designer analyzing typography, colors, spacing, layout, and accessibility.
Tear down a competitor's product from screenshots of its actual UI — onboarding, pricing page, core flows.
Scrum framework for AI agent self-management. Brings Scrum practices into any project to drive development and continuous improvement. Ceremonies chain automatically.
Guide Sprint Planning in AI-Agentic Scrum. Use when selecting PBI, defining Sprint Goal, or breaking into subtasks.
Advanced Scrum Master skill for data-driven agile team analysis and coaching. Use when the user asks about sprint planning, velocity tracking, retrospectives, standup…
Comprehensive Scrum Master assistant for sprint planning, backlog grooming, retrospectives, capacity planning, and daily standups with intelligent context-aware reporting — from…
Agile process facilitator specializing in Scrum framework implementation, team coaching, and continuous improvement.
AI-powered Scrum Master and Enterprise Agility Coach based on Jeff Sutherland, Taiichi Ohno, and First Principles thinking.
Angular Core UI portal executor for confirmed frontend implementation. Use for new SDCoreJS portal init, existing @sdcorejs/angular or @sd-angular/core portals, PO/BA mock-first…
Trigger: SDD, docs/sdd, PRD, spec, diseño, tasks, apply-progress, verify-report, archive.
Agentflow step 3/9: Prototype. Decides whether a throwaway spike is needed, runs the smallest experiment when needed, and preserves learnings with quality-loop review.
Setup inicial del proyecto como fase 0 del SDD. Genera PRD, RFC, AGENTS, dependencias, instala, verifica build e inicializa SDD.
Periodic cumulative-drift audit — look at the last stretch of shipped goals as a whole and ask whether the work still matches the north-star's stated bets, or whether the strategy…
One-command setup check-up — audits what THIS project needs (gh auth + project scope for the board, the graph builder for the KG, a filled north-star for vision-first, the .sdlc…
Interactive requirements elicitation for the Specification phase. Use when defining, reviewing, or modifying stakeholders, goals, user stories, requirements, assumptions, or…
Deploy defense-in-depth SDLC hardening across four phases: pre-commit hooks, CI/CD gates, runtime enforcement, and continuous audit evidence collection systems.
Use when creating implementation plans, breaking down tasks, sequencing changes, planning TDD cycles, or creating a roadmap for implementing a user story.
The Retrospective / learning executor — after a goal ships, surface the structural + product debt the narrow fix left behind, check what shipped against the original intent, and…
The antidote to vibe coding: a full software engineering team at your fingertips. Create or reverse-engineer PRDs, TRDs, personas, epics, and user stories with acceptance…
Externalize a tiered product north-star (vision -> strategy -> design -> architecture) into .sdlc/context/north-star.md, so goals are grounded in why you're building, not vibes.
Design or audit one search, browse, recommendation, or marketplace-discovery quality contract covering corpus and intent, retrieval and eligibility boundaries, ranking evidence,…
Activate when: user says 'our growth is slowing and we need to figure out what's next', 'we keep doubling down on the core but I'm worried about disruption', 'when is the right…
Expert knowledge on Howard Marks's contrarian investment framework — first-level vs second-level thinking, consensus analysis, cycle positioning, the relationship between price…
Use when a decision, intervention, policy, product change, metric target, or system fix needs analysis beyond the immediate effect: ask what happens next, how actors respond, what…
Playbook for the Related Work section. Positioning angles (axis-of-comparison / chronological / closest-prior), how to avoid lit-review-creep, when to use a comparison table.
Use when setting up, hardening, or reviewing a cloud server for self-hosting, including DNS, SSH, firewalls, Nginx, static-site hosting, reverse-proxying an app, HTTPS with Let's…
SEED 컴포넌트의 경로 조회·React·Lynx API 비교, 신규·포팅·기존 구현 변경, React·Lynx 문서·예제 작성, 또는 컴포넌트와 무관한 색상 토큰의 지도·WCAG 대비 조사를 할 때 사용한다.
Exportiert das gesamte Kemmer Knowledge System als portierbares Seed-Paket fuer andere Claude Desktop Instanzen.
Design or critique selection controls — pick the right control (checkbox, radio button, toggle switch, dropdown, slider, picker) for the choice being made, and apply labeling,…
Self-critique 루프의 설계·구현·정량 측정. LangGraph conditional edge 기반 구조적 루프, retry counter, diff 평가, A/B 실험으로 결함 감소율 측정.
Lightweight self-hosted project management using markdown files in a .development directory. Covers backlog, planning, todo, roadmap, and saved plans — everything an agent needs…