MarieLynneBlock

eval-driven-dev

Build an automated evaluation pipeline that tests a Python LLM application end-to-end with pixie test — real code paths, real LLM calls, instrumented external data — and scores outputs with evaluators instead of assertions. Use when adding evals to a Python AI app.

acceptance-test-plan

Produces a traceable acceptance test plan with individually numbered test cases. Each test case maps to a source requirement (user story, use case, or FR), specifies preconditions, steps, and expected results, and includes coverage of the happy path, edge cases, and negative scenarios.

architecture-audit

Provides a repeatable, evidence-based framework for reviewing software architectures.

gap-analysis

Provides a repeatable framework for identifying and prioritising gaps between where things are now and where they need to be.

process-map

Produces a structured process map with swim lanes, task nodes, decision diamonds, and handoff arrows. Output is in **Mermaid** flowchart notation (renderable in GitHub, VS Code, Confluence, and Miro) or **BPMN-lite** text when a formal notation is required.

requirements-document

Generates a Business Requirements Document (BRD) or Functional Requirements Specification (FRS) skeleton populated from the user's input. It structures requirements with unique IDs, priority, source, and acceptance notes — making them traceable and reviewable.

stakeholder-map

Produces a stakeholder map structured around the classic influence × interest grid (also called a power/interest matrix). It classifies each stakeholder, recommends an engagement strategy per quadrant, and surfaces alignment risks — stakeholders who are high-influence but opposed or unengaged.

tradeoff-analysis

Provides a structured framework for comparing options under uncertainty. It surfaces criteria, weights them by stated priorities, scores each option, and produces a transparent recommendation — including the conditions under which a different option would be the right call.

use-case

Produces a complete use case following the Cockburn/RUP format. A use case describes a goal-directed interaction between an actor and the system — capturing not just the happy path, but the extension flows (error, alternative, and exception paths) that user stories typically omit.

write-epic

Produces a complete epic definition following Atlassian agile guidance. An epic captures a large initiative that is too big for a single sprint and must be decomposed into user stories.

write-user-story

Produces a complete, ready-to-groom user story following the standard Atlassian/agile format. It applies the INVEST criteria and the 3 Cs framework (Card, Conversation, Confirmation) to ensure each story is well-scoped, valuable, and testable — not just syntactically correct.

miro-board

Generates Miro board content in two modes:

agent-governance-patterns

Design and implement governance controls for tool-using and multi-agent AI systems, including policy enforcement, approval gates, audit trails, trust scoring, rate limits, and safe tool execution.

agent-supply-chain

Review, generate, and verify supply-chain integrity controls for AI agent tools, plugins, MCP servers, skills, prompts, and custom agents, including SHA-256 manifests, dependency pinning, provenance evidence, promotion gates, and CI verification.

agentic-eval

Use when designing and implementing evaluation loops for AI agents, including reflection, evaluator-optimiser patterns, rubric scoring, LLM-as-judge review, test-driven refinement, convergence checks, and iteration logging.

copilot-cli-quickstart

Beginner-friendly interactive tutorial for GitHub Copilot CLI concepts, slash commands, permissions, file context, planning, and custom instructions.

generate-custom-instructions-from-codebase

Generate GitHub Copilot migration instructions by comparing two project versions and extracting conventions for framework upgrades, refactoring, dependency changes, or technology migrations.

github-copilot-starter

Set up a GitHub Copilot customisation starter pack for a new project based on its technology stack, including instructions, skills, agents, and optional setup workflow files.

foundry-agent-sync

Create and synchronise prompt-based AI agents directly within Azure AI Foundry via REST API, from a local JSON manifest. Unlike scaffolding skills that only generate local code, this skill registers agents in the Foundry service itself — making them immediately available for invocation. Use when the user asks to create agents in Foundry, sync, deploy, register, or push agents to Foundry, update agent instructions, or scaffold the manifest and sync script for a new repository. Triggers: 'create agent in foundry', 'sync foundry agents', 'deploy agents to foundry', 'register agents in foundry', 'push agents', 'create foundry agent manifest', 'scaffold agent sync'.

mcp-cli

Interface for MCP (Model Context Protocol) servers via CLI. Use when you need to interact with external tools, APIs, or data sources through MCP servers, list available MCP servers/tools, or call MCP tools from command line.

mcp-copilot-studio-server-generator

Generate a complete MCP server implementation optimised for Copilot Studio integration with proper schema constraints and streamable HTTP support

nano-banana-pro-openrouter

Generate or edit images via OpenRouter with the Gemini 3 Pro Image model. Use for prompt-only image generation, image edits, and multi-image compositing; supports 1K/2K/4K output.

noob-mode

Plain-English response style for non-technical Copilot CLI users. Explains approval prompts, errors, command output, and technical choices with clear risk indicators.

prompt-builder

Guide users through creating high-quality GitHub Copilot prompt files with clear structure, appropriate tools, validation criteria, and maintainable instructions.

remember

Transform lessons learned into domain-organised memory instructions for global or workspace scope. Syntax: `/remember [>domain [scope]] lesson clue`.

tldr-prompt

Create tldr-style summaries for GitHub Copilot customisation files, MCP server documentation, or Copilot documentation from files, URLs, or focused queries.

mentoring-juniors

Socratic mentoring for junior developers and AI newcomers. Guides through questions, never answers. Triggers: "help me understand", "explain this code", "I'm stuck", "Im stuck", "I'm confused", "Im confused", "I don't understand", "I dont understand", "can you teach me", "teach me", "mentor me", "guide me", "what does this error mean", "why doesn't this work", "why does not this work", "I'm a beginner", "Im a beginner", "I'm learning", "Im learning", "I'm new to this", "Im new to this", "walk me through", "how does this work", "what's wrong with my code", "what's wrong", "can you break this down", "ELI5", "step by step", "where do I start", "what am I missing", "newbie here", "junior dev", "first time using", "how do I", "what is", "is this right", "not sure", "need help", "struggling", "show me", "help me debug", "best practice", "too complex", "overwhelmed", "lost", "debug this", "/socratic", "/hint", "/concept", "/pseudocode". Progressive clue systems, teaching techniques, and success metrics.

performance-review-writer

Draft performance reviews, self-assessments, peer reviews, and upward feedback in your own voice. Analyses your contributions, emails, and meeting history via WorkIQ, then produces honest, impact-focused drafts using the STAR format. USE FOR: write my performance review, draft self-assessment, peer review, 360 feedback, annual review, mid-year review, upward feedback, write review for colleague, performance appraisal.

breakdown-epic-pm

Prompt for creating an Epic Product Requirements Document (PRD) for a new epic. This PRD will be used as input for generating a technical architecture specification.

impediment-prioritisation

Ranks any list of impediments and their countermeasures using a value-stream scoring model (ROI, Cost to Implement, Ease of Deployment, Risk Factor) and a fixed prioritisation formula. Use when someone asks to prioritise, rank, sequence, or triage impediments, countermeasures, remediation items, risks, findings, gaps, action items, or backlog entries; or mentions value-stream prioritisation, A3 / lean countermeasure ranking, ROI vs. effort scoring, or building a remediation / improvement backlog. Works with GHQR findings, audit results, retrospective action items, risk registers, architecture review gaps, or any free-form `{impediment, countermeasure}` list.

prd

Generate high-quality Product Requirements Documents (PRDs) for software systems and AI-powered features. Includes executive summaries, user stories, technical specifications, and risk analysis.

architecture-models-4plus1

Produce Philippe Kruchten's 4+1 architectural view model for a software system, with rendered diagrams (Mermaid primary, PlantUML fallback for deployment) AND Miro RISEN prompts for each view. Use this skill whenever the user mentions "4+1", "architecture views", "architectural documentation", "logical view", "process view", "development view", "physical view", or "deployment view" — and also whenever the user asks to document system architecture, produce architecture blueprints, generate architecture diagrams, or prepare architecture content for review with non-developer stakeholders, even if they don't say "4+1" explicitly. Works with zero-input (user gives a paragraph, skill drafts a full architecture), interview mode (user has detailed context), or partial mode (user wants only one or two views). Flexes notation to audience — UML-flavoured for dev-only audiences, BPMN-style swimlanes for cross-functional audiences, simplified C4 for executives.

create-architectural-decision-record

Create an Architectural Decision Record (ADR) document for AI-optimised decision documentation.

technology-stack-blueprint-generator

Comprehensive technology stack blueprint generator that analyses codebases to create detailed architectural documentation. Automatically detects technology stacks, programming languages, and implementation patterns across multiple platforms (.NET, Java, JavaScript, React, Python). Generates configurable blueprints with version information, licensing details, usage patterns, coding conventions, and visual diagrams. Provides implementation-ready templates and maintains architectural consistency for guided development.

dashboard-beautify

Design and build production-grade dashboards and infographics with Dash and Plotly Python: layout strategy, colour semantics, accessibility, and pre-ship validation. Use when creating or beautifying a dashboard, KPI panel, or data infographic.

dask

Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.

exploratory-data-analysis

Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analysing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations. Covers chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and general scientific data formats.

ai-ready

Guide users to review and install the external ai-ready skill from its upstream repository. Use when the user asks to install or try John Papa's ai-ready skill.

first-ask

Interactive task-refinement workflow that clarifies scope, deliverables, and constraints before carrying out the task. Uses Joyride input tools when available.

what-context-needed

Identify which files or folders Copilot needs to inspect before answering a user question, including required context, helpful context, and uncertainties.

remember-interactive-programming

Micro-skill that reminds the agent to use an available REPL or live runtime as the source of truth during interactive programming tasks.