ThomasRohde

Create or update independent vendor positioning matrix reports. Use when asked for magic quadrant style vendor comparisons, analyst-style market matrices, provider landscapes, technology shortlists, two-axis vendor charts, sourced scoring models, or PDF, Microsoft Word/DOCX, and Markdown vendor evaluation packages. Produces original, evidence-led reports with source ledgers, transparent scoring, bank/regulatory due diligence, and safeguards against Gartner or other analyst-firm imitation.

Create and edit checkpointflow workflow YAML files. Use this skill whenever the user wants to create a workflow, automate a process as a YAML pipeline, define steps that mix CLI commands with human or agent checkpoints, turn a conversation into a reusable runbook, or asks about writing cpf/checkpointflow workflows. Also use it when you see keywords like "workflow", "runbook", "approval flow", "pause and resume", or "await event" in the context of automation.

Create and improve Claude Code skills using a structured checkpointflow workflow with test-driven iteration. Use this skill whenever the user wants to create a skill, make a skill, build a skill, improve an existing skill, test a skill with evals, benchmark skill quality, optimize a skill description, or turn a conversation into a reusable skill. Also triggers on "skill for X", "automate this as a skill", "package this as a skill", and similar phrases.

Create new architecture evaluation rubrics (profiles and overlays) based on the Enterprise Architecture Rubric Operational Standard (EAROS). Use this skill whenever the user wants to "create a rubric", "add a rubric profile", "write an architecture evaluation rubric", "define scoring criteria for architecture artifacts", "create an EAROS profile", "add an overlay", "create a security overlay", "create a data overlay", "evaluate architecture artifacts", "set up architecture review criteria", "build a rubric for solution architecture", "create an ADR rubric", "create a capability map rubric", "define architecture quality criteria", or mentions "EAROS", "rubric", "architecture evaluation", "scoring profile", or "architecture review criteria" in the context of creating or extending evaluation rubrics. Also triggers when the user says "help me evaluate architecture documents", "define review criteria for our artifacts", "standardize architecture review", "create a review checklist", or any request to systematicall

Apply an EAROS rubric to an architecture artifact using the three-pass agent evaluation pattern (Extractor, Evaluator, Challenger). Use this skill whenever the user wants to "evaluate an architecture artifact", "apply a rubric", "review an architecture document", "score an architecture artifact", "run an EAROS evaluation", "assess architecture quality", "apply the solution architecture rubric", "evaluate this ADR", "review this capability map", "check this against the rubric", "run the architecture review", or mentions "evaluate", "score", "assess", "review", or "apply rubric" in the context of applying an EAROS rubric to a specific artifact. Also triggers when the user says "how does this artifact score", "is this architecture document good enough", "run the three-pass evaluation", "extract evidence from this document", or any request to systematically evaluate a specific architecture work product against defined criteria. Does NOT trigger for creating rubrics (use earos-rubric for that), general architectur

Autonomous agent-driven optimization loop inspired by Karpathy's autoresearch. Sets up and runs an iterative hill-climbing harness where subagents modify an artifact, evaluate against a single scalar metric, and keep improvements. Use this skill whenever the user wants to "optimize something iteratively", "run an autoresearch loop", "hill-climb on performance", "auto-optimize", "iterate and improve automatically", "run experiments autonomously", "autonomous optimization", or mentions "autoresearch" in any context. Also triggers when the user describes a workflow like "try variations and measure which is best", "keep tweaking until it's faster", "optimize this config", "find the best prompt", "tune hyperparameters", "benchmark variations", or any scenario where they want an agent to autonomously explore a search space against a measurable objective. Works with any domain — code performance, prompt engineering, config tuning, SQL optimization, CSS optimization, model training, build flags, or anything with a me

Discover, audit, reconcile, modify, and delete GitHub Copilot customizations across both Copilot IDE (VS Code) and Copilot CLI environments. Use this skill whenever the user wants to "list copilot customizations", "find copilot files", "audit copilot setup", "what copilot configs do I have", "reconcile copilot IDE and CLI", "clean up copilot files", "delete copilot agent", "show copilot instructions", "compare copilot configs", "remove unused copilot customizations", "copilot drift", "copilot inventory", "what does copilot see", "manage copilot", "copilot hygiene", or any request involving exploring, inspecting, modifying, or removing existing Copilot customization files. Also triggers when the user mentions conflicts between Copilot IDE and Copilot CLI, cross-readability issues, or wants to understand which files each Copilot variant sees. Does NOT trigger for creating new customizations from scratch (use copilot-customization skill instead).

Generate enterprise-ready, agent-first CLIs from OpenAPI or Swagger specifications. Use this skill whenever the user wants to "generate a CLI from an OpenAPI spec", "turn a Swagger API into a CLI", "scaffold an enterprise REST CLI", "create a CLI wrapper around a REST API", "derive a machine-readable CLI from an API description", "generate auth-aware commands from an OAS file", "build a deterministic CLI for this service", "create an agent-friendly CLI from this API", or mentions "api-anything", "OpenAPI CLI", "Swagger CLI", "REST CLI generator", "OAS to CLI", or "API CLI scaffold" in the context of generating CLI code from an API specification. Also triggers when the user provides an OpenAPI/Swagger spec file and asks to build a command-line tool from it, even if they don't use the exact term "CLI". Does NOT trigger for generic API discussion, SDK generation, client library generation, API debugging, or consuming an existing CLI.

Create architecture documents through guided interview. Triggers on "create an architecture document", "generate a reference architecture", "help me write a solution architecture", "document my architecture", "new architecture document", or any request to create/write/generate architecture artifacts.

Run a full EAROS evaluation on an architecture artifact. Triggers when the user wants to assess, evaluate, score, or review an architecture document using the EAROS framework. Also triggers for "score this architecture", "evaluate this ADR", "run EAROS on this", "assess this capability map", "review this solution design", "is this architecture any good", "quality check this design", "grade this document", "what score would this get", or any request to evaluate, rate, or assess the quality of an architecture artifact.

Generate executive reports from EAROS evaluation records. Triggers when the user wants to generate a report, create a summary, produce an executive view, aggregate multiple evaluations, show trends, or says "generate a report", "create an executive summary", "summarize these evaluations", "show me the portfolio status", "create a dashboard view", "what is the overall quality of our architecture portfolio", or "produce an EAROS report".

Run EAROS calibration exercises to validate rubric reliability before production use. Use this skill whenever someone wants to calibrate a rubric, validate inter-rater reliability, compare scores against gold-standard artifacts, measure scoring consistency, or says "calibrate this rubric", "run calibration", "check if the rubric is reliable", "compare my scores to the gold set", "test this profile against examples", "is this rubric ready for production", "what is our kappa", "measure agreement between reviewers", "validate a new profile", or "how well does the rubric score consistently". Calibration is required before any new profile can move from draft to candidate status.

Create a new EAROS rubric — core rubric, artifact profile, or cross-cutting overlay. Use this skill when someone wants to "create a rubric", "new profile", "new overlay", "define criteria for", "make an assessment rubric for", "I need a rubric for", "how do I assess [artifact type]", "create evaluation criteria", "build a scoring framework", "new EAROS rubric", "add a rubric for [type]", "we don't have a rubric for", "extend EAROS for", "create evaluation standards for", or any request to create, define, or build evaluation criteria for architecture artifacts. Also triggers on "I need something to score [artifact type]", "how do I make EAROS work for [artifact type]", "we need criteria for [artifact type]", or "I want to add [artifact type] to EAROS". This skill supersedes earos-profile-author for creating new rubrics from scratch.

Technical YAML authoring guide for EAROS profiles and overlays. Use this skill when someone has already completed rubric design (criteria defined, design method chosen) and needs help with the YAML structure, v2 field requirements, or schema compliance. Also triggers when someone asks "what are the 5 design methods", "how do I write a criterion", "what fields does a v2 criterion need", or "how do I structure overlay YAML". NOTE: For creating new rubrics from scratch — where the criteria are not yet defined — use earos-create instead. This skill focuses on the technical details of profile YAML authoring after rubric design is complete.

Generate a prioritized improvement plan from an EAROS evaluation. Triggers on "how do I fix this", "improve this artifact", "remediation plan", "how to pass EAROS", "fix the assessment", "improvement plan", "what's wrong with my architecture", "how to get a better score", or any request to improve an artifact based on evaluation results.

Challenge and peer-review an existing EAROS evaluation record. Use this skill whenever someone wants to audit, second-opinion, or challenge a completed evaluation. Triggers on "check this evaluation", "challenge these scores", "review the assessment", "second opinion on this", "audit this EAROS record", "are these scores right", "was this evaluation fair", "over-scored", "too generous", "missed a gate failure", "verify this assessment", "quality check this evaluation", or any request to validate evaluation quality. Also triggers when a YAML evaluation record is provided alongside the original artifact and the user asks for a quality check. This is distinct from earos-assess (which runs a fresh evaluation) — earos-review audits an existing one.

Plan safe batches of ECM Studio capability changes from a JSON operation list by validating IDs, names, parents, hierarchy rules, lifecycle operations, and command ordering before execution. Use for bulk reparenting, renaming, retiring, deleting draft leaves, or merge planning in ECM model repositories.

Safely create, update, move, retire, merge, and delete capabilities in ECM Studio repositories that store authoritative data in ecm/capabilities.jsonl and ecm-studio.json. Use this whenever the user asks to add capabilities, rename or reparent capabilities, change lifecycle state, merge duplicates, delete mistaken draft leaves, or otherwise modify capability data in an ECM repo, even if they do not mention JSONL files or ECM Studio by name.

Audit governance and traceability evidence in ECM Studio model repositories, including structural-operation rationale, downstream handling, retired capability traceability, ownership metadata, audit file health, release records, and publish evidence. Use before governance reviews and releases.

Analyze impact for a capability in ECM Studio model repositories by finding ancestors, descendants, replacement links, audit events, and generic JSON references in mappings, downstream consumers, change requests, and tasks. Use before retire, merge, delete, move, or major capability changes.

Convert external CSV capability exports into ECM Studio import-ready CSV, JSONL, or bundled JSON for ECM model repositories. Use when Codex needs to map source columns to capability fields, generate stable import files, validate import shape, or prepare data for ECM Studio import without editing the live ecm/capabilities.jsonl file.

Summarize ECM Studio capability model differences between two Git refs in an ECM model repository, including added, removed, renamed, moved, retired, lifecycle-changed, metadata-changed, and type-transitioned capabilities. Use for branch reviews, release notes, and scenario comparison.

Review ECM Studio model repositories for capability quality issues such as weak descriptions, missing ownership metadata, duplicate-like names, uneven decomposition, lifecycle inconsistencies, and missing tags or domains. Use before reviews, releases, restructuring, or governance checks.

Validate, inspect, and diagnose ECM Studio repositories that store capability data in ecm/capabilities.jsonl. Use this whenever the user asks whether an ECM repo is valid, wants to inspect capability IDs and paths, needs help understanding capability hierarchy issues, or before and after capability edits in an ECM repo, even if they only say the model seems broken or inconsistent.

World-class creation of valid, beautiful, and accessible Mermaid diagrams. Use when users request diagrams, flowcharts, sequence diagrams, entity relationship diagrams, state machines, Gantt charts, class diagrams, or any visual representation that can be expressed in Mermaid syntax. Handles all Mermaid diagram types with expert knowledge of syntax, styling, and best practices.

Expert guidance for creating strands-cli workflow specifications (YAML/JSON). Use when creating, modifying, or troubleshooting strands-cli specs for: (1) Multi-step agent workflows (chain, routing, parallel, graph patterns), (2) Tool configuration (python_exec, http_request, custom tools), (3) Runtime and provider setup (Bedrock, OpenAI, Ollama), (4) Input/output handling and templating, or (5) Debugging validation errors

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

Run, resume, and manage checkpointflow workflows interactively. Use this skill whenever the user wants to run a workflow, execute a YAML pipeline, resume a paused run, check workflow status, cancel a run, or interact with cpf at runtime. Also triggers on phrases like "run the workflow", "execute this", "resume the run", "what's the status", or when the user provides input for a waiting workflow step.

Create and improve Claude Code skills using a structured checkpointflow workflow with test-driven iteration. Use this skill whenever the user wants to create a skill, make a skill, build a skill, improve an existing skill, test a skill with evals, benchmark skill quality, optimize a skill description, or turn a conversation into a reusable skill. Also triggers on "skill for X", "automate this as a skill", "package this as a skill", and similar phrases. Always use this instead of the generic skill-creator when in the checkpointflow repo.

Create and edit checkpointflow workflow YAML files. Use this skill whenever the user wants to create a workflow, automate a process as a YAML pipeline, define steps that mix CLI commands with human or agent checkpoints, turn a conversation into a reusable runbook, or asks about writing cpf/checkpointflow workflows. Also use it when you see keywords like "workflow", "runbook", "approval flow", "pause and resume", or "await event" in the context of automation.

Run the full quality gate — formatting, linting, type checking, and tests. Use after implementing changes to confirm everything passes.

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

This skill should be used when the user asks to "write a JArchi script", "create an Archi script", "build an .ajs script", "add a dialog to a script", "use SWT widgets", "create a JFace dialog", "use Eclipse UI in JArchi", "extend a Java class in JavaScript", "use Java.type()", "work with ArchiMate elements", "use the jArchi API", "create a library module", "use GraalJS", mentions JArchi, Archi scripting, ArchiMate modeling scripts, SWT/JFace UI, or GraalVM JavaScript for Archi.

This skill should be used when the user asks to "use the model API server", "call the API", "query the model via HTTP", "create elements via API", "use curl with Archi", "interact with the REST API", "use the plan/apply pattern", "plan and apply changes", "run a script via API", "export a view via API", "search elements via HTTP", mentions the Model API Server, REST endpoints, or HTTP-based model operations against the JArchi server running on localhost:8765.

This skill should be used when the user asks to "migrate a JArchi script", "import a script from GitHub", "integrate an external script", "adapt a script to this project", "convert a script to project conventions", "port a script to this project", or mentions migrating, importing, porting, or integrating JArchi/Archi scripts from external repositories or sources into this project.

Cut a release atomically — bump version, date the CHANGELOG section, commit, tag. Invoke with /cut-release X.Y.Z.

Run the full mdvw quality gate — ruff, pytest, and the vendor-manifest hash check. Invoke with /verify.

Build enterprise PowerPoint decks using the `pptx` and `excal` CLI tools. Use this skill whenever the user wants to create a PowerPoint presentation, generate slides from a template, build a deck with diagrams, or produce consulting-style slide content. Also triggers for requests involving .pptx files, slide decks, presentation generation, Excalidraw diagrams for slides, or McKinsey/consulting-style deliverables. If the user mentions "pptx", "excal", "slides", "deck", "presentation", or "PowerPoint" in the context of creating output, use this skill.

How to use the `pptx` CLI to create PowerPoint presentations from enterprise templates. Use this skill whenever the user wants to create, build, or generate PowerPoint slides or decks, work with .pptx templates, inspect slide layouts or placeholders, validate presentations, or anything related to PowerPoint generation from the command line. Also trigger when the user mentions deck specs, slide layouts, manifest packages, or template-bound presentation workflows. Even if the user just says "make me a presentation" or "create some slides", this skill applies.

This skill should be used when the user asks to "write an A0 program", "create an A0 script", "generate A0 code", "write a .a0 file", "A0 syntax", "A0 example", "how to write A0", "A0 language", or needs to produce any new A0 source code. Provides the complete syntax, type system, tool signatures, stdlib, and idiomatic patterns needed to author correct A0 programs.

This skill should be used when the user asks to "debug an A0 program", "fix A0 error", "understand A0 error", "A0 diagnostic", "A0 exit code", "read A0 trace", "why does my A0 program fail", "A0 parse error", "A0 capability denied", "A0 runtime error", or needs to diagnose, understand, or fix issues in existing A0 source code.

Publishing assistant for Thomas's Astro-based GitHub Pages site (readme-pages). Creates publish-ready Markdown files for notes, recipes, and pages. Use when asked to write blog posts, articles, notes, recipes, or content for the readme-pages site at thomasrohde.github.io/readme-pages. Also use for content requests mentioning "publish", "blog", or "my site".

Create new pages or notes in the readme-pages project. Use when the user asks to create, add, or write a new page, note, article, or blog post. This skill handles file creation with proper frontmatter, filename conventions, and placement in the correct content collection.

Model and evolve ArchiMate architectures through the local Archi MCP server with semantically correct element and relationship choices. Use when asked to create/update Archi models, generate views, map capabilities to applications/technology, or apply migration roadmaps using safe async operations.

Helps users discover agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. Always ask the user for permission before installing any skill, and flag security risks.