DevGuyRash
- 40 skills
- 0 followers
- 10 hours ago last updated
- ▌ Diagram · devguyrash bundleProduce polished standalone visuals as files and open them in the browser — SVG flowcharts, architecture and containment diagrams, illustrative explainers, decision tables, level ladders, charts (Chart.js), geographic choropleth maps (D3), database ERDs (mermaid), interactive HTML explainers with sliders and steppers, UI mockups, and SVG art. Use this skill whenever the user asks for a diagram, chart, graph, map, mockup, visualization, schematic, ladder, or illustration, or says "draw", "sketch", "visualize", "plot", "show me", or "illustrate" about any structure, process, data, comparison, or concept — even if they never mention SVG or HTML.
- ▌ Authoring Goals · devguyrash bundleShape vague intent into clearer product decisions before execution. Use when the task involves: (1) exploring ambiguous product, design, or implementation directions with an Option Map, (2) converging on a chosen direction before writing durable context/docs artifacts, (3) generating Probe Packs with acceptance examples, adversarial checks, non-goals, and final source review prompts before handoff, or (4) reviewing planning output for premature docs, false blockers, HOW leakage, weak probes, and lost source nuance. Do not use for direct execution unless a probe note or handoff is needed first.
- ▌ Excel Foundry · devguyrash bundleInspect, create, diff, document, audit, automate, and sync Excel workbook artifacts across package-readable workbooks, safe copies, installed desktop Excel, Microsoft Graph workbook APIs, Office Scripts/Add-in hosts, and Fabric/Power BI semantic models. Use when the task involves: (1) workbook lifecycle or direct commands such as inspect/diagnose/capabilities/create/diff/save-as/ convert/repair/compatibility/document-inspect, sheet/table/range/cell/name edits, links, safe export, formulas, calc, Solver, scenarios, forecasts, data tables, or automation artifacts, (2) package inventory or preservation for charts, pivots, slicers, timelines, Power Query, connections, XML/custom XML, OLE, signatures, encryption, sensitivity, VBA/package metadata, or embedded media, (3) desktop Excel host operations, (4) Graph, Office Scripts, Office.js/Add-in, Fabric, Power BI, DAX, TMDL, PBIP, or semantic-model operations, or (5) manifest/artifact synchronization, audit bundles, parity reports, and portable workbook manifests.
- ▌ Chatgpt Browser · devguyrash bundleOperate ChatGPT in a user-authorized interactive browser across models, reasoning levels, Projects, ordinary or temporary chats, attachments and pasted context, apps and custom GPTs, response waiting, and thread hygiene. Use when an agent is asked to interact with ChatGPT through a browser; do not use for OpenAI API calls, ordinary web browsing, non-ChatGPT browser tasks, or generic second-model review unless the user specifically requests ChatGPT in the browser.
- ▌ Project Harness · devguyrash bundleDetects repo languages, frameworks, task runners, distribution shape, and CI surface, then scaffolds or updates a repo-level harness: justfile, GitHub Actions CI/dist workflows, .gitignore/.gitattributes support files, and local state under .local/harness/. Use when the task involves: (1) Bootstrapping a new or existing repo with a standardized command surface, (2) Creating or updating a justfile with build, test, lint, fmt, ci, dev, or dist recipes, (3) Scaffolding GitHub Actions CI or distribution workflows, (4) Configuring .gitignore, .gitattributes, or Git LFS for a project, (5) Standardizing or updating a project command surface without rewriting build system internals, or (6) Any task requiring repo-level harness scaffolding or project command surface management.
- ▌ Async Rust · devguyrash bundleREQUIRED for Rust async runtime, task-lifecycle, cancellation, backpressure, Send-boundary, or pinning work—do not write, review, debug, or scaffold those surfaces without this skill. Always compose with rust-development; exclude synchronous-only work. If Rust work is asynchronous, use this skill.
- ▌ Refactoring · devguyrash bundleUse for nontrivial restructuring when declared behavior stays unchanged. Covers baselines, modularity, cohesion, and duplication; exclude features, fixes, migrations, and tuning.
- ▌ Unsafe Rust · devguyrash bundleREQUIRED whenever Rust work touches `unsafe {}`, `unsafe fn`, `unsafe trait` or `unsafe impl`, `static mut`, unsafe extern items or blocks, `#[unsafe(...)]`, raw pointers or owners, `MaybeUninit`, FFI, ABI or layout, assembly or intrinsics, provenance or aliasing, pinning, unsafe `Send` or `Sync`, lock-free code, or thread-affine foreign handles. Do not write, review, debug, or scaffold these surfaces without this skill. Always compose with rust-development; exclude safe-only Rust. If unsafe Rust is in scope, use this skill.
- ▌ Docker Architect · devguyrash bundleGenerate hardened, production-ready Docker architecture including Dockerfiles, Compose stacks, and Swarm deploy configs. Use when the task involves: (1) Writing or improving a Dockerfile or multi-stage build, (2) Containerizing an application (Python, Node.js, Rust, Go, Nginx, or custom stacks), (3) Creating or modifying compose.yaml or Docker Swarm deployments, (4) Hardening container security, healthchecks, secrets management, or resource limits, (5) Setting up CI/CD container scanning or image supply-chain controls (hadolint, trivy, docker scout, SBOM, provenance), or (6) Any task involving Docker, containers, or container orchestration.
- ▌ Friction Mend · devguyrash bundleBatch-mend accumulated friction: cluster open events, root-cause them, fix the artifacts and instructions that misled, record resolutions, and distill recurring traps into known-traps.md. Use when the user asks to: (1) Review or triage an existing friction corpus, backlog, or dashboard, (2) Mend, resolve, or close logged friction events, (3) Distill or refresh known-traps.md, or (4) Work through friction accumulated across sessions. Do not use for logging new incidents (that is friction-diagnostics) or for reviewing the plugin's own implementation.
- ▌ C Development · devguyrash bundleUse for substantive C source, build-classified headers, or tooling. Covers ownership, bounds, undefined behavior, ABI, and errors; exclude C++-only work.
- ▌ Go Development · devguyrash bundleUse for substantive Go source, modules, or tooling. Covers APIs, errors, context, concurrency, resources, and tests; exclude framework-only and workflow-only work.
- ▌ Cpp Development · devguyrash bundleUse for substantive C++ source, build-classified headers, or tooling. Covers RAII, templates, undefined behavior, ABI, and errors; exclude C-only work.
- ▌ PHP Development · devguyrash bundleUse for substantive PHP source, Composer, or tooling. Covers types, APIs, errors, resources, and security-sensitive behavior; exclude framework-only work.
- ▌ SQL Development · devguyrash bundleUse for relational SQL queries, schemas, constraints, transactions, isolation, migrations, or embedded SQL. Compose with host languages; exclude NoSQL and administration without SQL effects.
- ▌ Playwright Testing · devguyrash bundleDesign durable, outcome-oriented Playwright and browser e2e tests that prove product behavior instead of recording today's DOM. Use when the task involves: (1) Creating, reviewing, or refactoring Playwright tests, (2) Designing selector strategies, page objects, fixtures, e2e assertions, or trace/artifact capture, (3) Reducing brittle selectors, fixed waits, layout assertions, or flaky authenticated flows, (4) Testing third-party, authenticated, frequently changing, or browser-extension UIs, or (5) Any task involving Playwright e2e test design or brittle-test cleanup.
- ▌ Java Development · devguyrash bundleUse for substantive Java source, builds, or tooling. Covers JDK compatibility, APIs, exceptions, resources, concurrency, and ABI; exclude framework-only work.
- ▌ Ruby Development · devguyrash bundleUse for substantive Ruby source, gems, Bundler, or tooling. Covers dynamic behavior, APIs, errors, resources, concurrency, and tests; exclude Rails-only work.
- ▌ Rust Development · devguyrash bundleUse for substantive Rust source, Cargo, or tooling. Covers ownership, APIs/errors, workspaces, MSRV, and verification; compose async-rust, unsafe-rust, or rust-panic-audit as needed; exclude workflow-only work.
- ▌ Rust Panic Audit · devguyrash bundleUse when direct-panic auditing is explicit, policy-required, or material at a hostile-input, embedded, FFI, or high-availability boundary. Compose with rust-development; exclude routine review.
- ▌ Shell Development · devguyrash bundleUse for substantive shell scripts, shell modules, or shell-based automation. Select rules by the declared interpreter; covers POSIX sh, Bash, PowerShell, and an explicit fallback for other shells. Excludes incidental one-liners.
- ▌ Swift Development · devguyrash bundleUse for substantive Swift source, SwiftPM, or tooling. Covers optionals, errors, ownership, concurrency, APIs, and ABI; exclude Apple-UI-only, signing, and Xcode-architecture work.
- ▌ Csharp Development · devguyrash bundleUse for substantive C# source, projects, or .NET tooling. Covers nullability, disposal, async, APIs, and targets; exclude framework-only ASP.NET/EF and workflow-only work.
- ▌ Kotlin Development · devguyrash bundleUse for substantive Kotlin source, builds, or tooling. Covers nullability, JVM interop/ABI, coroutines, and cancellation; exclude Android/framework-only work without Kotlin changes.
- ▌ Nodejs Development · devguyrash bundleUse for Node.js runtime or package work involving ESM/CJS resolution, exports, streams, buffers, processes, or resource lifecycles. Compose with JavaScript or TypeScript; exclude browser-only work.
- ▌ Python Development · devguyrash bundleUse for substantive Python source, stubs, or pyproject tooling. Covers typing, exceptions, resources, and concurrency; exclude Q&A, scratch code, and distribution/publication-only work.
- ▌ Friction Diagnostics · devguyrash bundleLog genuine surprise — reality diverged from what you predicted — as structured friction records with recurrence tracking. Use when: (1) A tool, command, instruction, document, or assumption behaved differently than expected, in any domain (code, non-code, writing, research, ops), (2) An action silently no-opped, half-applied, or succeeded without its intended effect, (3) Behavior differs across environments or runs in a way you did not predict, (4) An expected failure occurred for a different reason than predicted, (5) A known trap bit again — file --recur against the earlier event, or (6) The user asks to log a friction incident. Worth-logging test: would the record change what a future session does? Do not use for outcomes you predicted for the reason you predicted (intended test failures, expected error paths, probes), for task status, or for reviewing or mending accumulated friction (that is friction-mend).
- ▌ Systematic Debugging · devguyrash bundleUse for bugs, failures, crashes, hangs, unexpected output, or regressions with unknown cause. Own reproduction, hypotheses, and probes; exclude known-cause implementation.
- ▌ Skill Auditor · devguyrash bundleReview existing Agent Skills and plugins for instruction quality, discovery, dependencies, portability, executable behavior, and useful completion.
- ▌ Split Testing · devguyrash bundleCompare prompts, systems, processes, and other alternatives through experiments, benchmarks, or existing evidence to support decisions.
- ▌ Espanso Dynamic Forms · devguyrash bundleBuild portable dynamic Espanso forms where a script or binary generates form layouts at runtime. Use when the task involves: (1) Creating or modifying Espanso form triggers or match files, (2) Building dynamic Espanso forms with runtime-generated layouts or choices, (3) Scaffolding a new Espanso form provider pattern, (4) Configuring Espanso YAML for scripted fields or runtime-generated options, (5) Debugging or linting Espanso form configurations, (6) Implementing clipboard or output patterns for Espanso expansions, or (7) Any task involving Espanso text expansion with dynamic or scripted form UIs.
- ▌ Javascript Development · devguyrash bundleUse for substantive JavaScript, JSX, or JSDoc/checkJs work. Covers modules, promises, mutability, and prototypes; exclude TypeScript-only and Node-runtime-only work.
- ▌ Typescript Development · devguyrash bundleUse for substantive TypeScript, TSX, declarations, compiler settings, or typed APIs. Covers modeling, narrowing, and generics; exclude JavaScript-only and Node-runtime-only work.
- ▌ Concurrency Engineering · devguyrash bundleUse when task, thread, actor, worker, callback, cancellation, backpressure, synchronization, or parallel-execution contracts materially shape software behavior. Compose with language/runtime and performance skills; exclude trivial async syntax and Rust-runtime work owned by async-rust.
- ▌ Performance Engineering · devguyrash bundleUse when latency, throughput, CPU, memory, allocation, I/O, scale, or cost is explicit. Requires measurement; exclude unknown-cause regressions and speculative tuning.
- ▌ Test Driven Development · devguyrash bundleUse for changed executable behavior or a known bug when a test can show the gap. Own red, green, and cleanup; exclude unknown-cause diagnosis and behavior-neutral refactors.
- ▌ Trunk Based Development · devguyrash bundleUse when integration strategy needs mergeable slices, short branches, safe incomplete work, or divergence recovery. Excludes routine Git/PR operations, CI, releases, and governance.
- ▌ Behavior Preserving Migration · devguyrash bundleUse for API, schema, data, dependency, runtime, service, storage, or architecture transitions with declared compatibility, cutover, and rollback; exclude local refactors.
- ▌ Prompt Context Design · devguyrash bundleWrite, revise, or assess AI prompts and execution plans, and arrange the instructions, context, and handoffs needed to carry out a task.
- ▌ Foundational Knowledge · devguyrash bundleExplain principles of AI delegation, authority, grounding, independent understanding, continuity, and evaluation, and consult the authoring charter.