agentic-design-and-evaluation
claudecodexDesign, compare, and improve from evidence
5 skills
Focused, progressively disclosed language and engineering-method skills for repository-adaptive software development, including concurrency and runtime-specific guidance.
Plugin software-development from marketplace agent-tooling in DevGuyRash/agent-tooling. Commands read from the repo's manifest — 3 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
async-rustUse for async Rust: runtimes, task ownership, overlapping awaits, cancellation at suspension points, backpressure, Send and 'static bounds, pinning, and blocking in executors. Composes with rust-development; excludes synchronous-only Rust.
behavior-preserving-migrationUse when an API, schema, data store, dependency, runtime, implementation language, service, or architecture moves to a new form while its consumers keep working: compatibility windows, backfills, cutover, and rollback. Excludes local refactors.
c-developmentUse for C source, build-classified headers, or tooling: ownership, bounds, undefined behavior, threads, ABI, and errors. Excludes C++-only work.
concurrency-engineeringUse when code in any language starts, bounds, cancels, or joins concurrent work, new or existing: tasks, threads, goroutines, coroutines, workers, callbacks, subprocesses, queues, locks, and shutdown. Excludes one-at-a-time async calls.
cpp-developmentUse for C++ source, build-classified headers, or tooling: RAII and lifetimes, templates, undefined behavior, threads and futures, ABI, and errors. Excludes C-only work.
csharp-developmentUse for C# source, projects, or .NET tooling: nullable references, records and equality, exceptions, disposal, async/await, cancellation, channels, multi-targeting, and NuGet. Excludes ASP.NET- or EF-only work.
go-developmentUse for Go source, modules, or tooling: APIs, errors, context, goroutines and channels, synchronization, resources, and tests. Excludes framework-only and workflow-only work.
java-developmentUse for Java source, builds, or tooling: JDK and --release compatibility, collections and equality, exceptions, interruption, executors and virtual threads, and binary compatibility. Excludes framework-only work.
javascript-developmentUse for JavaScript, JSX, or JSDoc-checked code: modules, promises and async flow, collections, mutability, prototypes, and errors. Excludes TypeScript-only and Node-runtime-only work.
kotlin-developmentUse for Kotlin source, builds, or tooling: null safety, data classes and collections, coroutines, Flow, cancellation, Java interop and binary compatibility, and Multiplatform source sets. Excludes Android-only work with no Kotlin changes.
nodejs-developmentUse for Node.js runtime or package code: ESM/CJS resolution, exports, streams, buffers, the event loop, worker threads, child processes, and shutdown. Composes with JavaScript or TypeScript; excludes browser-only work.
performance-engineeringUse when new or existing code must reach, verify, or review a performance target or claim: latency, throughput, CPU, memory, I/O, or cost, with baselines, profiles, and benchmarks. Excludes slowdowns whose cause is unknown.
php-developmentUse for PHP source, Composer setup, or PHP tooling: types and coercion, public APIs, errors, resources, workers, processes, and security-sensitive input. Excludes framework-only work.
python-developmentUse for Python source, stubs, or pyproject tooling: typing, imports, exceptions, resources, asyncio, threads, processes, and subprocesses. Excludes conceptual Q&A, throwaway one-liners, and publication-only work.
refactoringUse when restructuring code without changing its behavior, or when reviewing such a change: splitting modules, giving duplicated rules one home, untangling dependencies, renames and moves. Excludes features, fixes, migrations, and tuning.
ruby-developmentUse for Ruby source, gems, Bundler setup, or Ruby tooling: dynamic dispatch, keyword and block APIs, errors, resources, threads, fibers, and subprocesses. Excludes Rails-only work.
rust-developmentUse for Rust source, Cargo, or tooling: ownership and borrowing, APIs and errors, features, workspaces, MSRV, threads, and verification. Composes with async-rust, unsafe-rust, and rust-panic-audit; excludes workflow-only work.
rust-panic-auditUse to audit direct panic surfaces (unwrap, expect, panic macros, indexing, arithmetic) in a Rust scope that a request or policy names, such as hostile-input, embedded, FFI, or high-availability boundaries. Compose with rust-development; exclude routine review.
shell-developmentUse for shell scripts, shell modules, or shell-based automation in POSIX sh, Bash, PowerShell, or another shell: quoting, exit status, traps, background jobs, and subprocesses. Excludes incidental one-liners.
software-foundationUse when writing, changing, reviewing, or revising code in any language: the design principles all code meets and existing code is brought to. Excludes questions, prose, and Git operations that touch no code.
sql-developmentUse for relational SQL: queries, schemas, constraints, indexes, transactions, isolation, migrations, or SQL embedded in host-language code. Excludes NoSQL and database administration without SQL effects.
swift-developmentUse for Swift source, SwiftPM packages, or tooling: optionals, errors, value and reference semantics, ARC, async/await, actors, Sendable, and API or ABI compatibility. Excludes Apple-UI-only, signing, and Xcode-project work.
systematic-debuggingUse when a bug, failure, crash, hang, flaky test, unexpected output, or regression has an unknown cause: reproduction, falsifiable hypotheses, discriminating probes, and a fix of the cause. Excludes known-cause fixes.
test-driven-developmentUse when adding or changing executable behavior or fixing a known bug: a failing test that shows the gap, the smallest change that passes it, then cleanup. Excludes unknown-cause diagnosis and behavior-neutral refactors.
trunk-based-developmentUse when integration strategy needs mergeable slices, short branches, safe incomplete work, or divergence recovery. Excludes routine Git/PR operations, CI, releases, and governance.
typescript-developmentUse for TypeScript, TSX, declaration files, tsconfig settings, or typed APIs: type modeling, narrowing, generics, runtime validation, promises and async flow, and emitted output. Excludes JavaScript-only and Node-runtime-only work.
unsafe-rustUse for unsafe Rust: unsafe blocks, fns, traits, impls, and attributes, `static mut`, extern blocks, raw pointers, MaybeUninit, FFI and layout, assembly and intrinsics, provenance and aliasing, pin projection, unsafe Send or Sync, lock-free code, and thread-affine handles. Compose with rust-developm
sh -c 'p="${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-}}"; [ -n "$p" ] && [ -f "$p/hooks/review-turn-stop.py" ] && exec python3 "$p/hooks/review-turn-stop.py"; exit 0'
Design, compare, and improve from evidence
5 skills
Browser tests, application surveys, and reproducible evidence with headless or isolated headed execution
2 skills
Visualize anything creatively and faithfully
2 skills
Operate ChatGPT reliably through an authorized browser
1 skill
Generate 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.
1 skill
Comprehensive dynamic form patterns for Espanso
1 skill
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Action-first, ADHD-friendly output shaping for Claude Code.
1 skill · hooks
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.