lamuniercosta
UserGated, spec-driven pipeline for AI coding agents — Cursor + Claude Code, no paid services
Categories
Indexed Skills (26)
k6-load-testing
Comprehensive k6 load testing skill for API, browser, and scalability testing. Write realistic load scenarios, analyze results, and integrate with CI/CD.
improve-codebase-architecture
Scan a .NET codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
scaffold
Scaffold a complete feature slice matching the repo's existing architecture — request/command type, handler, validator, DTOs, DI registration, and tests — never a half-feature. Use for "scaffold", "create feature", "add command", "add query", "new endpoint", "add validator", "generate feature".
ship-review
Pre-PR review gate. Runs verification, then fans out a parallel review — code review, security review, and mutation/coverage analysis — and consolidates findings before opening a PR. Use when: "ship", "ready to PR", "final review", "ship review", "pre-PR review".
handoff
Compact the current conversation into a handoff document for another agent to pick up.
start-issue
Repo-local wrapper around harness /task for this repository only. Takes a GitHub issue number and optional branch type, runs the same intake/branch flow as /task, then moves the issue to In Progress on every GitHub Project board item whose Status is empty, Todo, or Backlog. Warns and continues if the issue is on no project. Use when starting work from a GitHub issue in this repo (prefer over /task here so the Portfolio board updates). Not shipped by install.ps1 — lives under .claude/skills/, not packaged skills/.
architect
Run Stryker mutation testing, Gherkin mutation, coverage gap check, and full test suite. Route survivors back to gherkin/implement/refactor.
code-review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along three axes — Risk (bugs, security, concurrency, coverage gaps), Standards (does the code follow this repo's documented standards?), and Spec (does it match what the issue/spec asked for?). Scores blast radius, runs a Roslyn pre-pass, fans out to parallel sub-agents, verifies findings, and reports them severity-ranked. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
codebase-design
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
convention-learner
Detects and enforces this project's coding conventions by analyzing existing code before generating new code. Learns naming, folder structure, test organization, and style from the codebase. Use for "conventions", "coding standards", "project patterns", "enforce style", "detect patterns", "learn conventions", "code consistency".
diagnosing-bugs
Diagnosis loop for hard bugs and performance regressions in .NET codebases. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
domain-modeling
Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
gherkin
(OPTIONAL / opt-in for now) Convert tasks.md user stories into pruned Gherkin feature files under specs/<feature>/acceptance/. Run after human gate 1 (spec/tasks approved), only when acceptance tests are wanted.
implement
Implement feature from tasks.md with xUnit tests and production code (plus Reqnroll acceptance bindings when acceptance tests exist). TDD optional — all tests must pass before handoff. Run after human gate 1 (or human gate 2 when acceptance tests were generated).
modern-csharp
Modern C# language features for .NET 10 and C# 14. Covers primary constructors, collection expressions, the field keyword, extension members, records, pattern matching, spans, and raw string literals. Load this skill when writing any new C# code, reviewing existing code for modernization, using "modern C#", "C# 14", "primary constructor", "collection expression", "records", "pattern matching", "span", "field keyword", or "extension members".
opentelemetry
OpenTelemetry observability for .NET 10 applications. Covers traces, metrics, and logs using the OpenTelemetry SDK with OTLP export. Includes custom ActivitySource, IMeterFactory metrics, resource configuration, and Aspire Dashboard integration. Load this skill when setting up distributed tracing, custom metrics, OTLP export, or when the user mentions "OpenTelemetry", "OTLP", "traces", "spans", "Activity", "ActivitySource", "metrics", "IMeterFactory", "Meter", "Counter", "Histogram", "Gauge", "telemetry", "observability", "distributed tracing", "OTEL", or "Aspire Dashboard".
refactor
Refactor changed code down to the refactor complexity threshold, remove duplication, add FsCheck property tests. Run after /implement.
resilience
Resilience patterns for .NET 10 applications using Polly v8. Covers retry, circuit breaker, timeout, fallback, rate limiter, hedging, and composing resilience pipelines. Load this skill when implementing retry logic, circuit breakers, handling transient failures, or when the user mentions "Polly", "resilience", "retry", "circuit breaker", "timeout", "fallback", "rate limit", "hedging", "transient fault", "HttpClient resilience", or "resilience pipeline".
task
The entry point for any new task. Takes a GitHub issue number and (optionally) a branch type, reads the issue title/body via the gh CLI, creates a correctly-named branch off the latest default branch (feature/bug/hotfix), then hands off to the mandatory /grill-with-docs alignment step. Also handles the rebase step before a PR. Use when the user gives an issue number, says "start task", "create a branch for", "new feature/bug/hotfix", or "rebase before PR".
test-engineer
QA-engineer persona for test strategy, writing tests for existing code, and coverage-gap analysis (xUnit, FsCheck property tests, Testcontainers, WireMock, Reqnroll acceptance, k6). Use when designing test suites, adding tests, doing a Prove-It test for a bug, or evaluating test quality.
testing
Testing strategy for .NET 10 applications. Covers xUnit v3, WebApplicationFactory for integration tests, Testcontainers for real database testing, Verify for snapshot testing, and the AAA pattern. Load this skill when writing tests, setting up test infrastructure, reviewing test coverage, or when the user mentions "test", "xUnit", "WebApplicationFactory", "Testcontainers", "integration test", "unit test", "bUnit", "snapshot test", "Verify", "test coverage", "AAA pattern", "WireMock", or "FakeTimeProvider".
using-agent-skills
Meta-skill that discovers which skill(s) apply to the current task and governs how they are invoked. Use at the start of any non-trivial task, when unsure which skill fits, or to see how supporting skills slot into the gated pipeline.
verify
Run a multi-phase verification pipeline for .NET projects — build, analyzers, complexity, inspections, tests, property tests, security, format, mutation, and diff review — reporting PASS/WARN/FAIL per phase and short-circuiting on critical failures. Use when: "verify", "check everything", "is this ready", "pre-PR check", "run all checks", "quality gate", or after completing a feature or refactor.
grill-with-docs
A relentless interview to sharpen a plan or design, which also creates docs (ADRs and glossary) as we go. Run before /speckit-specify so the spec is written from settled vocabulary.
grilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
pipeline
Orchestrator for the Agent Development Pipeline — reports current stage, next command, and gate checklist.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.