calculate-coverage
Calculate code coverage for .NET projects using local coverage scripts. Use when user asks to calculate coverage, check coverage, coverage metrics, test coverage. For NEW CODE coverage (what SonarCloud Quality Gate checks), use when user says "new code coverage", "coverage on new code", "changed code coverage", "feature branch coverage". For OVERALL coverage, use when user says "overall coverage", "total coverage", "full coverage", "complete coverage".
debug-mode
Run an iterative, hypothesis-driven “debug mode” loop to diagnose and fix a bug using targeted instrumentation and log capture. Use when the user wants an interactive debug loop, when you need to quickly narrow a failure via added debug statements, or when you need a lightweight way to centralize logs from a repro run (via `agent-skills debug` server + SSE UI).
website-audit
A comprehensive auditing suite for the JupitLunar website. It performs deep scans for broken links, console errors, accessibility issues, SEO compliance, and feature verification. Use this when the user asks to "audit the website", "check for broken links", "verify features", or "do a health check".
debugreact
Debug React issues systematically. Use when encountering component errors like "Cannot read property of undefined", infinite re-render loops with "Too many re-renders", stale closures in hooks, key prop warnings, memory leaks with useEffect, hydration mismatches in SSR/SSG applications, hook rule violations, missing dependency warnings, or performance bottlenecks. Covers functional components, hooks, and modern React 18/19 patterns including Server Components and concurrent features.
fpf-skillverification-verify-behavior
Verifies that an execution trace complies with the FPF Behavioral Specification.
scope-capture
REPL debugging tool for capturing and inspecting local scope at runtime. Use when debugging functions, investigating test failures, understanding intermediate values, or when you need to recreate the runtime context of code without manually fabricating values.
root-cause-tracing
Systematically trace bugs and issues to their root cause using debugging techniques and analysis methods
marimo-inspect
This skill should be used when inspecting marimo notebook execution results. Triggers include: - Checking notebook output - Viewing execution results - Reading __marimo__ HTML snapshots - Debugging notebook errors - Verifying cell outputs
p5-code-review
Reviews p5.js tower defense game code for architecture patterns, manager responsibilities, performance issues, and code quality. Use when reviewing enemies, towers, managers, renderers, or asking for code review.
global-commenting
Write self-documenting code that explains itself through clear structure and naming, adding only minimal, evergreen comments for complex logic sections. Use this skill when deciding whether code needs comments, removing outdated temporal comments about changes/fixes, or writing concise explanations. Applies to all code files when balancing code clarity with necessary documentation, ensuring comments remain relevant far into the future rather than describing temporary states.
bug-interview
Analyze and review bug reports to capture repro, evidence, and next diagnostic step. Use when a bug report lacks clear reproduction.
instrumentation-planning
Plan what to measure in web applications. Use when starting observability or prioritizing instrumentation.
debugging-mastery
Systematic debugging methodologies for finding and resolving complex bugs. Use PROACTIVELY when encountering difficult bugs, mysterious failures, or issues that resist simple fixes. MUST BE USED when debugging spans multiple files, involves race conditions, or has eluded initial investigation attempts.
cljr-performance
Optimize Cljr compiler and runtime performance. Use when optimizing emitter output, runtime collections, REPL evaluation, or leveraging .NET 10/C# 14 features. Covers Span<T>, FrozenDictionary, AggressiveInlining, benchmarking, and allocation reduction strategies.
methodical-debugging
Systematic debugging approach using parallel investigation and test-driven validation. Use when debugging issues, when stuck in a loop of trying different fixes, or when facing complex bugs that resist standard debugging approaches.
sr22t-runway-brief
Calculate takeoff and landing performance for Cirrus SR22T at any runway. Input weather (winds, temp, altimeter) and runway data (elevation, heading, length) to get performance calculations, approach speeds, safety margins, and passenger briefing scripts. Use when evaluating runway feasibility, checking hot day performance, or analyzing unfamiliar airports.
lightweight-implementation-analysis-protocol
This skill should be used when fixing bugs, implementing features, debugging issues, or making code changes. Ensures understanding of code flow before implementation by: (1) Tracing execution path with specific file:line references, (2) Creating lightweight text diagrams showing class.method() flows, (3) Verifying understanding with user. Prevents wasted effort from assumptions or guessing. Triggers when users request: bug fixes, feature implementations, refactoring, TDD cycles, debugging, code analysis.
lineage-and-provenance
Track data lineage และ provenance เพื่อเข้าใจ data flow, dependencies และ impact analysis
openwebf-app-webf-go
Run and debug a WebF app specifically in WebF Go (desktop/iOS/Android): load dev URLs, connect via devtools://, collect WEBF_NATIVE_LOG logs, clear WebF Go cache, and handle WebF Go limitations. Use when the user explicitly mentions WebF Go, devtools://, WEBF_NATIVE_LOG, the WebF Go debug button, or WebF Go settings (Clear Cache).
