Loading...
Loading...
Found 56 Skills
Update the graft (feature flag) inventory when flags are added or removed. Use when adding new grafts via migrations, after CI flags inventory mismatches, or periodically to ensure docs match production D1.
Use when configuring Dialyzer for Erlang/Elixir type checking and static analysis.
Creates load and performance tests with k6, Artillery, or autocannon to validate system behavior under stress. Use when users request "load testing", "performance testing", "stress testing", "k6 setup", or "benchmark API".
Build, validate, and deploy LLM-as-Judge evaluators for automated quality assessment of LLM pipeline outputs. Use this skill whenever the user wants to: create an automated evaluator for subjective or nuanced failure modes, write a judge prompt for Pass/Fail assessment, split labeled data for judge development, measure judge alignment (TPR/TNR), estimate true success rates with bias correction, or set up CI evaluation pipelines. Also trigger when the user mentions "judge prompt", "automated eval", "LLM evaluator", "grading prompt", "alignment metrics", "true positive rate", or wants to move from manual trace review to automated evaluation. This skill covers the full lifecycle: prompt design → data splitting → iterative refinement → success rate estimation.
This skill should be used when users encounter cspell unknown word warnings, spelling errors from cspell diagnostics, or CI/linting failures on unrecognized words. Also applies when users ask to add words to the cspell dictionary, suppress or ignore cspell warnings, choose between cspell:words and cspell:ignore directives, or bootstrap cspell config in a new project
Fuzzing skill for automated input-driven bug finding in C/C++. Use when setting up libFuzzer or AFL++ fuzz targets, defining fuzz entry points around parsing or I/O boundaries, integrating fuzzing into CI, managing corpora, or combining fuzzing with sanitizers. Activates on queries about libFuzzer, AFL, afl-fuzz, fuzz targets, corpus management, coverage-guided fuzzing, or OSS-Fuzz integration.
This skill should be used when the user asks to "scan for TODOs", "find placeholders", "clean up stubs", "remove temporary code", "audit for incomplete code", or "erase substitutions from codebase". Scans existing files for placeholder tokens and generates remediation plan.
Configure and operate BiomeJS in JavaScript/TypeScript projects, including installation, `biome.json` setup, formatter/linter/check workflows, VCS integration, and CI usage. Use when users ask to adopt Biome, tune rules/includes, set up monorepo/shared configs, or troubleshoot Biome command behavior.