excellence-review
Mandatory excellence gates for Grok+ACOS. verification-loop, santa-method, gstack-qa, plan-reviews, repo-mastery, cso, rules-distill. Never ship without…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-29 00:09
Testing & quality
12,863 results
code-review
Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before…
svelte-testing
Fix and create Svelte 5 tests with vitest-browser-svelte and Playwright. Use when fixing broken tests, debugging failures, writing unit/SSR/e2e tests, or…
php-testing
Use when writing/configuring tests on a non-Laravel PHP project — PHPUnit vs Pest. Do NOT use for Laravel test helpers or quality tooling (php-quality-tooling).
comprehensive-code-review
Use when performing code review on a PR, reviewing code changes before merge, or when a GitHub code review is requested or received - orchestrates parallel…
analyze-ablation
Analyze guideline ablation experiment results to determine which guideline sections are essential, marginal, or dispensable. Use when the user asks to analyze…
create-pr
Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review…
debugging
Systematic debugging framework with root cause investigation, tracing, defense-in-depth validation, and verification. Use when: 'bug', 'test failure',…
problem-solving
Problem-solving frameworks for breakthrough thinking - collision zones, simplification cascades, meta-patterns, scale testing, inversion, and dispatch guide.…
reviewing-code
Code review checkpoint using codex review CLI. Returns structured result with pass/fail status and issues. Use when: 'code review', 'review changes', 'codex…
bug-diagnosis
Find the root cause of a code or system failure: an error, crash, wrong output, flaky test, hang, or performance regression, and verify the fix against the…
evaluation-design
Design or build an evaluation of an LLM system or model, or change what one measures: failure modes, cases and labels, code checks and validated judges,…
praxis-direction
Turn an organization's research agenda into one resourced bet (outcome, measure, intervention, cheapest test, compute ladder, kill condition), run the…
unit-test
Create comprehensive unit tests using Bun's test runner. Use when the user asks to create or fix unit tests or create test files.
fuzzing-memory-unsafe-expert
Use this skill to fuzz open source C/C++ software projects.
nightly-eval-investigation
Downloads and analyzes the latest three distinct nightly evaluation runs (Claude Code, Codex CLI, and Jetski CLI) from the GCS remote dashboard to identify and…
bio-pathway-kegg-pathways
Tests gene lists, ranked vectors, and fold-change vectors against KEGG pathways and modules with clusterProfiler enrichKEGG/enrichMKEGG (ORA), gseKEGG (GSEA),…
bio-pathway-wikipathways
Tests a gene list (ORA, enrichWP) or a ranked gene vector (GSEA, gseWP) against the WikiPathways community-curated pathway collection with clusterProfiler and…
bio-rna-quantification-count-matrix-qc
Quality control and exploration of RNA-seq count matrices before differential expression. Use when checking library sizes and composition, choosing VST vs rlog…
bio-single-cell-cell-communication
Infers ligand-receptor cell-cell communication from scRNA-seq with a consensus-first workflow (LIANA), plus CellPhoneDB specificity tests, CellChat pathway…
k6-load-test
Use this skill when the user says "write a k6 script", "generate a k6 load test", or "create performance tests with k6." Handles load, performance, stress,…
code-quality-analysis
Multi-mode code quality analysis covering security reviews (OWASP Top 10), clarity refactoring (readability rules), synthesis analysis (cross-file issues), and…
smart-debugging
AI-powered intelligent debugging with stack trace analysis, error pattern recognition, and automated fix suggestions. Use when debugging complex errors,…
tdd-orchestration
Master TDD orchestration with multi-agent coordination, strict red-green-refactor enforcement, a Layer-0 domain-modeling gate (DDD) that blocks Red until…