code-review
Review code written by Claude Code or humans across multiple languages. Use when asked to review, audit, critique, or analyze code quality. Supports R, Python,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-01 00:15
Testing & quality
13,005 results
propose-tests
Proposes missing test coverage for branch changes without writing tests.
code-review
Automated code review against project conventions (CLAUDE.md) and best practices
code-review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding…
write-testing
Implement a testing task — tests are the deliverable: behavior through the public surface, one reason to fail per test, each proven by flipping the assertion.…
code-review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding…
grilling
Grill the user relentlessly about a goal, plan, or decision. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
ico-your-internals
Runs Bob's Big Brain Compiler against an existing Markdown corpus, asks a versioned question bank, verifies citations against bounded source files, and renders…
deer_flow
Exercise an offline prototype that returns synthetic research findings, code stubs, and packaged artifact dictionaries. Use when testing a Deer Flow-shaped…
knowledge_graph
Generate synthetic graph counts, ranked artificial entities, and relationship paths from input strings. Use when testing the Knowledge Graph response contract,…
opinion_analyst
Score supplied text with deterministic keyword heuristics for sentiment, stance, and bias. Use when testing explainable offline classification behavior, not…
sandbox
Validate snippets with local keyword rules and return simulated execution output without running code. Use when testing the Sandbox response contract safely.…
stock_analyst
Generate deterministic synthetic fundamentals, indicators, and news sentiment from a ticker string. Use when testing the Stock Analyst response contract, never…
swarm_predict
Generate synthetic per-model values and exercise numeric or categorical consensus aggregation. Use when testing the Swarm Prediction contract, not when…
algolia-ci-integration
Build and review a bounded CI gate for Algolia index configuration and disposable-index smoke tests. Use when search changes need pull-request evidence without…
assemblyai-ci-integration
Build AssemblyAI CI with offline REST, Streaming v3, webhook, gateway, secret, and lifecycle tests plus a tightly gated live lane. Use when adding automated…
assemblyai-common-errors
Analyze and triage AssemblyAI REST, transcript, Streaming v3, webhook, and LLM Gateway failures without leaking customer content. Use when an integration…
assemblyai-debug-bundle
Produce a redacted AssemblyAI diagnostic bundle for support and incident triage. Use when evidence is needed without exposing keys, URLs, audio, transcripts,…
assemblyai-hello-world
Run a bounded AssemblyAI pre-recorded smoke test with explicit model fallback and safe output. Use when proving a new integration. Trigger with "AssemblyAI…
attio-debug-bundle
Assemble a minimal redacted Attio diagnostic bundle with request fingerprints, schema context, retry evidence, and environment metadata. Use when escalating an…
audit-tests
Diagnostic-only test suite auditor. Classifies repo type, maps against 7-layer testing taxonomy (git hooks → static → unit → integration → system → E2E →…
bamboohr-debug-bundle
Assemble a PII-minimized BambooHR diagnostic receipt using request IDs, statuses, timing, version facts, and redacted configuration. Use when escalating an API…
clari-ci-integration
Validate a Clari integration in CI with offline OpenAPI-derived contracts, synthetic job lifecycles, schema drift checks, and secret scanning. Use when adding…