debug-replay
Turns bug reports into reproducible steps by finding error sessions in Amplitude Session Replay, extracting interaction timelines, and identifying the common…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-27 00:15
Testing & quality
12,743 results
effect-arbitrary
This skill should be used when the user asks to "generate arbitrary values", "generate sample data from a schema", "use Effect Arbitrary",…
ado-sync-judge
Historical publisher Agent-purpose summary: Review Azure DevOps synchronization correctness,conflict handling and lifecycle management. The historical rules prioritize external tracker status and distinguish strict increment completion from flexible specification states. Old Skill original and install mapping are unverified.
pr-test-analyzer
PR test coverage analyzer. Use when reviewing PR tests, finding missing tests, or checking edge case coverage.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing…
flutter-mcp-e2e-harness
Use this skill when writing or running repeatable E2E scenarios for Flutter apps as checked-in Dart with the `flutter_mcp_harness` package (`packages/harness`)…
repo-quality-system-lifecycle
Establish or audit a structural quality contract for any agent-operated engineering repository: app, library, CLI/tool, plugin, harness, or meta repo. Use when…
review-ready-code
Turn a finished, tested implementation into a human-reviewable Git commit stack without changing the final code. Use when the user says a completed change is…
external-gitcode-ascend-triton-operator-precision-eval
Triton operator precision evaluation. Compare with the PyTorch reference implementation, automatically calculate error metrics, and generate a standardized precision report. Keywords: precision testing, precision evaluation, precision report, accuracy verification.
external-mindstudio-gitcode-code-reviewer
Used to review GitCode PRs and generate in-depth review conclusions or post line-by-line comments by combining PR metadata, the diff, and the context of the entire code repository. Use when the user wants to review a GitCode PR, inspect a GitCode PR link, analyze change risks, or post review comments to a GitCode PR. Typical triggers include "review this…
verify-fix-loop
Run the "verify → fix" iterative loop via local Playwright MCP (headed mode): each round verifies web page behavior using snapshot + console + network as evidence; if FAIL, fix the code and retry. After 2 rounds (from Round 3 onward), force a HITL ask each round on whether to continue, to avoid blind iteration. Suitable for…
debug
Diagnose and fix bugs, failures, and performance regressions. Read this skill BEFORE touching any code whenever the user reports a bug, broken behavior, a…
pyats-dynamic-test
Generate and execute deterministic pyATS aetest validation scripts - interface state, OSPF neighbors, BGP paths, ping matrices, and custom compliance tests.…
codex-code-review
Use Codex CLI for AI-powered code review. Triggers on "codex review", "review with codex", "code review pr", or when user wants AI code review before PR/merge.
test-desktop-app
Use when testing the Hubble Electron desktop app, especially when inspecting, clicking, screenshotting, or verifying a real note edit in the running app.
bmad-os-findings-triage
Orchestrate HITL triage of review findings using parallel agents. Use when the user says 'triage these findings' or 'run findings triage' or has a batch of…
clojure-repl
Interact with running Clojure REPLs via nREPL. Evaluate Clojure code, query namespaces, test functions, and debug live Clojure systems. Use when working with…
testing-guidelines
Language-agnostic test-admission rules for project-owned behavior and meaningful sans-I/O evidence. Use when adding, retaining, removing, or reviewing tests.
browser-use
When you need to interact with web pages using the user's logged-in browser → control Chrome via @playwright/cli daemon, reusing cookies/session with…
eval-systematic-optimization
Run foundation-suite baseline, cluster failures, and optimize pass@1 systematically.
pytest-django
pytest-django integration testing specialist. Covers all fixtures (db, transactional_db, client, rf, settings, mailoutbox,…
ads-copywriter
Multi-platform ad copy generation for Google Ads, Meta/Facebook, TikTok, LinkedIn with A/B testing variants
psi-classification
Personal services income determination under Division 84-87 ITAA 1997 — PSI rules, PSB tests, and deduction restrictions
clerk-monorepo
Work effectively in the clerk/javascript SDK monorepo. Use when setting up the repo, building / testing / running a package, deciding which of the @clerk/*…