jb-test-audit
Audit tests, remove useless or tautological tests, improve test value, or review implementation-coupled tests; also gate newly authored or changed tests for…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-30 00:12
Testing & quality
12,914 results
stub-skill
A fixture skill for tea-skill-runner and tea-evaluate preflight. Use when the stub agent asks for it.
bmad-forge-idea
Test a half-formed idea in a questioning conversation, with different personas probing its weak points, until the user can act on it or drop it with…
fda-qsr-audit-prep
FDA Quality System Regulation (21 CFR 820 / QMSR) audit-prep playbook for medical devices. Use when an FDA inspection is announced, when preparing for the new…
md-review
Pre-publication quality gate for authored Markdown — heading structure, on-disk link resolution, readability, accessibility, terminology. Use when reviewing…
jf-robustness
Use when planning or auditing the robustness, sensitivity, and multiple-testing battery for a The Journal of Finance (JF) manuscript. Decides which checks are…
chicken-scheme
Write, compile, debug, and package CHICKEN Scheme programs. Use this skill whenever the user mentions CHICKEN Scheme, call-cc.org, csc, csi, Scheme eggs,…
testdesiderata
Review test code against TestDesiderata's twelve properties that make tests valuable: isolation, composability, determinism, speed, readability, behavioral…
testing-patterns
Testing patterns for unit, integration, and end-to-end tests. Use when writing tests, setting up test fixtures, or validating RLS enforcement. Routes to…
triage
Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests,…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing…
super-autopilote-issue
Variante autosuficiente de issue-autopilot. Conduce AFK una carpeta de issues locales a done/, ejecutando por cada issue un ciclo completo implementar (con TDD…
walkmethrough
Interactive manual-test walkthrough of the changes on the current branch versus `main` (including uncommitted, staged, and untracked changes). Discovers what…
insight-challenge
Adversarial review of code quality findings. Challenges insights with counter-evidence, verifies claims against source code, and produces structured verdicts.…
odyssey-debug
Long-running debug cycle — archaeology, diagnosis, fix, confirmation, generalization, discovery, and knowledge persistence
odyssey-review-test-fix
Deep review + fix cycle — archaeology, exploration, multi-dimensional review, targeted fix, generalization, discovery, and knowledge persistence
chrome-devtools-mcp
Chrome-specific debugging via the official Chrome DevTools MCP server. Use for live logged-in Chrome sessions, DevTools-selected element inspection,…
skill-evals-optimize
Optimize OpenCode skill-loading eval failures. Use when triaging failed eval cases, applying limited fixes, and re-running targeted evals.
skill-evals-run
Run the OpenCode skill-loading eval suite for this repo. Use when asked to run skill evals, skill-loading evals, or the skill-evals-run command.
quality-scan
Run a scoped, read-only quality scan and report exact-candidate evidence, failures and frozen debt. Use for an ad-hoc gate sweep or release preparation; a…
validate-release-green
Run or inspect the local Release-Green observer for an exact base or combined PR candidate, separating hard failures, advisory drift and incomplete evidence.…
rendering-wpf-architecture
Explains WPF rendering pipeline (Measure/Arrange/Render passes) and hardware acceleration tiers. Use when debugging layout issues, optimizing render…
llm-as-judge
Design and validate LLM-as-judge scoring — pairwise vs pointwise, bias correction, anchor calibration, and the cases where a judge is the wrong tool. Use when…
codeant-review
Run a CodeAnt AI code review on local changes (uncommitted, staged, last commit, or against a branch), present findings, and apply safe minimal fixes for all…