writing-acceptance-tests
Use when adding or changing GitHub CLI acceptance tests, txtar scripts, testdata groups, repository fixtures, or acceptance harness behavior.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-23 00:13
Testing & quality
12,544 results
debug-plan
Create a systematic debugging plan for a bug report. Use when the user asks how to investigate a failure, regression, or unexpected behavior.
playwright-interactive
Persistent browser and Electron interaction through `js_repl` for fast iterative UI debugging.
roam
Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture…
tdd
Test-first build at agreed public seams, one red-green slice at a time. Process skill. Not repro-first hard-bug work without a seam, a throwaway spike, or…
code-quality
Use when the user asks to review code, lint files, fix linting errors, audit a project, run static analysis, check types, inspect complexity, find circular…
openscad-collision-detection
Detects and visualizes geometric intersections in OpenSCAD models using built-in techniques (intersection(), debug modifiers), BOSL2 utilities (debug_this,…
parallel-code-review
This skill should be used when performing comprehensive code reviews using multiple specialized review agents in parallel. It provides patterns for concurrent…
run-evals
DEPRECATED legacy automation runner. Load only when a user explicitly asks to run an EXISTING evals/flows/*.flow file. New coverage uses run-tests.
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 standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to \"review since X\".
evaluating-code-models
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding…
hand-compute
Hand-computes a system's execution with explicit state at each step. Use when debugging races, state machines, async bugs, regressions; stress-testing a fix;…
generate-snapshot-tests
Generate snapshot test files for Sentry frontend React components. Use when asked to "generate snapshot tests", "add snapshot tests", "create visual…
helpmetest-self-heal
Autonomous test maintenance agent. Monitors test failures and fixes them automatically. Always use this when tests start failing after a UI or code change —…
airwallex-webhooks
Receive and verify Airwallex webhooks. Use when setting up Airwallex webhook handlers, debugging x-signature / x-timestamp signature verification, or handling…
clio-webhooks
Receive and verify Clio (Clio Manage) webhooks. Use when setting up Clio webhook handlers, debugging X-Hook-Signature verification, completing the…
pylon-webhooks
Receive and verify Pylon webhooks. Use when setting up Pylon webhook handlers, debugging Pylon signature verification (Pylon-Webhook-Signature, hs256=…
treezor-webhooks
Receive and verify Treezor webhooks. Use when setting up Treezor webhook handlers, debugging signature verification, or handling BaaS banking events like…
zerohash-webhooks
Receive and verify Zero Hash webhooks. Use when setting up Zero Hash webhook handlers, debugging x-zh-hook-signature verification, or handling crypto…
unit-tests
Generates well-structured unit tests using Vitest with the "given/should" prose format. Use when writing tests for new code, adding coverage to existing code,…
debug
Use when diagnosing a Python traceback, failing test, intermittent failure, integration defect, or other unexpected runtime behavior.
find-cause
Investigate why something happens — confirm the question and success criteria with you, then trace the root cause with an evidence chain.
forensic-review
Use when SAM Stage 5 Execution has completed and task results need independent verification against acceptance criteria. Dispatches a separate reviewer agent…
check-traceability
Run and interpret the guardrails traceability checker - orphaned requirements, unmitigated hazards, unimplemented controls, untraced design, dangling…