Testing & QA

Unit tests, integration tests, E2E, QA, validation, and test automation

skills in category: 31,094
pages available: 1,296

Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.

Open in full browser

Browse testing & qa skills

Showing 1,945–1,968 of 31,094 skills

Skill Trigger Confusable Pair TestAUse when a trigger description may be too broad or collide with another skill to create or update a positive, negative, and boundary-case activation test set. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: positive cases route to the skill and confusable negatives do not. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally visible or irreversible writes.testingrustgoVotes: 0GitHub stars: 2
Skill Change To Evaluation Impact MapAUse when a skill update changes a workflow step, guardrail, example, or routing description to create or update a changed-instruction-to-eval-case map. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: every changed obligation has at least one affected scenario and unchanged obligations retain coverage. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally v...testingrustgoVotes: 0GitHub stars: 2
Scheduled Agent Noop Threshold ReviewAUse when a recurring workflow runs even when no actionable change may exist to create or update a decision record with trigger evidence, confidence, and no-op reason. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: the workflow acts only when the agreed evidence threshold is met. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally visible or irreversible...testingrustgoVotes: 0GitHub stars: 2
Same Error Fingerprint Stop Rule EnforcerAUse when two or more loop iterations fail with apparently unchanged feedback to create or update an attempt ledger with normalized failure fingerprints and stop reason. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: a changed hypothesis produces new evidence or repeated failure triggers escalation. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally vis...testingrustgoVotes: 0GitHub stars: 2
Progress Ledger Acceptance Claim Closure CheckAUse when a long task has multiple completed, partial, or blocked steps to create or update a ledger joining acceptance IDs, evidence paths, status, and owner. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: no item is called complete without a current artifact or reproducible observation. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally visible or irr...testingrustgoVotes: 0GitHub stars: 2
Per Iteration Tool Budget Before DispatchAUse when an agent is about to dispatch another tool call in a repeated workflow to create or update a budget record with projected call, time, and external cost. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: the next action fits within the remaining approved budget or stops cleanly. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally visible or irrever...testingrustgoVotes: 0GitHub stars: 2
Evidence Coverage Matrix Gap ClosureAUse when a research brief has multiple criteria but only an unstructured source pile to create or update a criterion-to-source matrix with pass, partial, missing, or contradicted states. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: every material criterion has evidence or a clear unresolved status. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally v...testingrustgoVotes: 0GitHub stars: 2
Evaluation Harness DesignAUse when measuring whether an agent, prompt, tool pipeline, or skill is reliable across repeated cases to define representative tasks, reference outcomes, metrics, graders, calibration checks, regression thresholds, and a reproducible report before tuning. Trigger before release, after model or prompt changes, or when subjective impressions are driving quality decisions.testingrustgoVotes: 0GitHub stars: 2
Agent Loop Budgeting And ObservabilityAUse when an agent loop can consume variable time, tool calls, money, tokens, or external quota to set explicit limits and progress signals, monitor them per iteration, detect churn or plateau, and stop or ask before crossing budgets. Trigger for unattended, recurring, multi-agent, or open-ended tasks where cost or runaway behavior matters.testingapiVotes: 0GitHub stars: 2
Agent Commit Message To Diff Consistency CheckAUse when a tool-using agent prepares a commit message from a diff to create or update a message-to-file mapping with any unsupported claims removed. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: every message claim has a corresponding changed path or verified behavior. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally visible or irreversible writes.testingrustgoVotes: 0GitHub stars: 2
Task Decomposition And PlanningAUse when a goal is too large or ambiguous to complete safely in one pass and must be broken into a sequence of verifiable tasks to identify dependencies, risks, owners, and acceptance checks; prioritize a thin path to evidence and keep scope controlled. Trigger at project starts, complex changes, or when parallel work needs a clear plan.testinggorailsVotes: 0GitHub stars: 2
State And HandoffAUse when work spans sessions, runs, agents, or context windows and progress must survive handoffs to record the objective, current state, decisions, evidence, unresolved risks, next action, and stopping rule in a durable artifact; verify freshness before resuming. Trigger for asynchronous, unattended, delegated, or long-running agent workflows.testingVotes: 0GitHub stars: 2
Partial Completion State ReconciliationAUse when a multi-part task cannot finish every component in one run to create or update a status matrix with dependencies and evidence per subgoal. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: the final status names completed, blocked, and unverified parts without contradiction. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally visible or irreversib...testingrustgoVotes: 0GitHub stars: 2
Multi Session Project BlueprintingAUse when a project is too large for one focused implementation pass and must span multiple pull requests, sessions, or collaborating agents to create a dependency-aware plan with self-contained work packets, acceptance evidence, ownership boundaries, and change-control rules. Trigger for migrations, broad refactors, multi-stage features, or context-loss-sensitive work; skip for small tasks.testingrustgoVotes: 0GitHub stars: 2
Multi Agent CoordinationAUse when two or more agents, subagents, or workers must contribute to a shared objective to define bounded roles, artifact ownership, interfaces, isolated work areas, message cadence, integration checks, and a responsible coordinator. Trigger for parallel research or implementation; do not parallelize tightly coupled edits without explicit ownership and merge rules.testinggoVotes: 0GitHub stars: 2
Loop Finalization Side Effect InventoryAUse when a multi-tool workflow is nearing completion to create or update a final side-effect inventory with target, status, and verification result. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: each effect is either verified, explicitly pending approval, or reported as not performed. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally visible or irrev...testingrustgoVotes: 0GitHub stars: 2
Failure Recovery And ReplanningAUse when a tool call, test, or action fails, returns ambiguous output, or does not improve the artifact to diagnose the failure, preserve known-good state, change the next attempt, bound retries, and escalate when evidence remains insufficient. Trigger for recovery, replanning, partial completion, and repeated errors in autonomous or multi-turn workflows.testinggorailsVotes: 0GitHub stars: 2
Agentic Code Change WorkflowAUse when an agent is asked to modify code, add a feature, fix a bug, or change configuration in a repository to establish scope, inspect project conventions, plan a small change, implement with relevant tests, review the diff, and verify before reporting. Trigger for multi-file edits, behavior changes, or production-impacting fixes; gate commits and deployments separately.testingapidocumentationVotes: 0GitHub stars: 2
Agent Architecture AuditAUse when an agent or LLM application behaves inconsistently, misses tool calls, regresses after wrapper changes, contaminates memory, or fails between model output and UI/API delivery to trace inputs through context, planning, tools, state, recovery, and rendering; isolate the failing stage with evidence. Trigger before broad prompt rewrites or blind retries.testingrustgoVotes: 0GitHub stars: 2
Breakdown TestATest Planning and Quality Assurance prompt that generates comprehensive test strategies, task breakdowns, and quality validation plans for GitHub projectstestinggotestingVotes: 0GitHub stars: 10
Breakdown PlanAIssue Planning and Automation prompt that generates comprehensive project plans with Epic > Feature > Story/Enabler > Test hierarchy, dependencies, priorities, and automated trackingtestinggotestingVotes: 0GitHub stars: 10
Ci Cd And AutomationAUse when setting up a project's CI pipeline, adding or changing automated checks, configuring deployment pipelines, or debugging CI failures. Covers quality gates, pipeline stages, and what to verify automatically on every change.testingtypescriptgoVotes: 0GitHub stars: 10
Bmad Qa Generate E2e TestsAGenerate end to end automated tests for existing features. Use when the user says "create qa automated tests for [feature]"testingpythongoVotes: 0GitHub stars: 10
Systematic DebuggingARoot-cause-first debugging discipline — build a red-capable feedback loop, minimise the repro, rank falsifiable hypotheses, fix at the source. Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.testinggobashVotes: 0GitHub stars: 6