Testing & QA
3,371 results
- Add Ynd CommandeyelockAdd a new command to the ynd developer CLI end to end — dispatch, flag parsing, output formats, tests and docs. Use when adding a ynd subcommand, the sibling of add-vendor-adapter for the other half of the product.
- Agent CaffeinemertbuildsKeep this Mac awake while long work runs, with the Agent Caffeine command line tool. Use before any command or job that can run longer than a few minutes with nobody at the keyboard (builds, test suites, renders, training runs, backups, large downloads, migrations, deploys, long scripts, background servers you must wait for), and when the user says "keep my Mac awake", "do not let it sleep", "I…
- Agent Routinggaurav8936Choose the agent and model for a piece of work by its kind (research, design, code, review, test, docs, chore), the remaining capacity of each seat, and the rule that a reviewer is never the author. Holds the routing.json and roles.json One Roof reads.
- Ai Human Handoff ContractalivirgoDefine and test AI→human handoff as a versioned state machine with multi-signal triggers, review packets, approval binding, and no silent consent. Use for escalations, approvals, and irreversible agent actions.
- Ai Review Of AudiogothicpixieUsing multimodal LLMs (Gemini, GPT-4o-audio and similar) as a second pair of ears on a mix or radio cut: chunking and proxies, the review brief and JSON schema, timestamped notes by category and severity, blind A/B tests with position-bias controls (run both orders, count only order-consistent wins), rating tables for restoration variants, hidden-vocal checks on generated underscores, and…
- Ambience And Sound For StillsgothicpixieAmbience beds, gap fill and spot effects for narrated documentaries, especially films built from photographs and silent archive: bed levels and coverage (never dead air), the gap lift, the layer hierarchy (bed / texture / spot / designed transition), density and timing rules for spot effects, no-sound classes (portraits, details, weak pictures), worldizing and era-matching so generated effects…
- Amg Check Storage AccountMicrosoft AzureFleet-wide Azure Storage Account health check — pulse check for availability, latency, transactions, and error rates across all accounts, then deep-dives into the top 7 most interesting accounts with metrics (E2E latency, server latency, capacity, ingress/egress) and resource logs. Tracks known issues across sessions via persistent report.
- Architecture TestsMalcolmMcNeelyTurn the rules in docs/agents/rules/ into architecture tests the team owns, with a common tool for the language where one fits and a starter test in the team's own language where none does, then wire each test into the Suite and the placement checks. Use when the user wants the rules enforced, after setup, or again when the repo gains a language or a rule.
- Ask For Alternative ViewpointsalivirgoCompare opposing viewpoints and stress-test the assumptions behind an argument or recommendation.
- Bigdata Post Ipo Day1Bigdata.comWrite a first-trading-day post-IPO reaction note for a newly listed company using Bigdata.com data plus web market data. Anchors the deal (offer price vs range, shares, greenshoe, implied market cap), reconstructs day 1 (open, intraday range, close, volume, first-day return), reads demand and float mechanics including stabilization, resets valuation against peers at the close, notes the…
- Bugfix WorkflowDimkoxUse for defects, regressions, exceptions, and hotfixes. Requires reproduction, root-cause evidence, a failing regression test, minimal repair, and verification.
- Build Review Loopkl-autonomousRun a project with two Claude Code sessions that check each other. A builder builds one step of the plan at a time, with tests and evidence; an independent reviewer checks the exact commit in its own copy, re-runs everything, and answers PASS, FIX or STOP against a short list of what blocks. An optional tester makes adversarial passes.
- Build Web Servicerhawk117Leads the design of a Python HTTP service from a requirements interview to one vertical-slice handoff packet: classifies the service, brings in the contract, persistence and test design skills, and settles identity, deferred work, rate limits, caching and deployment lifecycle. The primary recipe is FastAPI, Pydantic v2 and async SQLAlchemy. Writes no project files.
- Characterization Testingspacholski1225Create tests that describe what legacy code actually does (not what it should do) as safety net before refactoring
- CI CD HelperpaleoterraGenerate CI/CD configurations and automation scripts for building, testing, and deploying
- Code WritingParabolic-TechnologiesStrict implementation. Executes approved tasks under accepted ADRs, writes code/tests, verifies requirements and decisions, writes implementation-report.md, and updates the manifest. Auto-select only in a Banzai-adopted repository (root PROJECT_MANIFEST.md or .banzai/) or by name.
- CodesysalivirgoDevelop CODESYS Structured Text and Python ScriptEngine workflows; troubleshoot fieldbus and OPC UA integration in a test environment.
- Cold Call OpenermbfinottiWrites the opening 5-30 seconds of a live outbound cold call - a tailored opener for a named persona and pain point, with 2-3 testable variants, delivery notes, and a measurement plan. Covers B2B and B2C phone outreach, including do-not-call scrubbing.
- Cold Email DeliverabilitymbfinottiReviews a cold email draft and its sending setup for deliverability - SPF/DKIM/DMARC alignment, sender reputation and complaint risk, body mechanics (length, links, images, tracking pixels, HTML vs plain text, opt-out), and legal compliance by region. Covers B2B cold outbound and B2C bulk/lifecycle mail.
- CommiteyelockCreate well-formatted git commits with conventional commit messages. Follow this format: `type(scope): description` Types: feat, fix, refactor, test, docs, chore
- Create Prfandhe-aiConventional Commits 形式で GitHub PR を作成する。OWASP Top 10 のセキュリティチェック必須で、問題があれば PR 作成を中止。Summary/Test plan/Design を含む body を生成。「PR 作って」「プルリク」「`gh pr create`」などで使用。別リポジトリ (upstream) への貢献は contribute-skill。
- Create Skillrhawk117Interactive Claude Code skill creator, scenario-first. Use it to create, write, scaffold, improve, test or evaluate a skill (SKILL.md plus optional scripts, references and assets). It asks where the skill ships (personal, project, plugin), sets invocation and tool pre-approvals by checkbox, takes a plain description of what the skill does and what problem it solves, proposes a name and use-case…
- Data Engineeringrhawk117Makes data code correct first and cheap second: pins down the output, estimates sizes before running, checks schema and join contracts, chooses the engine, reads the query plan before tuning, and has results returned or published as artifacts instead of printed. Covers synthetic data and tests for data code. Hands back the changed code with the measurement behind every speed or memory claim.
- Data SciencePetriLahdelmaExpert data science guidance for analytics, data processing, visualization, statistical analysis, machine learning, and AI integration. Use when analyzing data, building ML models, creating visualizations, processing datasets, conducting A/B tests, optimizing metrics, or integrating AI features. Includes Python (pandas, scikit-learn), data pipelines, and model deployment.