Results for “agentic-testing”

Writes unit, smoke, and e2e tests for AI agents, covering tools, instructions, routing, citations, and guardrails.

`analysis-agent`/`task-agent`/`review-agent`: use when logic, rules, invariants, branches, edges, or failure paths need isolated tests; skip without a unit-test decision.

`analysis-agent`/`task-agent`/`review-agent`: use for provider-consumer compatibility of APIs, events, schemas, or behavior; skip without independent consumer/version risk.

Expert en tests d'agents IA (tests unitaires, intégration, régression, guardrails, red teaming agents)

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.

Implement iterative evaluation and refinement loops for AI agent outputs, using self-critique, evaluator-optimizer patterns, and rubric-based scoring to improve quality.

Check any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks, scanning for controls and generating a compliance report.

`analysis-agent`/`task-agent`/`review-agent`: use for database, broker, cache, HTTP, framework, process, or transaction seam proof; skip local, portfolio, and release-verdict work.

Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality

Use `analysis-agent` to map acceptance to validation, `task-agent` to add or run bounded tests, and `review-agent` to assess proof coverage. Skip work with no material change or already-fresh complete validation.

Agent profile for design test strategy across unit, integration, contract, E2E, visual, performance, and regression layers. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.

`analysis-agent`/`task-agent`/`review-agent`: use when behavior needs deterministic seams for time, randomness, UUIDs, collaborators, or external I/O; skip when seams are adequate.

`analysis-agent`/`task-agent`/`review-agent`: use for recurrence guards on known defects, incidents, or escaped failures; skip speculative risk without a prior failure mechanism.

Agent validation v4.3.0 — Make agents act effectively by disabling harmful actions, lowering gates, and injecting cross-run learning

Compare coding agents head-to-head on reproducible tasks with pass rate, cost, time, and consistency metrics.

Guides AI agents through engineering workflows with eval-first execution, task decomposition, cost-aware model routing, and review focus for generated code.

Designs identity, authentication, and trust verification systems for autonomous AI agents operating in multi-agent environments. Ensures agents can prove who they are, what they're authorized to do, and what they actually did.

Fundamental patterns for effective agentic behavior. Teaches decomposition, tool orchestration, error recovery, context management, quality self-assessment, and knowing when to stop. Model-agnostic principles that make any agent more effective regardless of domain. Activate on: "how should I structure this agent", "agentic workflow", "agent patterns", "multi-step task", "tool orchestration", "/agentic-patterns", "decompose this", "agent best practices", "chain of actions", "when should the agent stop", "agent loop design". NOT for: creating agent infrastructure (use agent-creator), building DAGs (use windags-architect), specific tool implementation.

Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.

Build persistent multi-agent operating systems on Claude Code with kernel architecture, specialist agents, slash commands, file-based memory, and scheduled automation.

Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases.

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases.

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics

Design reproducible evaluations for AI agents with representative task sets, explicit rubrics, appropriate graders, baselines, regression gates, and failure analysis. Use when defining agent quality, comparing prompts or models, validating a release, measuring tool-use reliability, investigating regressions, or deciding whether an agent is ready for production.

Agent skill for tester - invoke with $agent-tester

Audits a website against the Forter Agentic Readiness Guide by running 25 weighted rubrics, scoring each guideline, and producing a prioritized fix report.

`analysis-agent`/`task-agent`/`review-agent`: use to recommend a risk-to-test evidence portfolio and omissions; skip test implementation, fixed-command, and release-verdict work.

`analysis-agent`/`task-agent`/`review-agent`: use when symptoms, logs, metrics, regressions, or incidents need cause analysis; skip when no diagnosis decision exists.

Compares coding agents head-to-head on reproducible tasks, measuring pass rate, cost, time, and consistency.

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics

Designing red team attack scenarios, threat models, MITRE ATT&CK/OWASP application, Purple Team exercises, and AI/LLM red teaming. Use when adversarial security validation is needed.

Use `analysis-agent` to analyze permissions, secrets, sensitive data, trust boundaries, and injection; `task-agent` to implement controls; and `review-agent` to assess evidence. Skip self-review and no-trust-impact work.

AI/LLM red-team assessment using the OWASP LLM Top 10 (2025) + OWASP AI Testing Guide (AITG v1, Nov 2025) frameworks, plus OWASP MCP Top 10 runtime testing for agentic/MCP targets. Tests prompt injection, jailbreaks, system prompt leakage, sensitive data extraction, excessive agency, improper output handling, model extraction, content bias, evasion, membership inference, MCP token exposure, MCP command injection, and more. Uses four tools in combination: FuzzyAI (single-turn jailbreak fuzzing), PyRIT (multi-turn orchestrated attacks), Garak (probe-based vulnerability scanning), and promptfoo (plugin-based red-team evaluation). Each tool covers different OWASP categories; running them together gives systematic coverage. Includes a conditional MCP reconnaissance phase and a post-access AI infrastructure phase (chained from /post-exploit). Produces: OWASP LLM Top 10 + AITG + MCP coverage matrix, findings per category, architecture diagram of the AI system, PoCs for confirmed exploits. Chains into /gh-export for