Extracts human-readable pseudocode from a verified formal artifact (Dafny, Lean, TLA+) while preserving the verified properties as annotations, so the proof-carrying logic can be reimplemented in a production language. Use when porting verified code to an unverified target, when documenting what a formal spec actually does, or when handing a verified algorithm to an implementer.

TLA+-specific instance of model-guided repair — reads a TLC error trace, identifies the enabling condition that should have been false, strengthens the corresponding action, and maps the fix to source code. Use when TLC reports an invariant violation or deadlock and you have the code-to-TLA+ mapping from extraction.

Dispatch skill — routes a formal specification request to the right concrete generator based on what's being specified and what needs to be proven. Use when the user asks to formally specify something without naming a target formalism, or when unsure which verification tool fits the problem.

Converts a model checker counterexample trace into an executable test case in the source language, so the bug found in the model is reproducible (and regression-guarded) in the real code. Use when TLC/NuSMV/Spin finds a violation and you want a failing test before writing the fix.

Generates test oracles — the "expected output" part of a test — by choosing among reference implementations, invariants, inverse functions, or differential comparison when the correct answer isn't obvious. Use when the hard part of testing is knowing what the right answer is, not generating inputs.

Generates domain-specific mutation operators beyond the standard arithmetic/relational set — mutations tailored to your codebase's idioms, APIs, and bug history that standard tools don't try. Use when generic mutation testing plateaus, when your domain has specific failure modes, or when mining bug history reveals patterns standard operators miss.

Generates tests that mock external dependencies — HTTP, databases, filesystems, clocks — isolating the unit under test while still exercising realistic interactions. Use when the code has side effects you can't run in a test, when external services are slow or unavailable, or when testing error paths that are hard to trigger for real.

Translates natural-language requirements into formal constraints — logical predicates, schemas, or property-based test generators — that a machine can check. Use when turning a spec into validation code, when writing property tests, or as the bridge between requirements and formal verification.

Recognizes structural situations that match known design patterns and recommends whether to apply them — or explains why the pattern doesn't fit. Use when the user has a structural problem and is considering a pattern, when reviewing a design that uses a pattern questionably, or when the user asks which pattern fits their situation.

Analyze and optimize React component performance issues (slow renders, re-render thrash, laggy lists, expensive computations). Use when asked to profile or improve a React component, reduce re-renders, or speed up UI updates in React apps.

Look up VoltAgent documentation embedded in node_modules/@voltagent/core/docs for version-matched docs. Use for API signatures, guides, and examples.

Manage Azure DevOps projects, work items, repos, PRs, pipelines, wikis, test plans, security alerts, variable groups, environments/approvals, branch policies, and attachments. Use when user asks to: manage sprints, create/update work items, list repos, create PRs, run pipelines, search code, manage wiki pages, check security alerts, manage variable groups, approve deployments, or configure branch policies. Covers 13 domains with 99 tools via REST API.

Analyze recent code changes via git history and extract software engineering lessons. Use when the user asks 'what is the lesson here?', 'what can I learn from this?', 'engineering takeaway', 'what did I just learn?', 'reflect on this code', or wants to extract principles from recent work.

Review real software repositories for likely security issues using the local OWASP Top 10:2025 category set, official OWASP-mapped CWE lists, and canonical MITRE CWE records. Use when auditing source code, configuration, IaC, pipelines, dependencies, auth flows, crypto, logging, or error handling, and when the goal is evidence-based findings mapped to both CWE and OWASP 2025 with confidence levels and coverage gaps.

This skill should be used when the user says "use cases teams", "arn use cases teams", "team use cases", "debate use cases", "collaborative use cases", "use cases with debate", "team-based use case review", "use case debate", "review use cases as a team", or wants to create structured use case documents through expert debate where product strategist and UX specialist review and discuss each other's findings before revising, producing a use-cases/ directory with individual Cockburn fully-dressed use case files and a README index.

This skill should be used when the user says "discover", "product discovery", "arn discover", "help me define this product", "what should I build", "product concept", "define the product", "let's figure out what to build", "vision for this project", "shape this idea", "new project idea", "brainstorm this product", "starting from scratch", or wants to explore and structure a greenfield product idea through guided conversation. Produces a product-concept.md document capturing the product vision, core experience, target users, trust model, platforms, and scope boundaries.

This skill should be used when the user says "manage secrets", "arn infra secrets", "infra secrets", "secrets management", "set up secrets", "configure secrets", "audit secrets", "secrets audit", "rotate secrets", "secret storage", "vault setup", "key management", "credential management", "secrets scan", "check for exposed secrets", "secrets provider", "arn-infra-secrets", "set up secret manager", "configure secret injection", "environment variables", "env vars", "secure env vars", or wants to set up, configure, audit, or manage secrets and credential storage for their infrastructure deployment.

This skill should be used when the user says "save infra plan", "save infrastructure plan", "structure infra plan", "create infra project", "finalize infra plan", "arn infra save plan", "infra save plan", "save change plan", "structure infrastructure plan", "finalize infrastructure plan", "arn-infra-save-plan", or wants to convert a PLAN_PREVIEW_INFRA_*.md into a structured project directory with infrastructure-specific templates, report templates, and progress tracking.

This skill should be used when the user says "infra pipeline", "arn infra pipeline", "create CI/CD pipeline", "set up deployment pipeline", "generate pipeline", "infra CI/CD", "deployment pipeline", "setup cicd", "generate github actions", "generate gitlab ci", "generate bitbucket pipeline", "infrastructure pipeline", "pipeline setup", "create deployment workflow", "cicd for infrastructure", "infra deployment pipeline", "set up infrastructure CI/CD", "arn-infra-pipeline", or wants to generate infrastructure-specific CI/CD pipelines with SOC 2 alignment, OIDC authentication, and environment-aware deployment stages.

This skill should be used when the user says "cleanup", "infra cleanup", "arn infra cleanup", "clean up resources", "destroy expired resources", "check ttl", "check expired", "ttl cleanup", "remove old deployments", "destroy dev environment", "tear down", "teardown infra", "destroy resources", "cleanup ephemeral", "check for expired resources", "clean up infra", "resource cleanup", "destroy old resources", "prune resources", "delete expired deployments", "decommission", or wants to check for and destroy expired ephemeral infrastructure resources. This skill also supports periodic monitoring via `/loop 6h /arn-infra-cleanup` for session-duration TTL enforcement.