Claude Skills by Intense-Visions

> Identify modules that represent structural risk via co-change and churn analysis.

> Cognitive mode: **advisory-guide**. Inject i18n considerations into brainstorming, planning, and review workflows. Adapt enforcement based on project configuration — gentle prompts when unconfigured, gate-mode validation when enabled.

> Translation lifecycle management. Configure i18n settings, scaffold translation files, extract translatable strings, track coverage, generate pseudo-localization, and retrofit existing projects with internationalization support.

> Internationalization compliance verification. Detect hardcoded strings, missing translations, locale-sensitive formatting, RTL issues, and concatenation anti-patterns across web, mobile, and backend codebases.

> Pre-brainstorm ideation. Generates candidate ideas, critiques each against its strongest objection, and ranks them by `(impact × confidence) ÷ effort`. Writes a single ranked artifact to `docs/ideation/<slug>-YYYY-MM-DD.md`. **Produces ranked ideation, not specs** — brainstorming consumes the output.

> Graph-based impact analysis. Answers: "if I change X, what breaks?"

> Runbook generation, postmortem analysis, and SLO/SLA tracking. Diagnoses incidents by tracing symptoms through services, produces structured postmortems, and maintains error budget accounting.

> Terraform, CloudFormation, and Pulumi analysis. Module structure, state management, drift prevention, and security posture for infrastructure definitions.

> Scaffold a new harness-compliant project, migrate an existing project to the next adoption level, or bootstrap an existing project that just got the harness marketplace plugin installed (no `harness setup`). Ground the project in a strategic anchor (`STRATEGY.md`) first, then assess current state, scaffold or migrate, configure, validate, instrument (baselines / telemetry / Tier-0 integrations), and finalize.

> Service boundary testing, API contract verification, and consumer-driven contract validation. Ensures services communicate correctly without requiring full end-to-end infrastructure.

> Verify system wiring, materialize knowledge artifacts, and update project metadata. Integration is a gate, not a discovery phase -- it confirms that planned integration tasks completed.

> Unified integrity gate — single invocation chains mechanical verification with AI-powered code review and produces a consolidated pass/fail report.

> Auto-generate always-current knowledge maps from graph topology. Never stale because it's computed, not authored.

> 4-phase knowledge extraction, reconciliation, drift detection, and remediation with convergence loop. Keeps the business knowledge graph current and identifies coverage gaps.

> Stress testing, capacity planning, and performance benchmarking with k6, Artillery, and Gatling. Detects existing load test infrastructure, designs test scenarios for critical paths, executes tests, and analyzes results against defined thresholds.

> One on-demand entry point for project maintenance. Runs the checks that are actually overdue, triages what needs attention, and asks you — in plain text — which to fix. A thin wrapper over `harness maintenance run`; it owns no state of its own.

> Advise on ML pipeline management, experiment tracking hygiene, model serving patterns, and prompt evaluation frameworks. Audits reproducibility, model versioning, and deployment readiness across MLflow, Weights and Biases, SageMaker, and Vertex AI.

> Advise on mobile platform lifecycle management, permission handling, deep linking, push notifications, and app store submission compliance. Covers iOS, Android, React Native, and Flutter with platform-specific best practices.

> Test quality validation through mutation testing. Introduces deliberate code mutations to verify that the test suite catches real bugs, exposing weak assertions, missing edge cases, and dead test code.

> Structured logging, metrics, distributed tracing, and alerting strategy. The three pillars of observability, assessed and designed for production readiness.

> Conduct a structured departure debrief for an engineer leaving a harness-managed project. Capture the in-flight context, decisions, and social knowledge they hold in their head, hand off open work and ownership, run an access/knowledge/secret checklist, and verify nothing load-bearing leaves with the person. The symmetric counterpart to harness-onboarding: onboarding gets knowledge _in_, offboarding gets knowledge _out_ before it is lost.

> Navigate an existing harness-managed project and generate a structured orientation for new team members. Map the codebase, understand constraints, identify the adoption level, and produce a summary that gets someone productive fast.

> Dispatch independent tasks to concurrent agents, integrate results, and verify no conflicts. Only for truly independent problems. **Invoked automatically by `harness-autopilot` (and standalone `harness-execution`), not only manually.** When a plan's phase has an auto-dispatch wave, the execution loop calls this skill to run that wave. In that mode the caller supplies worktree-per-unit isolation per `docs/guides/agent-worktree-patterns.md` (one worktree per task, sequential commits, squash-m...

> Red-Green-Refactor with performance assertions. Every feature gets a correctness test AND a benchmark. No optimization without measurement.

> Performance enforcement and benchmark management. Tier-based gates block commits and merges based on complexity, coupling, and runtime regression severity.

> Implementation planning with atomic tasks, goal-backward must-haves, and complete executable instructions. Every task fits in one context window.

> Lightweight pre-commit quality gate — mechanical checks first, AI review second. Fast feedback before code leaves your machine.

> Generate structured product specifications from feature requests, issues, or descriptions. Produces user stories with EARS acceptance criteria, Given-When-Then scenarios, and PRD documents with traceable requirements.

> Property-based and generative testing with fast-check, hypothesis, and automatic shrinking. Discovers edge cases that example-based tests miss by generating thousands of random inputs and verifying invariants hold for all of them.

> Single-page time-windowed product pulse. **Phase 3 ships the first-run interview only**: it converts vague intent into a concrete `pulse:` block in `harness.config.json`, refuses read-write DB credentials, and seeds from `STRATEGY.md` when present. The actual `harness pulse run` (Phases 2-4 of the runtime) is deferred to spec Phase 4.

> Safe refactoring with constraint verification at every step. Change structure without changing behavior, with harness checks as your safety net.

> Rehearse an agent against a deliberately-broken fixture and score how well it recovers. Free-soloing a change in production is how a small planted defect becomes an incident. A fixture lets an agent practise the crux move — notice the defect, reach for the right gate, fix it without breaking anything else — on a rope first. The same fixtures double as a regression test for the harness's own gates: if `check-security` stops catching a leaked secret, the leaked-secret fixture's score drops.

> Audit, fix, and track your project's path to a publishable release. No release without a passing report.

> Fleet-wide branch and worktree pruning. Sync first, classify every ref against PR state and containment, prove nothing unpushed will be lost, then prune — and report the resulting ref state, not a delete count.

> Circuit breakers, rate limiting, bulkheads, retry patterns, and fault tolerance analysis. Detects missing resilience patterns, evaluates failure modes, and recommends concrete configurations for production-grade fault tolerance.

> AI-assisted selection of the next highest-impact unblocked roadmap item. Scores candidates, recommends one, and transitions to the appropriate next skill. Selection does NOT assign — the `assignee` field names who is _executing_, and is written at execution start (harness-execution), not at selection.

> Create and manage a unified project roadmap from existing specs and plans. Interactive, human-confirmed, always valid.

> Post-ship circuit breaker. Proposes a full-context **revert PR** when a shipped PR fails post-merge evaluation or crosses a signal threshold. v1 is **propose-only** — it NEVER auto-merges. A human merges the revert.

> Natural language entry point to all harness skills. Classifies intent by scope/domain, confirms routing with reasoning, dispatches to the appropriate skill.

> Secret detection, credential hygiene, and vault integration. Find exposed secrets, classify risk, and enforce externalization before they reach production.

> Deep security audit combining mechanical scanning with AI-powered vulnerability analysis. OWASP baseline + stack-adaptive rules + optional threat modeling.

> Lightweight mechanical security scan. Fast triage, not deep review.

> Create and extend harness skills following the rich skill format. Define purpose, choose type, write skill.yaml and SKILL.md with all required sections, validate, and test.

> Deep soundness analysis of specs and plans. Auto-fixes inferrable issues, surfaces design decisions to you. Runs automatically before sign-off.

> Adversarial review of SQL queries for performance anti-patterns, missing indexes, N+1 queries, and unsafe operations. Analyzes raw SQL, ORM-generated queries, and migration scripts to produce optimization recommendations with estimated impact.

> Manage persistent state across agent sessions so that context, decisions, progress, and learnings survive context resets. Load state at session start, track position and decisions throughout, and save state for the next session.

> Repo-root strategic anchor. **Phase 2 of the strategic-anchor spec ships the skill**: a first-run interview that writes a valid `STRATEGY.md`, plus an update flow that re-interviews one section at a time with pushback against fluff, goals-as-strategy, and feature-lists-as-strategy. Downstream wiring (init, brainstorming, roadmap-pilot, ideate, knowledge graph) ships in spec Phases 3-7.

> 6-factor dependency risk evaluation adapted from Trail of Bits security skill patterns. Surfaces dependency risk flags for human review — not automated verdicts.

> Red-green-refactor cycle integrated with harness validation. No production code exists without a failing test first.

> Graph-based test selection. Answers: "I changed these files — what tests should I run?"