v1truv1us

Guides systematic root-cause debugging. Use when tests fail, builds break, behavior does not match expectations, or any unexpected error appears.

Chrome DevTools for live runtime data: DOM inspection, console logs, network traces, performance profiling. Use when building or debugging anything in a browser.

Instinct-based learning system with confidence scoring, import/export, and evolution into skills. The system learns patterns from sessions and promotes high-confidence instincts into durable skills. Use when extracting patterns from completed work.

Architecture Decision Records, API docs, inline documentation standards. Use when making architectural decisions, changing APIs, or shipping features. Document the why, not the what.

Component architecture, design systems, state management, responsive design, WCAG 2.1 AA accessibility. Use when building or modifying user-facing interfaces.

Contract-first design, Hyrum's Law, One-Version Rule, error semantics, boundary validation. Use when designing APIs, module boundaries, or public interfaces.

Measure-first approach for Core Web Vitals targets, profiling workflows, bundle analysis, and anti-pattern detection. Use when performance requirements exist or you suspect regressions.

Build and reason about import graphs, call graphs, schema graphs, and service dependency graphs. Use when tracing paths, finding god nodes, surfacing cycles, or answering architecture questions about how parts connect.

Code-as-liability mindset, compulsory vs advisory deprecation, migration patterns, zombie code removal. Use when removing old systems, migrating users, or sunsetting features.

Run an extremely strict performance review for runtime efficiency, memory usage, bundle size, database query patterns, and scalability limits. Use for a thermo-nuclear performance review, thermonuclear performance audit, or especially harsh performance review.

Run an extremely strict architecture and system design review for coupling, boundary violations, dependency direction, layering, and structural decay. Use for a thermo-nuclear architecture review, thermonuclear system design audit, or especially harsh architecture review.

Trunk-based development, atomic commits, change sizing (~100 lines), commit-as-save-point pattern. Use when making any code change.

Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'

Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.

Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.

Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.

Premier research workflow for systematic investigation, synthesis, and verification. Use for literature reviews, competitive analysis, deep dives, market research, or any task requiring structured research with source attribution.

Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.

Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope.

Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, refuse to lie to the compiler, exhaust variants, derive from authoritative schemas.

Apply when sequencing an addition, refactor, or rewrite. Remove dead weight, redundant validators, and stub references first, then build on the simpler base.

Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.

Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.

Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions.

Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless of partial prior runs.

Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states with throwaway compatibility code.

Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.

Apply when integrating a new requirement into an existing design. Redesign as if the requirement had been a foundational assumption from day one, instead of bolting it on.

Apply when introducing a new internal API while old callers still exist. Migrate callers and delete the old API in the same wave instead of preserving compatibility layers.

Apply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one shared writer is a real invariant.

OWASP Top 10 prevention, auth patterns, secrets management, dependency auditing, boundary validation. Use when handling user input, auth, or external integrations.

Run Playwright smoke tests, debug failures, and verify fixes

Multi-axis code review with optional strict maintainability mode. Use before merging any change—human, agent, or automation output.

Recursively initialize AGENTS.md in monorepo subdirectories with smart detection. Creates hierarchical agent context files with proper linking to root CLAUDE.md and parent AGENTS.md. Use for setting up multi-package projects, microservices, or any project with important subdirectories that need AI agent guidance.

Write a structured specification before code: objectives, structure, code style, testing strategy, boundaries. Use when starting a new project or feature.

Red-Green-Refactor workflow: write tests before implementation, maintain coverage. Use when implementing logic, fixing bugs, or changing behavior.

Run the full repository compatibility pass: scanner score, startup path, validation loop, and docs reliability.

Ground every framework decision in official documentation. Use when you want authoritative, source-cited code for any framework or library.

Comprehensive prompt engineering for coding agents covering structured instruction design, few-shot prompting, chain-of-thought, decomposition, agent workflow patterns, and reliability techniques for multi-step pipelines.

Deliver changes in thin vertical slices. Use when implementing a feature or refactor that touches more than one file.

Evaluate learning progress, identify blockers, and adjust the learning plan

Feed agents the right information at the right time. Use when starting a session, switching tasks, or when output quality drops due to missing or stale context.

Resolve merge conflicts non-interactively, validate build and tests, and finalize conflict resolution

Research-backed prompting techniques for improved AI response quality (+45-115% improvement). Use when optimizing prompts, enhancing agent instructions, or when maximum response quality is critical. Invoked by /ai-eng/optimize command. Includes expert persona, stakes language, step-by-step reasoning, challenge framing, and self-evaluation techniques.

Summarize authored commits over a user-specified time period into a concise update

Normalize mixed inputs like code, docs, PDFs, screenshots, diagrams, audio, and transcripts into a structured corpus. Use when the task depends on combining multiple artifact types before analysis or retrieval.

Decompose specs into small, verifiable tasks with acceptance criteria and dependency ordering. Use when you have a spec and need implementable units.

Enhance any content type using research-backed techniques. Optimize AI prompts with step-by-step approval, improve code quality, refine database queries, enhance documentation, optimize commit messages, and improve communication. Wraps incentive-prompting skill with content-type detection.

Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via create-skill + unslop, optionally pulling fresh evidence from recent transcripts.

poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.

Discovery and invocation of all skills, commands, and agents. Decision tree for task-to-skill mapping. Core operating behaviors for agents. Use when unsure which skill or agent to use.

Structured divergent/convergent thinking to turn vague ideas into concrete proposals. Use when you have a rough concept that needs exploration before committing to a spec.

Simplifies code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be.

Extract reusable patterns from sessions, score confidence, and promote high-confidence instincts into durable skills. Use after completing significant work.

Coordinate a multi-repo refactor by fanning out subagents per repo onto one feature branch. Use for cross-repo changes that touch multiple repositories.

Review changes, open PRs, run pre-launch checks, staged rollouts, and rollback. Use when preparing to ship to production or closing out a branch.

Classify every skill in skills/ as user-invoked or model-invoked, ensure disable-model-invocation is set on user-invoked skills, and inject metadata.category on all. Run after adding or changing skills, or when token-cost/routing quality is being reviewed. Use for "sync skill taxonomy", "classify skills", "fix disable-model-invocation", or "skill token audit".

Extract durable working preferences from recent Cursor chats and convert them into skills, rules, or workflow docs. Use when asked to learn preferences, mine feedback, personalize workflows, or generate team/person-specific agent guidance.

Design CI/CD pipelines, quality gates, and iterate on failing PR checks until green. Use when setting up pipelines or fixing CI on a branch.

Build a personalized learning roadmap with milestones and practice checkpoints

Read the auto-memory graph (~/.claude/projects/*/memory/*.md), find cross-session patterns, and write a digest. The skill never mutates memory — output goes to a fresh file the user reads. The cron-driven version is the daily-brief-sdk dream-digest workflow, which writes to a separate dedicated directory.

Continuous iteration loop pattern for well-defined tasks with clear completion criteria. Use when getting tests to pass, implementing features with automatic verification, bug fixing with clear success conditions, or running automated development overnight. Provides prompt templates, safety guidelines, and integration patterns for ai-eng-system workflows.

Context window management for AI agents. Optimize context usage, prevent overflow, and ensure critical information is always available. Use when working with large codebases or long sessions.

Multi-phase research orchestration for thorough codebase, documentation, and external knowledge investigation. Invoked by /ai-eng/research command. Use when conducting deep analysis, exploring codebases, investigating patterns, or synthesizing findings from multiple sources.

Build a static-first knowledge architecture using file-backed domain maps, rules, hypotheses, and durable references. Use for knowledge architecture, learning systems, decision context, and long-lived team memory without runtime memory tooling.

Prepare PRs for review: clean noisy history, improve descriptions, add reviewer guidance without changing behavior. Use when a PR is hard to review.

Publish npm packages via GitHub Actions with OIDC trusted publishing and provenance. Use when setting up automated npm publishes, debugging ENEEDAUTH/E404 errors, configuring provenance attestations, or setting up a new package for publication.

Write, run, and maintain reliable end-to-end tests with Playwright. Use for test generation, CI integration, trace debugging, and cross-browser validation.

This skill should be used when creating extensions for Claude Code or OpenCode, including plugins, commands, agents, skills, and custom tools. Covers both platforms with format specifications, best practices, and the ai-eng-system build system.

Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Can critique architecture. Use why for motivation.

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.

Principal-engineer repository audit and prioritized improvement plan. Four phases - discovery, evidence-based audit, strategy, task plan - with file:line citations and severity ratings. Analysis only, no code changes. Use when asked to "audit this repo", "project review", "health check", "improvement plan", or after a model upgrade to re-baseline important projects.

Build, test, and archive iOS/macOS apps with xcodebuild and Xcode CLI tools. Use for CI integration, scheme management, simulator control, and build troubleshooting.

Build a local harness to drive, inspect, and profile an interactive CLI or TUI. Use for CLI UX checks, startup regressions, hangs, or prompt-flow verification.

Transform a vague idea, request, or prompt into a concrete, actionable goal with clear success criteria, scope boundaries, and measurable outcomes. Use when the user has an intention but needs help defining what "done" looks like.

Render a documentation-style Cursor Canvas that organizes architecture notes, API references, walkthroughs, and how-tos into a navigable layout with sections, tables of contents, and cross-references. Use when the user asks for a docs canvas, documentation overview, architecture walkthrough, API reference page, or wants to render structured documentation as an interactive canvas.

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Four LLM reviewers challenge changes from independent angles.

Use only when the user explicitly types `/ai-eng/orchestrate <goal>` to decompose a large task, spawn a tree of parallel cloud-agent workers/subplanners/verifiers via the Cursor SDK, and collect structured handoffs; do not invoke autonomously.

Agent evaluation framework. Measure agent performance, identify weaknesses, and track improvement over time. Use when assessing agent quality, comparing approaches, or validating changes.

Manage git worktrees for isolated parallel development. Use when running multiple sessions concurrently or working on parallel features.

Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.

Remove AI-generated filler, repetition, inflated language, and redundant comments while preserving meaning.

Daily briefing synthesizing calendar, tasks, and priorities. Use for "morning brief", "daily briefing", "start my day", or /morning-brief.

Multi-source deep research with confidence-rated synthesis. Use for "research deeply", "deep dive on", "comprehensive research", or /research-deep.

Self-continuing loop that fixes a deliberately failing test, reruns it, and exits cleanly when green. Smallest cooking-routines skill — pairs with the cooking Stop hook to keep iterating past natural stops.

Produce a weekly synthesis of authored commits with highlights by bugfix, tech debt, and net-new work

Unified agent application scaffolding across 5 harnesses: Anthropic, Cursor, OpenAI, OpenCode, and Pi. Interactive project generator with live SDK docs, per-harness code patterns, and built-in verification. Use when someone says "create an agent app", "new SDK project", "build with [harness] SDK", "scaffold agent", or wants to verify an existing agent setup.

Design or review CLIs so coding agents can run them reliably: non-interactive flags, fast actionable errors, idempotency, dry-run, layered --help. Use when building a CLI or adding commands.

Deploy applications to Coolify self-hosting platform. Use when deploying to Coolify, configuring build settings, setting environment variables, managing health checks, or performing rollbacks.

Conductor/subagent routing for tasks across multiple harnesses. Assesses task complexity and intent, then dispatches to the appropriate subagent model via a harness-specific adapter. Supports Anthropic (Claude), Cursor, OpenCode, Codex (OpenAI), and Pi adapters. Use via /dynamic-task command or direct invocation from other skills.

Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.

Stanford STORM multi-perspective research method. Runs four sequential phases (multi-perspective scan, contradiction map, synthesis, peer review) in one thread to produce a PhD-level briefing on any topic. Use for "storm research X", "multi-perspective research", "STORM method", or any topic where a single-prompt answer is too shallow.

Review recently changed files for reuse, quality, and efficiency issues, then fix them. Use after completing a change, before declaring done.

Extend grill-me by producing or updating a CONTEXT.md or ADR-style decision record while stress-testing a plan. Use when the user wants to be grilled and wants the shared understanding persisted as a living document.

Knowledge graph development for LLM applications. Graph storage selection, graph algorithms, extraction from documents/code/websites, entity extraction, Graph RAG, and visualization. Use when building knowledge graphs, graph databases, or LLM graph applications.

Build Gemini-backed agent workflows and adapters. Use for Google Gemini API/ADK-style runners, Gemini CLI workflow parity, tool calling, structured outputs, or adding a Gemini variant beside Cursor/OpenCode/Claude runners.

Generate an interactive PR review walkthrough as an HTML page. Fetches PR data via gh API, categorizes files into core vs mechanical changes, adds reviewer annotations, and renders diffs with moved-code detection. Use when the user pastes a GitHub PR URL and asks for a review, walkthrough, or summary, or says \"review this PR\".

Document solved problems with context, examples, and gotchas so learnings compound for the team. Use after completing a workflow worth remembering.

Convert vague requests into compact TCRO prompts with phase-specific constraints. Used by research, specify, plan, and work workflows.

Continuous verification after each change, plus claim-based proof when evidence is required. Use when implementing, fixing bugs, or refactoring.