Multi-pass first principles analysis for any domain — business, personal decisions, creative projects, career, health, relationships. Grounds the analysis in real evidence first, decomposes problems to fundamental truths, challenges assumptions through 4 universal lenses (Constraints, Resources, Human, Context), and reconstructs solutions from evidence-backed ground truths. Three depths: lite (quick inline sanity-check), standard, and deep (parallel subagents per lens). Use when the user says "first principles", "from first principles", "analyze fundamentals", "challenge assumptions", "decompose problem", "why does this cost so much", "is this the right approach fundamentally", "what are we really solving", "strip away assumptions", "should I really be doing this". Also use when the user is stuck on a problem that seems intractable, when conventional approaches have failed, when questioning whether the whole approach is wrong, or when facing a "we've always done it this way" situation — whether in business, l
ALWAYS invoke this skill when the user reports a bug to fix — it traces the active code path, writes a failing test, iterates the fix, and reviews the diff, with test gates that prevent fixing the wrong code path. Do not edit suspected code directly before tracing the active path and writing a failing test. Triggers: "/bugfix", "fix bug", "investigate bug", "trace and fix", or a referenced issue ID. Do NOT use for new features (use /tdd), refactoring without bugs, or documentation changes.
Semi-automatic end-of-session ritual. Scans the session and machine for loose ends, presents ONE categorized report, and on approval executes cleanup + closing tasks so the user can `exit` with nothing undone, uncommitted, unmerged, or left as garbage. Invoke whenever the user signals they're finishing up — "/wrap-up", "wrap up", "wrap up the session", "close out", "let's wrap", "I'm done for today", "before I exit", "tidy up the session". Covers: uncommitted/unmerged work, stale dev servers, leftover git worktrees, booted/leaked simulators, scratchpad & temp files, issue-tracker status, docs that drifted, a code review of the session's diff, and a disk-residue check. Do NOT use for a one-off cleanup of a single thing the user named explicitly (just do that directly), nor as a substitute for a mid-session code review or deploy verification.
Spec-Driven TDD with a strict Red-Green-Refactor cycle using context-isolated subagents. Every feature starts with a structured spec; tests are generated from numbered acceptance criteria, with post-cycle three-dimension verification (Completeness + Traceability + Coherence), severity-tiered findings (CRITICAL/WARNING/SUGGESTION), and a spec-defect escape hatch that halts when the spec is internally contradictory or unimplementable instead of silently encoding it. Use when the user says "/tdd", "test first", "use tdd", "tdd approach", "write tests first", or when implementing new features/functionality. Trigger phrases: "implement", "add feature". Do NOT use for bug fixes without new tests, documentation changes, configuration-only changes, or refactoring existing code without new behavior.
Strategic research framework that compresses months of market/competitive research into hours through structured power questions. Extracts unspoken industry insights, fragile market assumptions, and strategic attack surfaces from competitor data, reviews, and industry sources using parallel Exa-powered intelligence gathering. Use when user says "attack surface", "research the market", "competitive analysis", "analyze competitors", "find market opportunity", "stress-test this idea", "market research", "evaluate opportunity", "find blind spots", "market entry", or when they want to deeply understand a market, evaluate a new direction, find industry blind spots, assess a partnership, or analyze opportunities. Do NOT use for code review, testing, deployment, bug fixing, or implementation tasks.
Conduct deep, multi-source research on any topic using parallel subagents, Exa search, and adversarial validation. Two modes: /deep-research (standard: 10+ sources, one researcher + a source-vetting pass) and /deep-research deep (multi-agent with 20+ sources, adversarial review, UNION merge). Use when the user asks to research a topic, investigate a question, find information across multiple sources, compare approaches, understand a domain, or says "research this", "deep dive", "investigate", "find out about", "what are the best practices for", "compare options for", "глубокое исследование", "ресерч", "исследуй", "найди информацию", "разберись в теме". Also use when the user wants competitive analysis, technology evaluation, or needs to understand a complex topic before making a decision. Do NOT use for simple factual questions answerable in one search, code review, bug fixing, or implementation tasks.