Design, refactor, or review code when semantic clarity is the explicit goal, using precise domain names, explicit failures and effects, useful domain types, immutable data flow,…
Z analytického kontextu (investigation.md / anomaly entry / refactor proposal) složí Jira issue body podle projektových konvencí. Předloží draft ke schválení.
Run comprehensive expert code review on current branch changes and fix findings across debug/dead code, rule violations, correctness risks, and explicit…
Improve code quality through adaptive refactoring workflows while preserving behavior and enforcing architectural standards.
Implement, refactor, or review worker-based multithreading in TypeScript/JavaScript apps (browser or Node).
Use when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation.
Manufacturing-fokussierter Continuous Improvement Skill fuer fabrikIQ. Implementiert Lean Manufacturing Prinzipien (5 Whys, Ishikawa, PDCA) fuer systematische Problemloes — from…
Manufacturing-fokussierter Continuous Improvement Skill fuer fabrikIQ. Implementiert Lean Manufacturing Prinzipien (5 Whys, Ishikawa, PDCA) fuer systematische Problemloes — from…
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface ass — from…
Applies Karpathy's "A Recipe for Training Neural Networks" adapted to software engineering. Forces a minimum runnable baseline before optimizing, one knob at a time, with…
Guidelines to improve coding style and avoid common pitfalls. Use when writing, reviewing, or refactoring any kind of code.
Resolve complex coding, refactoring, and engineering problems using an epistemic loop (Triage -> Prior Art -> Risk Planning -> Adversarial Critic -> Grounded Test Verification).
Development conductor — the dev toolbox. Run it by name to build and maintain through the Pocock spine (grill-with-docs → to-spec → to-tickets → implement → code-review → keel-qa…
Why leading with precise imperative action verbs ('Refactor', 'Audit', 'Synthesize') maximizes model attention and eliminates preamble fluff.
Delegate a coding task to the Kimi Code CLI (`kimi`) as a background implementer, then review its diff and land it yourself.
Auto-generate code structure index (Repo Map). Extracts class names and method signatures for component types defined in ecw.yml (e.g., Facade/BizService/Manager), grouped by…
Use after completing a refactor, implementing a major feature, or when skills may be outdated. Analyzes code changes, identifies affected skills, and proposes updates to keep team…
Use when reviewing implemented Kotlin Multiplatform / Compose Multiplatform code for architecture consistency, business-logic placement, state correctness, concurrency, Compose…
Refactor discipline for existing codebases. Enforces scope control, migration safety, compatibility, observability, and tests to keep refactors reviewable and low-risk.
Use when designing, reviewing, or refactoring module boundaries in KMP or Android projects — feature, data, app, and common modules, dependency direction, visibility control, and…
Land a large change too big for one PR as a sequence of PRs merging into a long-lived integration branch, then a final PR into main.
Post-work verification sweep run by a FRESH agent: did the change land where it actually executes, do the stated claims match disk, and what should have moved and didn't.
Reviews LangGraph code for bugs, anti-patterns, and improvements. Use when reviewing code that uses StateGraph, nodes, edges, checkpointing, or other LangGraph features.
Use when Claude Code hits "File content exceeds maximum allowed tokens" error, or when files are too large to read.
Guardrails, protocols, and operating constraints for large-scale, long-running, or parallelized AI coding tasks — migrations, codebase-wide refactors, framework upgrades, and any…
Put a tangent on the later list (one line in LATER.md) and go back to the current task, then sort the list at a natural break (do now, schedule, drop).
Autonomous bug-elimination loop. Iteratively invokes /bug-hunt and /implement-batch until findings converge below an operator-specified severity floor.
Autonomous technical lead. Takes commander's intent and drives a project to completion through an OODA loop over implementation, refactoring, review, and bug-hunting skills.
Autonomous comprehensive refactoring. Three-phase pipeline — Phase 1 /refactor (tactical, loops internally to convergence) → Phase 2 loop of /review-arch + /implement-batch until…
Interactive LeetCode-style teacher for technical interview preparation. Generates coding playgrounds with real product challenges, teaches patterns and techniques, supports…
Expert system for identifying deprecated patterns, suggesting refactoring to modern standards (Python 3.12+, ES2024+), checking test coverage, and leveraging AI-powered tools.
Methodological guide for the AI Agent to safely and systematically translate, refactor, and modernize giant legacy codebases (PHP, Python 2, old React) into modern stacks.
Investigate unfamiliar legacy code before edits. Triggers: legacy module, unknown repo, risky refactor, trace ownership. Triggers:
Refactor legacy codebases, migrate outdated frameworks, and implement gradual modernization. Handles technical debt, dependency updates, and backward compatibility.
Knowledge steward for Johnny-Decimal/Zettelkasten Obsidian vaults. Use when managing vault structure, auditing links, cleaning up notes, constructing new vault sections, reviewing…
Secure code review skill for application risk analysis, threat modeling, scanner tuning, and developer-focused remediation guidance.
Apply linuxlewis's code review style to pull requests, local diffs, or proposed code changes. Use when asked to review code the way linuxlewis would, emulate Sam Bolgert's review…
Nightly direct-execution skill for reducing code complexity thresholds. Receives pre-computed threshold data, refactors violations, updates thresholds, commits, and creat — from…
Analyzes source code repositories using list-codes and ghq. Use this when the user asks to analyze, review, explain, or refactor a codebase (local or remote).
Reviews Phoenix LiveView code for lifecycle patterns, assigns/streams usage, components, and security. Use when reviewing LiveView modules, .heex templates, or LiveComponents.
Worker that checks DRY/KISS/YAGNI/architecture compliance with quantitative Code Quality Score. Validates architectural decisions via MCP Ref: (1) Optimality - is chosen approach…
Checks DRY/KISS/YAGNI/architecture compliance with quantitative Code Quality Score. Use when implementation tasks are Done and need quality scoring.
Auto-fixes low-risk tech debt (unused imports, dead code, commented-out code) with >=90% confidence. Use when audit findings need safe automated cleanup.
Audit code comments and docstrings quality across 6 categories (WHY-not-WHAT, Density, Forbidden Content, Docstrings, Actuality, Legacy).
Launch and manage OpenAI Codex CLI (local agent) as a non-interactive coding sub-agent. Use when the user wants to delegate coding tasks to Codex, run code reviews, generate or…
Logic optimization and image-based code tasks with Codex CLI in --yolo mode. Use when (1) optimizing code logic or algorithms, (2) processing image inputs (screenshots, diagrams,…
Run multi-axis implementation review through Loom critique. Use before merge, after feature or bug-fix implementation, when receiving review feedback, when reviewing AI/human…
Use when a code diff, branch, PR, worker output, or implementation-complete ticket needs a code-focused quality review across correctness, tests, architecture, security,…
Implement changes in small verified slices. Use when a feature, refactor, migration, or bug fix touches multiple files, feels too large to land at once, needs feature flags, or…
Run Ralph implementation packets. Use for larger feature, refactor, test, migration, or cleanup slices when a Ralph-ready ticket needs fresh context, explicit write scope,…
Maintain bounded execution and acceptance. Use when adding or changing code, tests, docs, config, refactors, migrations, cleanup, blockers, evidence/review disposition, or any…
Lorekeeper-specific BLOCKER patterns, severity tiers, and review checklist — used when reviewing any PR touching src/lorekeeper/
Standalone refactor CLI driving any LSP server: project-wide rename, file-move with importer updates, and code actions.
Use when reviewing code for anti-patterns. Keywords: anti-pattern, common mistake, pitfall, code smell, bad practice, code review, is this an anti-pattern, better way to do this,…
Reviews Rust macro code for hygiene issues, fragment misuse, compile-time impact, and procedural macro patterns.
Review code changes against requirements for production readiness. Evaluate technically, no rubber stamping.
Write a comprehensive plan to refactor with TDD tasks. Every step has real code, no placeholders.
Bring a project's formal verification back in line with the code after the code changes: find the commits that touched verified code, update the model, harness, or properties to…
Use to sequence your work on a change — make it work, then make it right, then make it fast, in that order; keep one concern per change; don't tangle a feature with a refactor.
Analyzes existing code and guides new type design to make invalid states unrepresentable using type system techniques such as sum types, newtypes, typestate, branded types, and…