Repository
AnastasiyaW/codex-claude-code-config agent skills
- skills
- 52
- GitHub stars
- 154
GitHub description: “Claude Code, Codex, and multi-agent configuration system: principles, hooks, skills, and workflow patterns for AI-assisted development”
- Stars
- 154 (25 forks)
- Licence
- MIT
- Last push
- Oct 2026
- Created
- Mar 2026
- ai-agents
- claude
- claude-code
- llm
- machine-learning
- prompt-engineering
- skills
- mcp
- agent-harness
- harness
- wiring
Install all skills
npx skills add AnastasiyaW/codex-claude-code-configAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in AnastasiyaW/codex-claude-code-config, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Find likely software bugs in a codebase, rank concrete bug candidates, and prove or reject them with focused regression tests before proposing a fix. | AnastasiyaW/ | 154 | — | ~4.1k | Automated safety check: Pass | MIT | 5 days ago |
| 2 | A skill your agent uses when implementing Motion or Framer Motion in React/JavaScript: interactive UI components, micro-interactions, gestures, layout or page transitions, and scroll-based animation. | AnastasiyaW/ | 154 | 1 repo | ~5.2k | Automated safety check: Pass | MIT | 5 days ago |
| 3 | Plan-based verification - freeze acceptance criteria before building, then verify after with an independent fresh-context agent (the builder must not verify their own work). | AnastasiyaW/ | 154 | — | ~2.6k | Automated safety check: Pass | MIT | 5 days ago |
| 4 | Написание и запуск Claude Code dynamic workflows (JS-оркестратор субагентов). | AnastasiyaW/ | 154 | — | ~3.8k | Automated safety check: Pass | MIT | 5 days ago |
| 5 | A skill your agent uses when: NotebookLM, notebooklm MCP, large documentation sets, courses, books, papers, or citation-backed research are mentioned. | AnastasiyaW/ | 154 | — | ~2.4k | Automated safety check: Warn | MIT | 5 days ago |
| 6 | Validate a proposed DeepSeek API integration before any key or project context is sent: check thinking-mode tool-call history, strict-schema assumptions, bounded output, and provider data boundaries. | AnastasiyaW/ | 154 | — | ~1.2k | Automated safety check: Pass | MIT | 5 days ago |
| 7 | Discover, search, and selectively restore Claude desktop app sessions hidden across multiple accountIds. | AnastasiyaW/ | 154 | — | ~2.4k | Automated safety check: Pass | MIT | 5 days ago |
| 8 | Turn captured user-correction signals into durable rules (learn-from-corrections loop). | AnastasiyaW/ | 154 | — | ~2k | Automated safety check: Pass | MIT | 5 days ago |
| 9 | Scaffold a feature narrative in an existing project layer with Design, Plan, Verify, and Conclusion sections. | AnastasiyaW/ | 154 | — | ~3.4k | Automated safety check: Pass | MIT | 5 days ago |
| 10 | 10.Repo Map Ranked symbol map of a codebase within a token budget — a compact "what matters in this repo" before reading files. | AnastasiyaW/ | 154 | — | ~1.5k | Automated safety check: Pass | MIT | 5 days ago |
| 11 | A skill your agent uses when work moves between Claude Code and Codex, a session resumes from a handoff, or an agent may rewrite an existing implementation. | AnastasiyaW/ | 154 | — | ~1.2k | Automated safety check: Pass | MIT | 5 days ago |
| 12 | Score a project's agent harness across 5 subsystems (Instructions / State / Verification / Scope / Lifecycle), identify the bottleneck, and produce a prioritized improvement plan. | AnastasiyaW/ | 154 | — | ~2.5k | Automated safety check: Pass | MIT | 5 days ago |
| 13 | Comprehensive iOS app development skill. An agent skill from AnastasiyaW/codex-claude-code-config. | AnastasiyaW/ | 154 | — | ~2.2k | Automated safety check: Pass | MIT | 5 days ago |
| 14 | Design, audit, and troubleshoot production monitoring and observability using user-impact checks, layered telemetry, USE/RED, SLI/SLO/SLA, error budgets, cardinality controls, actionable alerting… | AnastasiyaW/ | 154 | — | ~4.1k | Automated safety check: Pass | MIT | 5 days ago |
| 15 | Iterative plan review using multisampling + focused decomposition. | AnastasiyaW/ | 154 | — | ~4.4k | Automated safety check: Pass | MIT | 5 days ago |
| 16 | 16.UI Design Unify product UI design, frontend implementation, and verification. | AnastasiyaW/ | 154 | — | ~2.4k | Automated safety check: Pass | MIT | 5 days ago |
| 17 | Choose and evaluate VLM or segmentation pipelines, including text-conditioned detection, masks, part labels, model-license constraints, and measured GPU deployment choices. | AnastasiyaW/ | 154 | — | ~910 | Automated safety check: Pass | MIT | 5 days ago |
| 18 | A skill your agent uses when designing, auditing, refactoring, or explaining an agentic harness for any domain, especially when work must continue from a measured gap to verified completion. | AnastasiyaW/ | 154 | — | ~5.4k | Automated safety check: Pass | MIT | 5 days ago |
| 19 | Keep web applications, APIs and services readable as they grow: choose feature or domain seams, assign state ownership, enforce dependency direction, keep adapters thin, and verify file shape. | AnastasiyaW/ | 154 | — | ~1.6k | Automated safety check: Pass | MIT | 5 days ago |
| 20 | 20.Deep Review Parallel competency-based code review. An agent skill from AnastasiyaW/codex-claude-code-config. | AnastasiyaW/ | 154 | — | ~4.4k | Automated safety check: Notes | MIT | 5 days ago |
| 21 | A skill your agent uses when the user asks the agent not to agree automatically, to challenge an assumption, evaluate a proposal critically, identify counterevidence, or make a high-consequence… | AnastasiyaW/ | 154 | — | ~1.2k | Automated safety check: Pass | MIT | 5 days ago |
| 22 | Expert prompt engineering for FLUX.2 [klein] image generation and editing model. | AnastasiyaW/ | 154 | — | ~2.8k | Automated safety check: Pass | MIT | 5 days ago |
| 23 | Plan or review LoRA and edit-training work specifically for FLUX.2 Klein or Qwen-Image-Edit, including paired datasets, trainer-version contracts, and held-out fidelity checks. | AnastasiyaW/ | 154 | — | ~4.5k | Automated safety check: Pass | MIT | 5 days ago |
| 24 | Делегирование задач в Gemini CLI с проверкой установленной версии, доступной модели и текущего доступа. | AnastasiyaW/ | 154 | — | ~2.1k | Automated safety check: Pass | MIT | 5 days ago |
| 25 | Design a scoped multi-agent harness for a requested long-running AI workflow. | AnastasiyaW/ | 154 | — | ~2.6k | Automated safety check: Pass | MIT | 5 days ago |
| 26 | A skill your agent uses when an agent says a test, VM, proof, evaluator, or release gate is overloaded, too strict, blocking staging, or causing false positives; split checks by profile, measure the… | AnastasiyaW/ | 154 | — | ~1k | Automated safety check: Pass | MIT | 5 days ago |
| 27 | Edit English drafts for clear, natural language while preserving facts, uncertainty, technical meaning, citations and genre. | AnastasiyaW/ | 154 | — | ~1.8k | Automated safety check: Pass | MIT | 5 days ago |
| 28 | 28.Layer New Scaffold a new layer in a project's docs/layers/ tree following the feature-layer architecture (principle 28). | AnastasiyaW/ | 154 | — | ~1.8k | Automated safety check: Pass | MIT | 5 days ago |
| 29 | 29.Owner Voice Пишет и редактирует текст голосом владелицы — сообщение, письмо, пост, объяснение, урок, рабочий разбор, на русском и английском. | AnastasiyaW/ | 154 | — | ~874 | Automated safety check: Notes | MIT | 5 days ago |
| 30 | A skill your agent uses when a large plan, PRD, feature, refactor, research plan, or multi-step coding task must be split into small ready-for-agent tickets with acceptance criteria, verification… | AnastasiyaW/ | 154 | — | ~683 | Automated safety check: Pass | MIT | 5 days ago |
| 31 | Deep product analysis before creating videos, presentations, or ads. | AnastasiyaW/ | 154 | — | ~2.7k | Automated safety check: Pass | MIT | 5 days ago |
| 32 | Remotion (React video framework) production guide with Apple-style design rules. | AnastasiyaW/ | 154 | — | ~2k | Automated safety check: Pass | MIT | 5 days ago |
| 33 | Evaluate video scripts and presentations for flatness, tension, and emotional impact. | AnastasiyaW/ | 154 | — | ~2.1k | Automated safety check: Pass | MIT | 5 days ago |
| 34 | A skill your agent uses when planning or reviewing tests for a code change, choosing between unit, focused regression, integration, contract, end-to-end, performance, security, property-based, or… | AnastasiyaW/ | 154 | — | ~2k | Automated safety check: Pass | MIT | 5 days ago |
| 35 | 35.Verify This Prove a concrete behavior, performance, UI, CLI, API, or memory claim with fresh baseline-versus-treatment evidence and one explicit verdict. | AnastasiyaW/ | 154 | — | ~1.2k | Automated safety check: Pass | MIT | 5 days ago |
| 36 | Proven narrative arc templates for product videos and ads. An agent skill from AnastasiyaW/codex-claude-code-config. | AnastasiyaW/ | 154 | — | ~2.3k | Automated safety check: Pass | MIT | 5 days ago |
| 37 | Video post-production rules: audio mastering, color, captions, platform export. | AnastasiyaW/ | 154 | — | ~1.7k | Automated safety check: Pass | MIT | 5 days ago |
| 38 | Decide module boundaries before the first file: what modules exist, which way dependencies point, who owns state, and what each module may know. | AnastasiyaW/ | 154 | — | ~2k | Automated safety check: Pass | MIT | 5 days ago |
| 39 | Практическая инженерия диффузионных моделей: архитектуры, обучение, инференс, оптимизация памяти. | AnastasiyaW/ | 154 | — | ~1.2k | Automated safety check: Pass | MIT | 5 days ago |
| 40 | Создание высококачественных, визуально выдающихся фронтенд-интерфейсов. | AnastasiyaW/ | 154 | — | ~1.1k | Automated safety check: Pass | MIT | 5 days ago |
| 41 | Operate GPU and remote compute across RunPod (Pods and Serverless), Massed Compute VMs, and owned or virtual remote servers through existing bridges, SSH sessions, MCP/API adapters, bounded polling… | AnastasiyaW/ | 154 | — | ~3k | Automated safety check: Pass | MIT | 5 days ago |
| 42 | Decide whether the system will hold, and where the data lives: requirements and load first, then back-of-the-envelope numbers, building blocks (cache, queue, load balancer, CDN), and the data layer… | AnastasiyaW/ | 154 | — | ~1.7k | Automated safety check: Pass | MIT | 5 days ago |
| 43 | Designing agent harnesses and tool systems — risk taxonomy for tools, permission decisions, draft/commit pattern, structured tool results, agent budgets (10 types), context trust labels against… | AnastasiyaW/ | 154 | — | ~764 | Automated safety check: Pass | MIT | 5 days ago |
| 44 | 44.Caveman Ultra-compressed reply mode. An agent skill from AnastasiyaW/codex-claude-code-config. | AnastasiyaW/ | 154 | — | ~3k | Automated safety check: Pass | MIT | 5 days ago |
| 45 | 45.Control CLI Drive and inspect an interactive CLI or TUI with a repeatable local harness, deterministic input, transcripts, and optional profiling. | AnastasiyaW/ | 154 | — | ~887 | Automated safety check: Pass | MIT | 5 days ago |
| 46 | 46.Control UI Drive and inspect a local web, IDE, or Electron UI with browser or CDP automation and evidence. | AnastasiyaW/ | 154 | — | ~757 | Automated safety check: Pass | MIT | 5 days ago |
| 47 | 47.Deslop Remove AI-generated code noise from the current diff while preserving behavior. | AnastasiyaW/ | 154 | — | ~706 | Automated safety check: Pass | MIT | 5 days ago |
| 48 | 48.Lean Code On-demand minimalism intensifier — find the smallest sufficient, verified implementation for the requested outcome. | AnastasiyaW/ | 154 | — | ~1.3k | Automated safety check: Pass | MIT | 5 days ago |
Questions, answered from the data.
What is the best skill in AnastasiyaW/codex-claude-code-config?
Bug Reproducer from AnastasiyaW/codex-claude-code-config ranks first of the 52 skills in AnastasiyaW/codex-claude-code-config listed here, with the highest score: its repository has 154 GitHub stars, its SKILL.md loads about 4.1k tokens and it passes the automated safety check with no findings. Next come Motion Framer and Proof Verify.
Are the skills in AnastasiyaW/codex-claude-code-config official?
None yet. All 52 skills in AnastasiyaW/codex-claude-code-config listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from AnastasiyaW/codex-claude-code-config?
Run npx skills add AnastasiyaW/codex-claude-code-config in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.