codebytes-skills
claudecodexPortable, tested agent skills for GitHub Copilot, Codex, Claude Code, Cursor, Gemini CLI, and other Agent Skills compatible hosts.
5 skills
Claude Code and Codex plugins their authors filed under "Developer Tools". All categories.
Portable, tested agent skills for GitHub Copilot, Codex, Claude Code, Cursor, Gemini CLI, and other Agent Skills compatible hosts.
5 skills
Persistent cross-session memory for Claude Code backed by Rembr: bundled MCP server, first-prompt semantic recall or session restoration, trigger capture, and manual skills.
3 skills · 1 MCP server · hooks
Real-time terminal status bar for Claude Code — context window, rate limits, 5-hour/7-day quotas, burn-rate alerts, sparkline history, and preset themes.
4 commands · hooks
Open-source Codex plugin for auditable A-share research and paper trading with MCP, Skills, and a deterministic Python engine.
4 skills · 1 MCP server
Maintenance companion for AI_Skills_Collection plugin refinement and current-machine AI Research Stack updates: formal release routing, generated parity, replay, regression, versions, changelogs, profile installation, and Bridge Kit distribution delegation.
5 skills
Five selected Lox engineering skills for explicit trials.
5 skills
Open-source Codex plugin for auditable A-share research and paper trading with MCP, Skills, and a deterministic Python engine.
4 skills · 1 MCP server
Compare instructions, MCP servers, skills, and plugins across the Claude Code, Codex, and Copilot CLI agents installed on one machine, with fixes only on request.
5 skills
Evaluate repository maturity for Dockerfiles, npm projects, repository hygiene, and CI workflows, with fixes only on request.
5 skills
Read-only investigation skills across CI pipelines (Jenkins, GitHub Actions), CD (Argo CD, Flux, Helm, Kubernetes), databases (PostgreSQL, MySQL, MongoDB) and telemetry (Grafana, Loki, Tempo, Prometheus).
5 skills
Detect vacuous Lean 4 proofs (fake P=NP and friends)
2 skills · 2 commands
codosos: a small kit of must-have agent skills (bro, tldr, handoff, next-steps)
4 skills
Guided Payments AI skills for merchant onboarding and checkout branding, plus the bundled Payments AI MCP server.
3 skills · 1 MCP server
Command syntax testbed - reference implementations of all plugin feature types
2 commands · 1 agent · 1 MCP server
Tools for contributors to the Axon Framework project: code reviews against AF5 standards, core coding patterns, framework infrastructure design guidelines, reference documentation authoring, and PR comment processing. Not intended for application developers.
4 skills
Migrate applications from Axon Framework 4 to Axon Framework 5 / Axoniq Framework 5.
4 skills
Code review and change analysis skills — why/how investigation of PRs from git history, diff blast-radius proof by execution, credential authn/authz checks, and adversarial review
4 skills
Agent Message Queue - file-based inter-agent messaging with co-op mode, cross-project federation, and orchestrator integrations (Symphony, Kanban).
4 skills
Finds code that breaks book-derived principles. A deterministic Python scanner with 20 detected rules (DRY, small functions, crash early, Law of Demeter, shared state, injection, dependency rule, inheritance tax, CQS and more), each tied to a book and tip and proven by fixtures; JSON and SARIF output for CI. A cited model judge covers what code cannot decide. 2 skills (review, principles) and 1 agent (principles-judge).
2 skills · 1 agent · hooks
View and control local Apple simulators and connected devices through Xcode.
3 skills · 1 MCP server
逆向复盘与因果走读:自己看与对外发布各提供 Markdown/HTML;HTML 先事实、大纲、文案再写受限 XSU,由独立脚本渲染固定步进页或翻页报告,默认离线,Pele 图表须显式联网;Markdown 保持直接写作入口
4 skills
Jurisdigta task preparation, implementation, incident reporting, and architecture decision workflows.
4 skills
Passive, opt-in agent failure capture and deterministic regression evidence.
1 skill · 1 MCP server · hooks
Continuous quality review with source-anchored findings.
2 skills · 1 MCP server
Estimates the water footprint of your Claude Code sessions from local token counts. Transparent, editable coefficients; the estimator makes no network calls; reads no message content.
2 commands · hooks
Check quantum circuits locally and work with evidence-bearing Leona notebooks through MCP.
2 skills · 1 MCP server
@rabjs/kit skills for coding agents: using-rabjs-kit, adding-kit-function, migrating-lodash-to-kit
3 skills
Run GPU workloads with Nodus, monitor progress, read logs and inspect results.
2 skills · 1 MCP server
Practical, composable skills for engineering work and personal development.
3 skills
Agent operations skills — set up a project's memory layout once, rebuild working context at session start, and turn each session's lessons into approved edits to the memory structure the codebase already has
3 skills