evals-from-sessions
claudecodexTurn your own coding-agent sessions into verified Harbor eval tasks, with two human review checkpoints.
1 skill
Claude Code and Codex plugins their authors filed under "development". All categories.
Turn your own coding-agent sessions into verified Harbor eval tasks, with two human review checkpoints.
1 skill
Migration skills for web apps, frameworks, Cordova, SPM, Appflow, Ionic Enterprise SDK, and SQLite alternatives.
8 skills
Capacitor plugin development skills for SPM support and plugin major-version upgrades.
8 skills
Capgo cloud skills for CLI usage, live updates, hosted native builds, release management, and organization workflows.
7 skills
Audit Xcode storage and clean only exact user-approved candidates.
1 skill
Official Gradle skills for AI coding agents: audit a build against Gradle best practices, and upgrade the Gradle wrapper.
2 skills
Autonomous multi-agent software evolution via /factory:implement
7 skills
多智能体工作流扩展,提供完整的 AI 辅助编程工作流
24 skills · 13 agents · hooks
Build, test, and ship voice agents with LiveKit. Skills for the LiveKit Agents SDK (Python and Node.js) covering voice AI architecture, live debugging, turn-level tests, simulations, and deployment, plus the LiveKit Docs MCP server for current docs, SDK code search, and changelogs.
7 skills · 1 MCP server
Manage Laravel Forge servers, sites, deployments, and logs with Hermit, with approval before changes.
6 skills
Git safeguards, debugging, and merge-conflict resolution for your Hermit.
4 skills · hooks
Terminal-based code review companion for Claude Code. Review diffs, leave structured feedback, and submit reviews — all from a TUI running alongside Claude.
4 commands · 1 MCP server
Craft is a Claude Code plugin that asks you the product questions and works out the technical ones. Features get planned, built, and tested, with your codebase read-only until you approve the work. Point at a live page to change it. The calls you make - decisions, design tokens, the tweaks you loved - carry into every build after.
11 skills · 77 commands · 27 agents · 1 MCP server · hooks
Orchestration harness that turns Claude Code into a coordinated team of specialist AI agents
21 skills · 14 commands · 13 agents · 1 MCP server · hooks
Make Claude predict, act, measure, learn, and stop at the smallest verified solution.
1 skill
Claude Code plugin for SAP ABAP development on On-Premise S/4HANA — 26 specialized agents, 16 workflow skills (create-program with Phase 4/6 hardening + multi-executor split, create-object, program-to-spec, program-to-manual (end-user HTML manual), compare-programs, config-to-document (module configuration document from the live system), analyze-code/symptom, stock-cbo, ask-consultant, setup, internal trust-session), 4-Tier context loading, Sonnet/Opus model routing, OK_CODE binding pattern, paradigm-split Clean ABAP, and SPRO config reference for 14 modules.
24 skills · 27 agents · 1 MCP server · hooks
Production-grade platform engineering handbook for Claude, Codex, and Cursor. 51 slash-command workflows: Kubernetes (baseline, RBAC, workload, debug), GitHub Actions (design, security, review, debug), Azure (Workload Identity, AKS, tagging, RBAC), OpenShift (SCC, Routes, GitOps, upgrades), Secrets (ESO, Sealed Secrets, rotation, audit), Helm, Terraform, Flux CD, Argo CD, Gateway API (ingress-nginx migration), AWS, Kyverno, OPA, KEDA, Karpenter, cluster upgrades (EKS version rollback), Flagger progressive delivery, Velero backup and restore drills, FinOps (Infracost, cost tags, OpenCost), supply chain security, Kubescape posture and operator (NSA, MITRE, CIS, SOC2), Falco, chaos engineering, DORA metrics, Datadog, Dynatrace, Linkerd, AWS MCP, Renovate, Checkov, Trivy, Zizmor workflow auditing, Kingfisher secret scanning and revocation, token optimization, and multi-agent scaffolding. Every answer includes blast radius, validation steps, and rollback plan.
52 skills · 1 agent
Capture and diagnose Claude Code trajectories with AgentDebugX.
1 skill · hooks
Set up git worktrees for Laravel projects with Laravel Herd integration
1 skill
Automatically generates relationship and dependency maps for codebases. Creates JSON indexes of component usage, npm dependencies, data flow, and utility relationships to help AI understand project structure.
1 skill
Optional enforcing hooks for platform-skills: self-improve lifecycle capture and the ai-governance policy gate (active only in projects with a .ai-governance.yaml). Separate from platform-skills because plugin hooks run in every session for everyone who enables them.
hooks
AI agent skill for Catalyst by Zoho — the agent-ready, full-stack cloud. Covers all services, SDKs, CLI, architecture patterns, pricing, migration guides, and Zoho MCP tool-based resource management.
19 skills · 1 MCP server
Orchestrateur Claude Code à modules : socle de gouvernance (conductor) posé d'office, puis un choix — lab de développement + design (modèle agentique : intention → équipes d'agents qui portent les briques GSD) ou lab métier sur mesure via la Lab Factory (vf-new-lab) — via une UX guidée. 3 bundles métier disponibles (content / growth / business-pilot — équipes sur le team-kernel).
24 skills · 8 commands
Picks the right payment provider for your project and writes the integration, with deterministic validators that block insecure writes as they happen.
8 skills · 8 commands · 1 agent · hooks
Power Platform Migration Factory skills for modernizing legacy forms and app data sources into Power Apps and Dataverse.
4 skills
Systematic code review using Language Server Protocol tools
1 skill · 1 command
Daemon-based GHCi build status monitor for Haskell projects
2 skills
Daemon-based GHCi build status monitor for Haskell projects, using an MCP server
1 skill · 1 MCP server
Automated eval generation for Power Apps Code Apps and Generative Pages — feature presence checks, unit tests, static security analysis, and an HTML dashboard.
2 skills
Skills to analyze Canvas App performance and quality.
1 skill