eval-lab

Économie de tokens : routage manuel par alias de modèle (model-router), budget estimé (status/analyze/optimize), sortie compressée caveman, handoff de contexte (context-compress), documentation fraîche via Context7 (docs-fresh) ; models.json unique.

6 skills · 3 agents · hooks

Discipline de développement TricorderKit : cadrage (interview-me), protocole spec→plan→sous-agents→tests→ship (dev-protocol), revue adverse (doubt-driven-development), débogage par cause racine, correction/durcissement web OWASP (code-corrector), observabilité des automatisations.

6 skills

Données et graphe TricorderKit : accès normé à Neo4j (MCP officiel, lecture seule par défaut), recherche hybride Qdrant+Neo4j (graphrag-hybrid), scraping adaptatif (Scrapling), veille de changements (changedetection.io + RSSHub).

4 skills

Méta-compétences TricorderKit : gestion et audit de l'écosystème de skills (skill-manager), evals de skills (skill-evals), transformation de documentation en skill (doc-to-skill), orchestration de livrables non-code (head-agent).

4 skills

Sécurité de la surface agent : audit lecture seule de la configuration (MCP, hooks, permissions, secrets en clair, code non épinglé) et compression CLI rtk avec installation épinglée.

2 skills

Forge de CLIs validées pour agents — registre central, scaffolding et manifestes CLI normalisés.

Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.

7 skills · 1 command · 3 agents

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

Install the "AAS QA & Test Automation" editorial skill bundle for Claude Code.

14 skills

Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.

10 skills · 2 commands · 3 agents

45 advanced engineering skills: agent designer, agent workflow designer, RAG architect, database designer + schema designer + SQL assistant, migration architect, observability designer, dependency auditor, changelog generator, API design reviewer, API test suite builder, CI/CD pipeline builder, MCP server builder, skill security auditor, skill tester, performance profiler, focused-fix, browser-automation, full-page-screenshot, git-worktree-manager, monorepo-navigator, codebase-onboarding, interview-system-designer, runbook-generator, spec-driven-workflow, secrets-vault-manager, env-secrets-manager, pr-review-expert, self-eval, tc-tracker, feature-flags-architect, kubernetes-operator, chaos-engineering, ship-gate, slo-architect (error-budget + multi-window burn-rate alerts per Google SRE Workbook), tech-debt-tracker, agent-regression-evals, coding-agent-rollout, commit-craft, agent-run-forensics and i18n-localization. Agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw.

48 skills · hooks

Comprehensive SEO analysis plugin for Claude Code. 26 sub-skills and 19 sub-agents, plus 9 optional MCP extensions. v2.6.0 adds deterministic page, TLS and header, sitemap and JavaScript-gap checks ported from web-obs; v2.5.1 merged 39 community fixes and raised the urllib3 floor for three advisories; v2.5.0 fixed Claude Desktop installs and hardened Google sign-in, page rendering and agent prompts; v2.4.2 added the seo-cockpit companion and gcloud sign-in; v2.4.1 brought Google guidance current through 2026-09-28; v2.4.0 added /seo agentic for agent readiness (Lighthouse Agentic Browsing, WebMCP, AI agent access).

33 skills · 19 agents · hooks