0xb4bal/specter
SPECTER: Autonomous HTB penetration testing agent — Hermes + DeepSeek V4 Pro. Persistent memory, self-improving skills, Telegram bot, auto IP continuity, flag auto-submit.
SPECTER: Autonomous HTB penetration testing agent — Hermes + DeepSeek V4 Pro. Persistent memory, self-improving skills, Telegram bot, auto IP continuity, flag auto-submit.
npx add-skill 0xb4bal/specterSPECTER: Autonomous HTB penetration testing agent — Hermes + DeepSeek V4 Pro. Persistent memory, self-improving skills, Telegram bot, auto IP continuity, flag auto-submit.
Production-ready Claude Code skills — audit code quality, forge design docs, generate documentation, automate infrastructure. CLI = Command Line Interface + Clement Liard Initials.
Plugin suite + bundled MCP servers for Claude Code. Full delivery lifecycle: Agile pipeline with multi-model AI review, project bootstrap, documentation generation, codebase audits, performance optimization, community workflows. Includes hex-line (hash-verified editing), hex-graph (code knowledge graph), and hex-ssh (remote SSH) MCP servers.
Use when a task is complex, ambiguous, architectural, debugging-oriented, refactoring-heavy, strategic, causal, performance-sensitive, security-sensitive, multi-file, high-impact, or likely to suffer from hallucinated verification. Builds a disk-backed causal workspace before answering, planning, or modifying files; avoid for trivial edits, simple formatting, and direct factual answers.
A collection of Claude Code skills for evaluating LLM applications end-to-end: prompts, RAG pipelines, tool calls, and agents. Built for prompt engineers, AI builders, and teams who want a repeatable loop of "edit → eval → see scores → improve" instead of vibes-based iteration.
Claude skill for generating, reviewing, and improving Moodle quiz questions. Works with Claude Code and Claude Desktop. GIFT, XML, and Aiken formats. Easy, standard, and challenging difficulty modes. Built by a lecturer for lecturers.
MCP-based equity research agent — three FastMCP servers, Claude Code skills, and a standalone CLI mode that produce 8-section interactive HTML research reports.