Browse Skills

Scientific Schematics creates publication-quality scientific diagrams from natural-language prompts. Use it for architecture diagrams, flowcharts, pathways, schematics, and other visuals for papers, posters, and slides.

Add Agent Support delivers maintainable AgentSessions provider support for a new or changed local AI agent or provider. It is used to verify real sessions, build parsers and fixtures, wire discovery and UI surfaces, and document release-ready support.

Agent Support Matrix keeps the agent support matrix and JSON/JSONL tracking current. Use it when checking upstream releases for session format changes and when updating verified version limits, docs, fixtures, or parser tests.

Blind Spot Pass surfaces the unknown unknowns in a domain before you start work, so you can prompt and decide with enough context. Use it when you are new to a field or handing off unfamiliar work and need a brief briefing first.

Claude Code Agent guides Claude Code projects with spec-first planning, context engineering, sub-agents, and post-dev verification. Use it when writing CLAUDE.md or spec.md, dispatching parallel agent work, or running the handoff and docs sync workflow.

Continuous Learning V2 turns Claude Code sessions into atomic instincts using hooks, confidence scoring, and background pattern detection. Use it to capture repeated behaviors and evolve them into skills, commands, or agents.

LLM Evaluation Harness evaluates language models on 60+ academic benchmarks such as MMLU, GSM8K, and HumanEval. Use it to compare models, report results, or track training checkpoints over time.

Prompts And Skills Lookup searches, installs, and improves AI skills and prompts through prompts.chat or the skills.sh CLI. Use it when looking up a skill, installing one, or refining a prompt.

Strategic Compact suggests manual /compact at logical workflow boundaries instead of waiting for arbitrary auto-compaction. Use it to preserve context between planning, implementation, and debugging phases.

Vision Toolkit gives text-only agents tools to inspect images, locate objects, run OCR, compare screenshots, and extract regions. Use it when a task depends on visual evidence instead of text alone.

A Deliverable Is Not an Instruction helps separate research deliverables from harness instructions when building a study plan and checking coverage. Use it to keep `report_plan.json` focused on findings and to mark genuinely unreachable items honestly.

Analyze turns recon output into ranked attack paths, crown-jewel targets, and blind spots for a target. Use it before hunting to decide which endpoints and vulnerability classes to test first.