mole

does the story check out? — flag answer claims that aren't supported by the provided sources (a lexical grounding check for RAG).

1 skill

call its bluff. — extract the URLs and citations from an answer and check they actually resolve, catching hallucinated links.

1 skill

pull the whole routine. — chain tricks into one pipeline so the output of one flows into the next: `combo "frisk | launder | deadpan"`.

1 skill

the answer. nothing else. — strip LLM replies of personality, filler, hedging, emoji, and sycophancy.

1 skill

know when to fold. — catch overconfident phrasing and absolutes so the model hedges or abstains instead of bluffing.

1 skill

pat it down before it ships. — scan text headed to the model for secrets and PII (API keys, tokens, private keys, emails) and redact or flag them.

1 skill

Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

Claude API and SDK documentation skill for building LLM-powered applications

19 skills

Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.

2 skills · 2 commands · 2 agents · 1 MCP server

Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.

hooks

RuVLLM local inference with chat formatting, MicroLoRA fine-tuning, and SONA adaptation

3 skills · 1 command · 1 agent

Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.

1 skill