20 skills found
opslane / opslaneVerification Layer for Claude Code
shenlian19831109 / progmune-runtimeProgmune Runtime — Program Immunology: A constraint-guided program synthesis runtime for verifiable AI-generated code
petar-nauka / fact-check-skillFact-checking and disinformation detection skill for Claude and Codex
PlaiPin / check-statusROS2 meets OpenClaw 💗
semaj90 / 20-validationlegal ai contextual chat
netresearch / automated-assessment-skillSystematic project assessment against checkpoint-enabled skills with scripted verification + LLM review - by Netresearch
almeidagabriel01 / ai-cost-checkVocê é um assistente de controle de custos de IA para o App Financeiro Pessoal com IA. Analise o uso e custo da Claude API no projeto: Consulte o banco Supabase para métricas de uso: ```sql
NeuralBlitz / climate-science-based-validationAlternative to OpenClaw with OpenClaw Support 👍
nikkoxgonzales / crash-mcpMCP server for structured and efficient reasoning with step validation, branching, and revisions.
Zenobia000 / auto-triz-x1c01Auto-TRIZ closed-loop reasoning framework for e-bike drive unit technical contradiction resolution
cas-bigdatalab / QC3_NumericDataThresholdCheckπflow is a big data flow engine with spark support
wowinter13 / solscan-mcpAn MCP server for querying Solana transactions using natural language with Solscan API
Huaizz-shawen / check-statusOpenclaw + rosclaw + visual feedback
shlomiuziel / asher-mcpA Personal Financial Data MCP Server over the israeli-bank-scrapers package
kaustubhgupta / postgress-mcp-server-claudeInteractive SQL learning playground powered by MCP + PostgreSQL + Claude
Metaworkers-ai / governedmemoryOpen-source governed memory for AI agents: prompt-injection-resistant writes, purpose-bound retrieval, provenance, and tamper-evident audit.
boettiger-lab / mcp-data-serverDuckdb-based MCP server for datasets
Cyptopimpinainteazy / 01-proof-before-claimNo completion claim is valid without proof from actual source, tests, wiring, and command output. - Before saying anything is "done", run the strongest proof command available.
bridge-mind / BridgeWardTrust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, red-flag patterns, refusal templates, and a read-only injection auditor. MIT.
lanveric / clarify-critClarify (CRIT): a portable AI-skill package for request refinement
