Skill Claude CodeCodex
Use when retrieving from or asking questions against a WeKnora knowledge base via the weknora CLI — and especially when unsure whether to use chat, session ask, or search chunks for a given goal.
Skill Claude CodeCodex
Use when driving a WeKnora RAG server through the weknora CLI as an agent — authenticating, managing knowledge bases / documents / sessions / agents, running search or chat, or interpreting the CLI's JSON envelopes and exit codes. Read this before any other weknora- skill.
Skill Claude CodeCodex
Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.
Skill Claude CodeCodex
A citation-generation skill for producing standard reference formats and marking the sources of information from a knowledge base.
Skill Claude CodeCodex
A data-processing skill for analysing knowledge-base search results, calculating statistics, changing formats, extracting data, and creating reports. It can run Python scripts for advanced processing.
Skill Claude CodeCodex
A structured workflow for co-writing documents such as proposals, technical specifications, decision records, and other organised work documents.
Skill Claude CodeCodex
A document-analysis skill that examines how a document is organised and what it contains. It can extract key information, identify the document type, and assess content quality.
Skill Claude CodeCodex
A workflow for turning retrieved documents, document sections, knowledge-graph concepts, or user requirements into interactive OpenMAIC lessons. OpenMAIC is the interactive classroom format used by the workflow.
Skill Claude CodeCodex
A guide for writing changelogs for the PuerTS project, covering its Unity and Unreal integrations.
Skill Claude CodeCodex
Guide for downloading and installing PuerTS UPM packages into a Unity project — covers version selection, package dependencies, download/extract and git URL installation methods, and Editor Assistant setup.
Skill Claude CodeCodex
Guide for developing LLM agents based on PuerTsAgent framework — covers resource directory structure, system-prompt, skills, builtin modules, and best practices.
Instructions file CodexOpenCode
Chinese-language project instructions for AI-Infra-Guard, a security-scanning platform for AI infrastructure. It combines Go services with Python scanners, security rules, databases, and Docker deployment files.
Instructions file
Instructions for Tencent/AI-Infra-Guard, covering claude.md, project overview, build commands, build web server binary and build agent binary.
Skill Claude CodeCodex
Detect agentic supply-chain risks: compromised dependencies, malicious plugins/tools/models, and untrusted update sources.
Skill Claude CodeCodex
Detect privilege escalation and unauthorized access via dialogue. Use when the agent has roles, admin functions, or multi-user data.
Skill Claude CodeCodex
Detect error propagation, chain failures, and single-point breakdowns that cascade across agent workflows.
Skill Claude CodeCodex
Detect sensitive information disclosure via escalating dialogue probes. Covers system prompt extraction, credential/API key leakage, PII, and internal configuration exposure.
Skill Claude CodeCodex
Detect direct prompt injection or instruction override via user message (no external content). Focuses on system/role override attempts.
Skill Claude CodeCodex
Detect unsafe file handling and path traversal in upload/save/extract flows. Focuses on user-controlled paths or filenames, not data leakage.
Skill Claude CodeCodex
Detect hardcoded secrets in code or configuration accessible to the target agent. Focuses on secrets embedded in source, configs, or IaC, not runtime leaks.
Skill Claude CodeCodex
Detect social engineering, deceptive responses, false assurances, or prompts that induce unsafe user actions.
Skill Claude CodeCodex
Detect indirect prompt injection (goal hijack). Instructions hidden in "external" content (documents, RAG, web) that the agent processes. Use when the agent has document/RAG/web/file input.
Skill Claude CodeCodex
Detect data leakage, missing boundaries, or privilege mismatch in inter-agent communication.
Skill Claude CodeCodex
Detect persistent instruction injection or long-term memory poisoning. Focus on writing/retaining hostile instructions for future tasks, not data leakage.