rhtevan

rhtevan/agentfs

Skill Claude Code

Regenerate index.md for a skills directory by scanning all SKILL.md files.

rhtevan/agentfs

Skill Claude CodeCodex

Copy project-scoped skills into the shared USER skills directory so they become available across all projects and agents.

rhtevan/agentfs

Skill Claude Code

Create a two-site Skupper Virtual Application Network (VAN) on the Linux/systemd platform using native skrouterd, link the sites with mTLS, and verify end-to-end connectivity using nc (netcat).

rhtevan/agentfs

Skill Claude Code

Expose remote GPU-hosted LLM models to localhost via a Skupper V2 Virtual Application Network. Separates one-time infrastructure setup from daily start/stop operations.

rhtevan/agentfs

Skill Claude CodeCodex

Detect, install, or upgrade the specify CLI (GitHub Spec Kit) via uv tool.

rhtevan/agentfs

Skill Claude Code

Install and manage Apache Jena Fuseki as a local user systemd service with associated CLI tools (riot, shacl, etc.).

rhtevan/agentfs

Skill Claude CodeCodex

Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and…

rhtevan/agentfs

Skill Claude Code

Prevent accidental commit of secrets, PII, hardcoded paths, and stale README content to git repositories. The workflow enforces a two-phase safety model: deterministic scan (script) followed by a mandatory human confirmation gate. This skill absorbs the full Git Push Safety workflow previously inline in AGENTS.md…

rhtevan/agentfs

Skill Claude CodeCodex

Manage the Knowledge Graph Memory (KGM) MCP extension for Goose. KGM provides a deterministic substring-search index over OKF knowledge bundles — it is an optional accelerator, not a replacement for OKF progressive discovery.

rhtevan/agentfs

Skill Claude Code

Audit existing Containerfiles or generate new ones that comply with Red Hat OpenShift security constraints and container certification requirements. Supports three modes targeting different OpenShift SCC models: legacy (restricted-v2, OCP 4.11–4.19), user namespaces (restricted-v3, OCP 4.20+), or both for backward…

rhtevan/agentfs

Hook Claude Code

One of 3 in hooks.json

Runs when you submit a prompt, before the agent sees it for ^[Hh]ey tool calls, executing detect-hey.sh. From rhtevan/agentfs.

rhtevan/agentfs

Hook Claude Code

One of 3 in hooks.json

Runs before the agent uses a tool, executing enforce-hey.sh. From rhtevan/agentfs.

rhtevan/agentfs

Hook Claude Code

One of 3 in hooks.json

Runs when a session starts, executing cleanup-stale.sh. From rhtevan/agentfs.

rhtevan/agentfs

Skill Claude Code

Full behavioral self-audit of session conduct against the agent's rules (AGENTS.md guardrails) and principles (SOUL.md). Unlike agentfs-ctx-chk which audits the context files for structural health, this skill audits the agent's behavior during the current session for compliance violations.

rhtevan/agentfs

Skill Claude Code

Evaluate individual skills against the seven quality principles defined in skill-gen. Runs deterministic checks on structure, scripts, and content, plus optional LLM rubric checks for semantic quality. Produces a severity-graded report per skill.