Shared skills for AI agents (Claude Code, Codex, Gemini)
Skill Claude Code
Verifies relationships between a source text (e.g. Episode, Task) and existing Knowledge Graph lessons. Runs KNN/Hybrid search to find candidates, then uses LLM (scillm) to verify "verifies", "contradicts", or "related" stances with strict rationales.
Skill Claude Code
Dual-backend embedding service for semantic search. Text-only (MiniLM, 384d) and multimodal (Qwen3-VL-Embedding-2B via vLLM, 2048d). Persistent Docker containers with automatic routing by modality.
Skill Claude Code
Read and explain Embry OS configuration from embry.yaml.
Skill Claude CodeCodex
Skill wrapper for the Embry Dashboard (Tauri app). Launch, navigate tabs, and screenshot the dashboard for design review.
Skill Claude CodeCodex
Agent-readable Embry voice control-plane contract for speaking, listening, cancelling, replaying, and inspecting live voice/chat turns. Use when a project agent needs to control Embry Chatterbox voice, RealtimeSTT listener state, shared Chat UX synchronization, memory/Tau routing, orb state, or session replay through…
Skill Claude CodeCodex
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
Skill Claude Code
Episodic Memory Archiver. Stores full conversation transcripts with embeddings and analysis into ArangoDB. Tracks UNRESOLVED sessions for reflection with structured failure episodes (trigger/diagnosis/action/outcome), K4 similar failure retrieval, user behavioral profiling, and federated taxonomy classification.
Skill Claude CodeCodex
Behavioral evaluation of skills using fixture-based test cases. Runs eval.json fixtures per skill to verify correct output, exit codes, latency budgets, and compose chain pipelines. Produces transparent Markdown and JSON reports with diffs for failures. Complements sanity.sh (smoke tests) and skills-ci (static…
Skill Claude CodeCodex
Self-improving evidence case convergence loop. Runs question banks against /create-evidence-case, diagnoses mismatches, and tracks convergence across cycles.
Skill Claude CodeCodex
Live evidence case pipeline viewer with NVIS sentence markup and agent chat well. Shows gates firing, entity grounding, QRA evidence, and verdicts in real-time. Chat well connects to /subagent-service for human-agent course correction.
Skill Claude Code
NIST OSCAL JSON export of compliance evidence from ArangoDB graph.
Skill Claude Code
Extract framework control references from documents and create graph edges to spartacontrols. Supports NIST, CWE, ATT&CK, SPARTA, D3FEND, ISO. 3-tier extraction: regex → RapidFuzz → classifier (future).
Skill Claude Code
Extract control IDs, domain phrases, taxonomy tags, and relationship data from question text. Composes /memory (ArangoDB recall to load spartacontrols vocabulary). Returns structured EntityExtractionResult that defines the shape of evidence cases, conversations, and QRA reviews before any LLM runs. Zero LLM cost …
Skill Claude CodeCodex
Extract structured JSON from HTML using Schematron3B, deterministic table extraction, and Vision-based media OCR.
Skill Claude Code
Self-improving PDF extraction engine. Rust-native via pdfoxide. Replaces PyMuPDF (AGPL) with MIT-licensed extraction: text, blocks, sections, tables, figures, profiling, engineering detection. Shadow-LEGO cascade for automatic quality improvement via predict-extract-verify loop.
Skill Claude Code
Composable PDF table extraction skill. Hybrid Rust+compiled-Python architecture replacing Camelot. Rust hotspots (image processing, geometry) via PyO3, compiled Python parsers (lattice, stream, network, hybrid), pdfoxide for text extraction, polars for output. Shadow-LEGO self-correcting with strategy routing via…
Skill Claude CodeCodex
Persona-driven datalake quality assessment with Margaret Chen (Pratt & Whitney) and Jennifer Cheung (NIWC Pacific). Dynamic annealing thresholds, batch review, and /ask consult integration.
Skill Claude Code
Extract one local document through the canonical Extractor application command. Use when the user says "extract this", "extract pdf", "convert to markdown", "parse this file", "process document", or provides a document.
Skill Claude CodeCodex
Stage cleaned chapter text and extract quote-grounded minimal fact/QRA candidates from source text or primary/context chunks, with streaming model calls, retries, validation, and durable artifacts.
Skill Claude Code
Fetch web pages, PDFs, and documents with automatic fallbacks and content extraction. Use when user says "fetch this URL", "download this page", "crawl this website", "extract content from", "get the PDF", or provides URLs needing retrieval.
Skill Claude Code
Iterative visualization development lab for /create-figure. Compose novel D3 visualizations from primitives (marks, scales, encodings), test rendering, evaluate against user intent, and promote successful compositions to /create-figure as first-class commands. Self-improving: tracks render success, visual fidelity…
Skill Claude CodeCodex
Search a codebase or UI for places that don't animate but should, and reject everything that shouldn't. Read-only; it proposes motion with exact values, it does not implement it. Use when the user asks "what could be animated here?" or wants to "make this feel more alive". For fixing existing animations, use…
Skill Claude Code
Generate adversarial PDF content that breaks extractors. Creates false-positive tables, malformed tables, cursed text, and layout traps. Extensible registry for adding new edge cases discovered from real-world PDFs.
Skill Claude Code
Convert natural language requests into verifiable formal specs using interview loops.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: