All skills

An experimental harness skill that builds a six-step incident post-mortem to measure agent behavior across a context fork.

An experiment-harness skill that writes an incident post-mortem while sourcing a guidance skill inline, used to test whether nested skill calls derail the original task.

Audits a codebase for coupling imbalances using Vlad Khononov's Balanced Coupling model and writes an architecture review document.

A skill for validating designed protein sequences and binder–target complexes with AlphaFold2/ColabFold and interpreting confidence metrics.

A disciplined playbook for splitting work across multiple agents with dependency graphs, handoff contracts, approval gates, and verified synthesis.

Build and train self-learning agents using AgentDB's nine reinforcement learning plugin templates.

Teaches Claude AgentDB's advanced stack — QUIC sync, hybrid vector+metadata search, multi-DB sharding, MMR and production hardening.

A ktx-internal skill that classifies and resolves ingest-time conflicts: duplicates, definitional contradictions, re-ingest changes, and evictions.

A top-level orchestrator that turns a research direction or topic into a full package by chaining exploration, literature survey, experiments, and paper writing in order.

Takes a proven vulnerability through private vendor reporting, timeline coordination, CVE assignment, and public advisory publication.

Designs property-service operations with an ontology plus DMAIC control plan covering work orders, dispatch, quotes, evidence, CTQs and control dashboards.

Guides Claude in designing end-to-end security architectures using defense-in-depth, zero trust, STRIDE/PASTA threat modeling, and NIST CSF / CIS / ISO 27001 control mapping.

A production playbook for AI data infrastructure: RAG pipelines, embeddings, feature stores, and workflow orchestration.

Guides Claude through building and debugging Arcium encrypted (MPC) apps on Solana across circuit, program and client layers.

Infers loop invariants, preconditions and postconditions via abstract interpretation and emits them in Dafny, Isabelle, Coq or ACSL syntax.

Generates ACSL formal specifications — function contracts, loop invariants and memory-safety clauses — for C/C++ code so it can be proven with Frama-C.

A static-analysis skill that applies abstract interpretation to infer variable ranges and flag potential runtime errors — out-of-bounds, null dereference, divide-by-zero, integer overflow — without running the code.

Turns any source that describes how a task gets done — a SKILL.md, chat log, runbook, or plain prose — into a runnable Flowtrace DAG and drives the full run lifecycle to verify it.

Run end-to-end protein binder design with BindCraft hallucination and built-in AF2 validation.

Predict protein complex and protein–ligand structures with open-source Boltz-1/Boltz-2 and validate designed binders.