Skills Inventory

skills inventory Link to heading

Comprehensive inventory of agentic-development and Claude Code competence, anchored on ten current production works.

Anchor works Link to heading

#WorkWhat it is
1JOBBER (v3 → v4)Go monorepo automating job-listing collection, ingest, and curator-console web UI; msgvault MCP server wired in; Vault-sourced Postgres creds; ~2,937 LOC Go in v4
2md-util (mdu)SHACL-first data-governance CLI (Go, ~10,879 LOC, 13 packages, 8 subcommands, v0.8.0); never moves rows, never executes live DDL
3Nate B. Jones 5-Level PromptingPassed the five-level test — external validation of prompt competence
4Phone UIMobile front-end built with Claude Code — cross-modality fluency
5Southwall + 67 codified skillsHomelab IT maintenance with Claude + Oz — kafka-topic-admin, vault-secret-rotate, pggold-schema-manage, homelab-health-check, netbox-inventory-sync, southwall-dotfiles-sync, and more
6Claude Cowork + LinearAI-assisted CI/CD and PM — Linear MCP for ticket lifecycle, Cowork for collaborative agentic delivery
7Temporal workflowssouthwall-streams, metro-streams, training-streams — deterministic workflow code authored agentically
8Det vs non-det trade-off frameworkArchitectural distinction between where determinism is mandatory (workflows, DDL, money paths) and where non-determinism is acceptable (synthesis, design, exploration)
9Organized prompt library8 promptsets, 377-line XML prompt schema, 173+ lines of session logs
10LMTRAINFirst locally trained small model (nanoGPT, Obsidian-vault character-level checkpoint on MPS)

Claude Code as a platform Link to heading

  • Custom skills. 67 versioned, scoped capabilities across ops, design, QA, debug, deployment
  • Scoped permission profiles. Per-project .claude/settings.local.json allowlisting specific binaries (go test, go build, mdu *, curated git commands)
  • Persistent memory layer. Slug-indexed .md memory files plus MEMORY.md index; reference memories kept hot across sessions
  • MCP servers in production use. Linear (92-ticket cycle), msgvault (JOBBER mail ingest), MotherDuck, claude.ai-hosted (Gmail, Drive, Calendar). Custom MCP wiring, not vendor-default
  • Status-report discipline. .context/status_YYYY-MM-DD_HHMM.md after each step — auditable agent provenance
  • Hooks for session lifecycle. SessionStart hooks for behavior customization (e.g., Ponytail mode)

Skill ladder Link to heading

Must Have — carried Link to heading

SkillEvidence
Claude Code at platform level67 skills, scoped permissions, persistent memory, MCP, hooks
Production agentic buildsmd-util (10,879 LOC), JOBBER (~2,937 LOC), phone UI, Temporal streams
MCP integrationLinear, msgvault, MotherDuck, claude.ai MCPs
Prompt architecture (multi-pattern, meta-prompting)Nate B. Jones 5-level pass; 8 promptsets; 377-line XML schema
HDD–SDD–BDD methodologypractice-docs, interactive Go CLIs, 20,350-line book outline
Det vs non-det trade-off commandmd-util governance-only; Temporal for deterministic side
Schema-first governance for AI-touched dataSHACL 1.2 Turtle, mdu: vocab, multi-target emit
Ops as agentic skillsSouthwall + Oz + 67 skills
Frontier-LLM inference orchestrationClaude Code production loops; Cowork + Linear

Should Have — carried Link to heading

SkillStatus
Vector / memory R&D (Qdrant)Carried
Workflow orchestration (Temporal)Carried
Curriculum / enablement designCarried (Hyperion Master Curriculum + AI 5-section program)
Local-first homelab AI environmentCarried (Vault, Consul, Kafka native on Gold, direnv)
Local model trainingCarried (LMTRAIN / nanoGPT)
Cross-modality delivery (CLI, web, mobile)Carried
Lineage / observability for AI artifactsCarried (md-util DuckDB lineage)

Nice to Have — gaps Link to heading

SkillStatus
Published OSS artifact for the AI workGap (see roadmap)
Conference talk on agentic methodologyGap
Anthropic builder partner credentialGap
Formal eval rig (Inspect / Promptfoo / homegrown)Gap
RLHF / fine-tuning at scaleGap (deliberate; not pursuing)
Multi-agent fan-out (LangGraph / AutoGen / Crew)Gap (Claude Code pipelining covers most use cases)

Fit review Link to heading

Strong signals

  • Volume and variety of production agentic work — ten anchor works spanning CLI, web, mobile, workflow, ops, PM, and model training
  • Operating Claude Code at platform scale — 67 codified skills is a rare signal; custom MCP wiring (JOBBER msgvault) rarer still
  • Externally verified prompt skill — Nate B. Jones 5-level pass is a third-party benchmark
  • Methodology, not just usage — HDD–SDD–BDD codified as a named framework
  • Hands-on with the model end — LMTRAIN closes the “only an inference user” objection
  • Strategic command of det vs non-det — the senior-engineer judgment call
  • 30+ years of DW/BI depth underneath — reviewers don’t have to teach fundamentals

Soft signals (gaps)

  • No public OSS for the AI work — all anchor works are private
  • No frontier-lab employment line — Hyperion / Vertica / Full360 anchor the resume; Anthropic / OpenAI / Databricks do not
  • No conference talk on agentic methodology — presentation-ready but unpresented
  • No formal eval rig named (mitigation: build one against md-util’s dataset-batch loop)

Tools Link to heading

Claude Code (skills, custom MCP, hooks, scoped permissions, persistent memory) · Claude Cowork · Anthropic API · MCP (Linear, msgvault, MotherDuck, custom) · Qdrant · Temporal.io · SHACL 1.2 · DuckDB / DuckLake · Apache Iceberg + AWS Glue · Go (Cobra, pgx/v5, aws-sdk-go-v2, go-duckdb) · Python 3.11 · nanoGPT / PyTorch / MPS · Vault · direnv · Linear · GitLab · OpenMetadata.