# The Dark Arts of Skill Engineering — Paul Bakaus, Renaissance Geek (Impeccable)

Source: [AI Engineer](https://www.youtube.com/watch?v=SQMCtZX3trg)  
Feed7 permalink: https://feed7.dev/p/the-dark-arts-of-skill-engineering-paul-bakaus-renaissance-geek-impeccab-1athv5b  
Published: 2026-09-21T19:00:10.000Z  
Trust: Source Linked (source_linked)

## Why Included

Reliable agent skills need more than prompts: use hooks as automatic guardrails, test across models, and compile harness-specific variants when instruction-following differs.

## Source Summary

Impeccable grew from a normalization prompt into a design skill with **two-agent critiques**, scripts and design hooks. Its hooks support Claude Code, Cursor, Codex and GitHub Copilot, while model- and harness-specific builds adjust instructions and tool syntax.

## Practical Implication

Treat skills as executable harness components. Put recurring checks into **pre-tool or post-tool hooks**, personalize them with project rules, and test each target model instead of assuming one prompt behaves consistently everywhere.

## Agent-Ready Context

Impeccable grew from a normalization prompt into a design skill with **two-agent critiques**, scripts and design hooks. Its hooks support Claude Code, Cursor, Codex and GitHub Copilot, while model- and harness-specific builds adjust instructions and tool syntax.

Treat skills as executable harness components. Put recurring checks into **pre-tool or post-tool hooks**, personalize them with project rules, and test each target model instead of assuming one prompt behaves consistently everywhere.

Pre-tool blocking may be necessary for weaker instruction followers, but it is more restrictive. Cross-harness packaging also remains fragmented: common installers do not preserve Impeccable's provider-specific directory layout, so it uses a custom CLI.

## Connected Context

Feed7 judgment across 843 accumulated Signals:

This sharpens skill engineering from prompt writing into software maintenance: recurring checks can live in hooks, critiques can use multiple agents, and each model or harness may need its own instructions and tool syntax. Portability therefore requires target-specific testing and packaging; stricter pre-tool enforcement may improve compliance but also constrains execution.

- [On the Maintenance and Co-evolution of Agent Plugins: An Empirical Study of Claude Code Plugin Marketplaces](https://feed7.dev/p/2608-28497v1-1mlcj09) — The marketplace study provides ecosystem-scale support for treating skills as evolving software whose instructions and scripts require coordinated maintenance, matching Impeccable’s hooks, scripts, and provider-specific builds.
- [WorldFlowAI/everything-claude-code](https://feed7.dev/p/everything-claude-code-11d9320) — The harness kit demonstrates the same combination of skills, hooks, subagents, rules, and evals, while its context warning reinforces selective adoption rather than enabling every component.
- [Agents Are Where Microservices Were in 2015 — Roberto Milev & Uday Kanagala, Navan](https://feed7.dev/p/agents-are-where-microservices-were-in-2015-roberto-milev-uday-kanagala-1pk4hle) — Navan’s independently testable skills and tool-boundary guardrails reinforce Impeccable’s use of hooks and per-target testing, while adding persistence, traces, and trajectory tests as production requirements.
- [Coding Agents Don't Scale Themselves. Neither Do Your Teams. — Patrick Debois, Tessl](https://feed7.dev/p/coding-agents-don-t-scale-themselves-neither-do-your-teams-patrick-deboi-1tkeyjb) — Impeccable exposes the provider-specific maintenance burden behind shared skills; the team-systems view makes curation, evaluation, and guardrail ownership an organizational consequence of that burden.

## Context Map

- Layer: agent
- Domains: coding
- Topics: skills, harness-engineering, subagents

## Uncertainty

- Pre-tool blocking may be necessary for weaker instruction followers, but it is more restrictive. Cross-harness packaging also remains fragmented: common installers do not preserve Impeccable's provider-specific directory layout, so it uses a custom CLI.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.