Open Brain
AI EngineerVideoSource Linked

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

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

AI Engineer · Sep 21, 2026
Open Source Open MarkdownOpen JSON
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

Impeccable sharpens skills from reusable instructions into provider-specific executable harness packages: critiques, hooks, scripts, and blocking behavior must be adapted and tested per model. This conflicts with assumptions that one portable prompt or generic installer is enough, while reinforcing that stronger enforcement increases restriction and maintenance burden.

On the Maintenance and Co-evolution of Agent Plugins: An Empirical Study of Claude Code Plugin MarketplacesImpeccable’s coupled instructions, scripts, hooks, and provider builds exemplify the study’s finding that skill files and executable components require coordinated maintenance.WorldFlowAI/everything-claude-codeBoth treat hooks, skills, and subagents as harness components, but Impeccable adds evidence that selective adoption must also account for model-specific syntax and enforcement behavior.Agents Are Where Microservices Were in 2015 — Roberto Milev & Uday Kanagala, NavanPre- and post-tool hooks provide the candidate’s tool-boundary guardrails, while per-model testing supplies a practical prerequisite for treating skills as independently reliable components.Coding Agents Don't Scale Themselves. Neither Do Your Teams. — Patrick Debois, TesslFragmented packaging and provider-specific variants create the curation and ownership work that the candidate assigns to a shared agent platform rather than individual prompt authors.
Context Map
agentcoding#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.