---
id: "concept-procedural-vs-ability-skills"
type: "concept"
source_timestamps: ["00:17:04", "00:20:02"]
tags: ["agent-design", "prompt-engineering"]
related: ["claim-procedural-over-abilities", "contrarian-disable-model-skills", "entity-matt-pocock-skills"]
definition: "The difference between skills invoked autonomously by the model (abilities) and skills explicitly triggered by the human (procedures)."
---
# Procedural vs. Ability Agent Skills

## The two skill types

When designing custom skills for AI agents, [[entity-matt-pocock|Pocock]] categorizes them into two distinct types:

**Abilities** are skills the model is empowered to invoke autonomously during its execution loop. Example: an agent might have an ability to check React coding standards whenever it writes a component. The model decides *when* to use it.

**Procedures** are skills explicitly invoked by the human user — typically as slash commands — to force the model into a specific behavior or workflow. A prime example is Pocock's `grill-me` skill, which turns the AI into an adversarial interviewer to stress-test a product plan before any code is written.

## Pocock's preference

Pocock strongly prefers **procedural skills** because they keep the human developer in the driver's seat. He actively *disables* the model's ability to invoke certain skills autonomously, preventing the AI from hallucinating workflows or wasting tokens on unprompted actions. This is the basis for:

- [[claim-procedural-over-abilities]] — procedural skills beat autonomous abilities.
- [[contrarian-disable-model-skills]] — disable model autonomy for better results.
- [[action-blank-slate-agents]] — start agents with a blank slate, adding only specific procedural skills as needed.

## Where the skills live

Pocock's procedural skill library is at [[entity-matt-pocock-skills]]. Notable procedures include `teach` (see [[concept-stateful-learning-skills]]), `grill-me`, and `setup-matt-pocock-skills`.

## Philosophy

This philosophy centers on using AI as a **powerful tool guided by human strategic intent**, rather than a fully autonomous black box. It aligns with the broader thesis that strategic human control over the [[concept-ai-harness|harness]] is more valuable than maximizing model autonomy.

## Counter-perspective

In high-volume, low-risk environments (internal tools, batch pipelines), autonomous tool-use frameworks like AutoGen, LangGraph, and ReAct-style planners can be more efficient. Pocock's preference is normative and context-dependent — strongest in safety-critical or human-reviewed software engineering, weakest in exploratory or research settings.