III · Tool Use & EnvironmentEmerging★

Agent Skills

also known as Author-Time Procedures, Slash Commands, Agent Rules

Package author-time procedures (markdown + optional resources) the agent loads on demand for specific task types.

Context

A team is shipping an agent product that handles many distinct recurring workflows. The same agent might process refunds, change addresses, schedule appointments, and answer policy questions, each with its own multi-step procedure that the engineering or operations team has already worked out and wants the agent to follow consistently.

Problem

Stuffing every workflow into one system prompt pushes context past tens of thousands of tokens and the agent still skips steps or blends procedures together. The alternative of dropping ad-hoc prompt files into the repository leaves the team with no clean way to version, review, or roll back individual procedures, and no clear story for how the agent decides which one applies to the current task.

Forces

  • Discovery: how does the agent know which skill applies?
  • Versioning of authored procedures.
  • Skill quality bounds agent quality on the relevant workflow.

Example

A customer-support agent now handles refunds, address changes, subscription pauses, and SIM swaps. Cramming every workflow into the system prompt has pushed it past 18k tokens and the agent still skips steps. The team breaks each workflow into an Agent Skill — a markdown file with the procedure plus a few example dialogues — that the agent loads on demand once the user's intent is classified. The base prompt shrinks; only the relevant procedure enters context for that conversation.

Diagram

Solution

Therefore:

Package each procedure as a markdown file (and optional companion resources) under a known directory. The agent loads relevant skills on demand based on the current task. Skills are author-time artefacts versioned with the agent.

What this pattern forbids. The agent operates within the procedure of the loaded skill; ad-hoc deviation is forbidden when a skill is active.

And the patterns that stand alongside it, or against it —

  • alternative-toSkill Library★— Let the agent grow its own toolkit by writing reusable skills that subsequent runs can call.
  • complementsDynamic Scaffolding★— Inject task-specific scaffolding (examples, hints, schemas) into the prompt only when the task type warrants it.
  • complementsSpec-First Agent★— Drive the agent loop from a human-authored specification document rather than free-form prompts.
  • complementsToolformer✕— Train the model to learn when and how to call tools through self-supervised data, without human annotation.
  • complementsDSPy Signatures★— Specify agent behaviour as declarative typed signatures and modules; compile prompts and few-shot examples automatically against a metric.
  • alternative-toPrompt Bloat✕— Anti-pattern: every bug fix adds a sentence to the system prompt; nothing is ever removed.
  • complementsAgent Persona Profile★— Treat agent identity as a structured profile object — persona, primary motivator, allowed actions, knowledge bindings — rather than a free-form role sentence in the system prompt.
  • complementsHierarchical Tool Selection★— Organise tools into a tree of categories so the agent first picks a branch and then a specific tool within it.
  • complementsTool Transition Fusion·— Mine tool-call telemetry for high-probability X-then-Y transitions and fuse those pairs into a single composite tool, shrinking the planner's step count.

Neighbourhood

Click any neighbour to follow the language. Scroll to zoom, drag to pan.

Used in recipes

Used in frameworks

References

Provenance