Local only
On this device
0 / 13 proofs · 0%
Part II · Compounding harness · 09

Skills

On-demand procedural memory — not a second system-prompt dump.

20 min
Skills path
01
Catalog
Names only
02
Select
Right skill
03
Body loads
Procedure
04
Run
Proof file

What a skill is

A skill is a reusable instruction package (SKILL.md). Front matter names and describes it; the body teaches the procedure. Hermes sees names and descriptions first — a vague description means the right skill may never load.

Skills use progressive disclosure: the catalog stays cheap; only the selected body enters the prompt. That is how a large library avoids burning the context window every turn.

  • ·Skill = procedure / knowledge package (agentskills-compatible).
  • ·Plugin / MCP = executable surface or product hooks — a different layer.
  • ·Slash commands (for example /plan) and /learn can capture workflows as skills when supported.
  • ·Install narrowly; run security scans on hub skills before trust.
  • ·Pin or curator: critical skills should not vanish to automated cleanup when you outgrow defaults.

Desktop first

Steps · tap to check0/4
If every skill is enabled, the model spends tokens choosing rather than working. Least privilege. Skills Hub is a map, not homework.

Skills tax the fixed budget

The skills index and every enabled tool schema load into the empty-session budget (see module 06 — prompt-size). A large “install for later” catalog costs tokens before any task starts.

Steps · tap to check0/3

Proof

Checklist · this device0/4
Proof of completion

You listed skills for this profile, ran or inspected one, and wrote skills-notes.md with name and when to use it.

Proof · this device0/1

Stored on this device only — not sent anywhere.