---
schema: 1
type: video
title: 'Building Great Agent Skills: The Missing Manual'
description: >-
  Let's discuss how to navigate "skill hell" by providing a structured framework
  for building high-quality agent skills. Without a shared rubric, developers
  and organizations struggle to create effective, maintainable skills for AI
  agents. Timestamps: 0:00 - Introduction to the talk and the concept of "skill
  hell" 2:12 - Overview of the skill checklist framework 3:16 - Trigger:
  Choosing between user-invoked and model-invoked skills 7:29 - Structure:
  Organizing steps and references 9:00 - Making the skill.md file minimal 11:54
  - Steering: Using leading words to guide agent behavior 14:56 - Increasing
  "leg work" per step 16:48 - Pruning: Removing sediment, crud, and no-ops 19:06
  - Final summary of the checklist framework 19:55 - Where to find the "writing
  great skills" resource The Skill Checklist Framework: Trigger (3:16 - 7:25):
  Decide whether a skill should be user-invoked or model-invoked. Matt notes
  that while model-invoked skills offer more flexibility, they increase context
  load and introduce unpredictability. User-invoked skills offer more control
  but require greater cognitive load from the pilot. Structure (7:29 - 11:53):
  Organize your skill into two primary units: steps (procedures) and reference
  (supporting information). To keep the skill.md file minimal, move branching
  reference material behind context pointers to reduce bloat and maintenance
  costs. Steering (11:54 - 16:47): Use leading words—specific terms that pack
  dense meaning—to influence agent behavior and guide reasoning traces.
  Additionally, you can force the agent to perform more "leg work" on specific
  tasks by breaking complex processes into smaller, individual skills that hide
  future steps. Pruning (16:48 - 19:05): Maintain a clean skill set by ensuring
  a single source of truth, removing "sediment" (irrelevant legacy material),
  and eliminating "no-ops" (instructions that don't actually change agent
  behavior).
  https://github.com/mattpocock/skills/blob/main/skills/productivity/writing-great-skills/SKILL.md
  --- Watch along with the corrected transcript, summary, timestamps and
  resources on this talk's official AIE page:
  https://ai.engineer/talks/UNzCG3lw6O0-building-great-agent-skills Join our
  upcoming AI Engineer conferences (see https://ai.engineer landing page): -
  AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and
  engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference
  returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS
  2026 in Sydney ---
canonical: >-
  https://liquidgold.cc/channel/aidotengineer/explore/video/building-great-agent-skills-the-missing-manual-26939d720db0
markdown: >-
  https://liquidgold.cc/channel/aidotengineer/video/building-great-agent-skills-the-missing-manual-26939d720db0.md
llms: null
parent: 'https://liquidgold.cc/channel/aidotengineer.md'
channel: aidotengineer
updated: '2026-10-24T08:50:29.206Z'
language: null
children: []
videoId: UNzCG3lw6O0
durationSeconds: 1243
publishedAt: '2026-06-29T18:53:10.000Z'
searchChunks:
  - ordinal: 0
    text: null
    startSeconds: 11
    endSeconds: 142
    watch: 'https://liquidgold.cc/watch/UNzCG3lw6O0?t=11'
    heldReason: rights
  - ordinal: 1
    text: null
    startSeconds: 11
    endSeconds: 142
    watch: 'https://liquidgold.cc/watch/UNzCG3lw6O0?t=11'
    heldReason: rights
  - ordinal: 2
    text: null
    startSeconds: 11
    endSeconds: 142
    watch: 'https://liquidgold.cc/watch/UNzCG3lw6O0?t=11'
    heldReason: rights
  - ordinal: 3
    text: null
    startSeconds: 152
    endSeconds: 196
    watch: 'https://liquidgold.cc/watch/UNzCG3lw6O0?t=152'
    heldReason: rights
  - ordinal: 4
    text: null
    startSeconds: 207
    endSeconds: 457
    watch: 'https://liquidgold.cc/watch/UNzCG3lw6O0?t=207'
    heldReason: rights
  - ordinal: 5
    text: null
    startSeconds: 207
    endSeconds: 457
    watch: 'https://liquidgold.cc/watch/UNzCG3lw6O0?t=207'
    heldReason: rights
  - ordinal: 6
    text: null
    startSeconds: 207
    endSeconds: 457
    watch: 'https://liquidgold.cc/watch/UNzCG3lw6O0?t=207'
    heldReason: rights
  - ordinal: 7
    text: null
    startSeconds: 468
    endSeconds: 545
    watch: 'https://liquidgold.cc/watch/UNzCG3lw6O0?t=468'
    heldReason: rights
  - ordinal: 8
    text: null
    startSeconds: 468
    endSeconds: 545
    watch: 'https://liquidgold.cc/watch/UNzCG3lw6O0?t=468'
    heldReason: rights
  - ordinal: 9
    text: null
    startSeconds: 555
    endSeconds: 718
    watch: 'https://liquidgold.cc/watch/UNzCG3lw6O0?t=555'
    heldReason: rights
  - ordinal: 10
    text: null
    startSeconds: 555
    endSeconds: 718
    watch: 'https://liquidgold.cc/watch/UNzCG3lw6O0?t=555'
    heldReason: rights
  - ordinal: 11
    text: null
    startSeconds: 555
    endSeconds: 718
    watch: 'https://liquidgold.cc/watch/UNzCG3lw6O0?t=555'
    heldReason: rights
  - ordinal: 12
    text: null
    startSeconds: 730
    endSeconds: 900
    watch: 'https://liquidgold.cc/watch/UNzCG3lw6O0?t=730'
    heldReason: rights
  - ordinal: 13
    text: null
    startSeconds: 730
    endSeconds: 900
    watch: 'https://liquidgold.cc/watch/UNzCG3lw6O0?t=730'
    heldReason: rights
  - ordinal: 14
    text: null
    startSeconds: 730
    endSeconds: 900
    watch: 'https://liquidgold.cc/watch/UNzCG3lw6O0?t=730'
    heldReason: rights
  - ordinal: 15
    text: null
    startSeconds: 912
    endSeconds: 1016
    watch: 'https://liquidgold.cc/watch/UNzCG3lw6O0?t=912'
    heldReason: rights
  - ordinal: 16
    text: null
    startSeconds: 912
    endSeconds: 1016
    watch: 'https://liquidgold.cc/watch/UNzCG3lw6O0?t=912'
    heldReason: rights
  - ordinal: 17
    text: null
    startSeconds: 1027
    endSeconds: 1148
    watch: 'https://liquidgold.cc/watch/UNzCG3lw6O0?t=1027'
    heldReason: rights
  - ordinal: 18
    text: null
    startSeconds: 1027
    endSeconds: 1148
    watch: 'https://liquidgold.cc/watch/UNzCG3lw6O0?t=1027'
    heldReason: rights
  - ordinal: 19
    text: null
    startSeconds: 1027
    endSeconds: 1148
    watch: 'https://liquidgold.cc/watch/UNzCG3lw6O0?t=1027'
    heldReason: rights
  - ordinal: 20
    text: null
    startSeconds: 1148
    endSeconds: 1158
    watch: 'https://liquidgold.cc/watch/UNzCG3lw6O0?t=1148'
    heldReason: rights
---


# Building Great Agent Skills: The Missing Manual

Let's discuss how to navigate "skill hell" by providing a structured framework for building high-quality agent skills. Without a shared rubric, developers and organizations struggle to create effective, maintainable skills for AI agents. Timestamps: 0:00 - Introduction to the talk and the concept of "skill hell" 2:12 - Overview of the skill checklist framework 3:16 - Trigger: Choosing between user-invoked and model-invoked skills 7:29 - Structure: Organizing steps and references 9:00 - Making the skill.md file minimal 11:54 - Steering: Using leading words to guide agent behavior 14:56 - Increasing "leg work" per step 16:48 - Pruning: Removing sediment, crud, and no-ops 19:06 - Final summary of the checklist framework 19:55 - Where to find the "writing great skills" resource The Skill Checklist Framework: Trigger (3:16 - 7:25): Decide whether a skill should be user-invoked or model-invoked. Matt notes that while model-invoked skills offer more flexibility, they increase context load and introduce unpredictability. User-invoked skills offer more control but require greater cognitive load from the pilot. Structure (7:29 - 11:53): Organize your skill into two primary units: steps (procedures) and reference (supporting information). To keep the skill.md file minimal, move branching reference material behind context pointers to reduce bloat and maintenance costs. Steering (11:54 - 16:47): Use leading words—specific terms that pack dense meaning—to influence agent behavior and guide reasoning traces. Additionally, you can force the agent to perform more "leg work" on specific tasks by breaking complex processes into smaller, individual skills that hide future steps. Pruning (16:48 - 19:05): Maintain a clean skill set by ensuring a single source of truth, removing "sediment" (irrelevant legacy material), and eliminating "no-ops" (instructions that don't actually change agent behavior). https://github.com/mattpocock/skills/blob/main/skills/productivity/writing-great-skills/SKILL.md --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/UNzCG3lw6O0-building-great-agent-skills Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney ---

Canonical: https://liquidgold.cc/channel/aidotengineer/explore/video/building-great-agent-skills-the-missing-manual-26939d720db0 · Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md)

> Search chunk text is held until public-source provenance is verified.

## Document chunks

> Missing: no stored document chunks are available.
