Daniel's personal website

This library entry is part of The Extended Frontier thesis. Entries are curated with AI assistance and human review; most initial entries were prepared with Claude (Anthropic), while individual entries may note other assisting systems. Metadata and annotations are editorial, not peer-reviewed. Entries flagged as unverified may contain placeholder dates, authors, or classifications.

Claude Skills are awesome, maybe a bigger deal than MCP

Simon Willison··blog·source
A skill is a Markdown file telling the model how to do something, optionally accompanied by extra documents and pre-written scripts.

Practitioner synthesis of Anthropic's Agent Skills feature, arguing the markdown-file pattern is conceptually simpler and more token-efficient than MCP, and that the ease of sharing a single file is the feature.

Classification

Role
synthesis-node
Domain
software
Source type
blog
Harness types
grounding-context-loadingexecution-harnesslearning-harnesssocial-harness
Validation position
before-generation
Validation mode
empirical
Prescription stance
mixed
Relation to argument
capability-is-extendedfirst-mile-input-formationdiffusion-adoption-bottleneck
Tags
agent-skillsmarkdown-skillsmcpprogressive-disclosuretoken-efficiency

Extended capability commentary

Input legibility
Progressive disclosure — scan metadata, load full skill on demand — is a legibility pattern.
Task structure
Reward richness
Repairability
Observability
Offline evaluability
Institutional ratification
Distribution is social: skills spread as shareable markdown files, not packaged tools.

Why it matters

Makes visible the argument that the markdown-skill pattern is a diffusion mechanism, not only a technical one. Pair with Tan (thin harness) and Anthropic's engineering post to triangulate what 'skills' actually refer to.

Annotation

Willison argues two things at once:

  1. Conceptual simplicity beats MCP. A skill is a markdown file; the model knows how to read markdown; a CLI tool with --help solves most of what an MCP server solves, at a fraction of the token budget.
  2. Distribution is the feature. Many skills are a single file. The shareability is the point — skills spread.

Read as a synthesis node that connects:

Related entries

Overlap is computed on tags, relation-to-argument, and harness types — not on role or domain, because contrasts are often the most useful neighbours.