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 Metadata and annotations are editorial, not peer-reviewed.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.

Equipping agents for the real world with Agent Skills

Anthropic··blog·source
Metadata unverified. URL and title verified; date borrowed from Simon Willison's same-day commentary (2025-10-16) — confirm from the Anthropic post header before citing.
Agent Skills are organized folders of instructions, scripts, and resources that agents can discover and load dynamically to perform better at specific tasks.

Anthropic's engineering announcement of Agent Skills: a markdown-based pattern for extending Claude's capabilities by progressive disclosure. Important as an *institutional* ratification of the thin-harness / fat-skills framing.

Classification

Role
framework-piece
Domain
software
Source type
blog
Harness types
grounding-context-loadingexecution-harnesslearning-harnessratification-harness
Validation position
before-generationduring-generation
Validation mode
empiricalinstitutional
Prescription stance
mixed
Relation to argument
capability-is-extendedfirst-mile-input-formationinstitutions-shape-capabilitydiffusion-adoption-bottleneck
Tags
agent-skillsanthropicprogressive-disclosureinstitutional-launchmarkdown-skills

Extended capability commentary

Input legibility
Task structure
Reward richness
Repairability
Observability
Offline evaluability
Institutional ratification
The model vendor officially blessing the markdown-skill pattern is a ratification event, not only a technical one.

Why it matters

When the model vendor publishes an engineering post describing the pattern, the pattern becomes a point of reference that downstream tooling, hiring, and documentation can anchor on. The library should treat this as institutional ratification of the thin-harness-adjacent thesis.

Annotation

An important entry for the institutions-shape-capability axis. Anthropic's engineering post is not just a feature announcement — it is the moment the markdown-skill pattern gets a canonical, vendor-endorsed framing. That changes what downstream practitioners cite, what conference talks reference, and which designs are considered "default."

Three things to note:

  1. The pattern has been used internally at Anthropic for some time (search snippet: "they now have hundreds of them in production"). The public post is ratification, not invention.
  2. Progressive disclosure — scanning only metadata until a skill is relevant — is a specific design move and deserves to be tracked. It is not just "markdown files"; it is a loading strategy.
  3. Agent Skills and MCP are presented as complementary, not competing. That framing matters for the library's harness_types taxonomy.

Related entries

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.