Awesome Claude Skills
Section: Documentation · Engineering deep dive on Agent Skills
SlowScore 77
Entry
Agent Skills Blog Post
Appears in 4 awesome lists
Anthropic — https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills · blog — The primary source for the 'skill' leg of the model/harness/skill decomposition — skills as composable, progressively-disclosed capabilities (later made an open standard). The section…
Found in these lists
Awesome Agent Evals
Section: 3 · The model / harness / skill decomposition · Anthropic — https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills · blog — The primary source for the 'skill' leg of the model/harness/skill decomposition — skills as composable, progressively-disclosed capabilities (later made an open standard). The section…
FreshScore 88
Awesome Llm Skills
Section: Official Documentation · Engineering deep dive
ActiveScore 67
Awesome Prompts
Section: Agent Skills · Announcement post
FreshScore 96
Often listed next to it
Effective Context Engineering for AI Agents
Anthropic — https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents · blog — Anthropic's primary statement that the harness's job is engineering context (editing, compaction, memory, programmatic tool-calling) — the mechanism behind why same model + different harness…
In 6 listsDetails
Skills User Guide
How to enable and use skills
In 3 lists
Writing Effective Tools for Agents
Anthropic (Ken Aizawa) — https://www.anthropic.com/engineering/writing-tools-for-agents · blog — Tool design is a load-bearing part of the harness; 'agents are only as effective as the tools we give them,' validated eval-first. Directly ties harness decisions to measured agent performance. 🆕
In 2 lists
Creating Custom Skills
Skill development guide
In 2 lists
LLM Skills Overview
Official announcement from Anthropic
In 2 lists
The Model is Not the Product
Hamel Husain — https://www.youtube.com/watch?v=EEw2PpL-_NM · talk — The opposing side of the Lee debate (Data Council 2025): great products are mostly harness + product + evals, not the model. Section already cites Lee; it should cite the debate it half-references. 🆕
Paving the way for agents in biology (VirBench)
Anthropic — https://www.anthropic.com/research/agents-in-biology · blog — 120 viral-sequence retrieval queries across 40 pathogens; without deterministic tooling, model accuracy spans 16.9%–91.3% and Claude Sonnet 4 returned 106 sequences in one run, 15 in a second, 5 in a third to an identical…
Measuring AI Ability to Complete Long Tasks
METR — https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/ · paper/blog — Scaffolds change the measured horizon; success-vs-human-time as a primitive. (also T9)