skills

DE//AGENT currently lists 3 resources under skills: 2 tutorials, 1 reference. Everything below is derived from the live registry — counts, capabilities, verification state and security posture come from the curated records, never from marketing copy.

Documented learning objectives across these resources:

• Install a registry skill and bind an MCP server with least-privilege credentials — via Wire cloud tooling — registry skills, MCP servers, and one review workflow
• Compose skills and MCP servers into a single review workflow — via Wire cloud tooling — registry skills, MCP servers, and one review workflow
• Keep agent access read-only by default — via Wire cloud tooling — registry skills, MCP servers, and one review workflow
• Describe the SKILL.md schema and the directory layout convention — via Inside a skill — SKILL.md, references, examples, the loading protocol
• Evaluate a skill's objectives before you trust it — via Inside a skill — SKILL.md, references, examples, the loading protocol
• Install a registry skill and inspect its files — via Inside a skill — SKILL.md, references, examples, the loading protocol

These resources map to stages: Cloud (1), Agentic Data Engineering (2). Follow the four-phase roadmap to place this topic inside a progression instead of learning it in isolation.

Every entry, its shape and its trust state — sorted by the registry's composite score. This table is the honest version of a marketing comparison: no sponsored placements, no unverifiable claims.

How scores are computed: source quality score.

Highest composite score first:

1. Wire cloud tooling — registry skills, MCP servers, and one review workflow score 34.15 — beginner
2. Inside a skill — SKILL.md, references, examples, the loading protocol score 34.15 — intermediate
3. Agent Skills (open format) score 27.7 — difficulty not documented

Scores rank provenance, completeness and trust — read how verification works before adopting anything.

Start here if you're new: Wire cloud tooling — registry skills, MCP servers, and one review workflow.

• Wire cloud tooling — registry skills, MCP servers, and one review workflow — Wire the registry's cloud tooling into one agent workflow: install the Glue and Athena review skills, bind the AWS MCP server to a least-privilege profile, and compose both skills … details
• Inside a skill — SKILL.md, references, examples, the loading protocol — A skill is the unit of reusable agent behavior: one SKILL.md with front-matter, plus directories the agent loads on demand. Dissect a real registry skill file by file, learn the ev… details
• Agent Skills (open format) — The Agent Skills format specification — a SKILL.md file with front-matter (name, description, version), plus references/, scripts/, and examples/ directories that an agent loads on… details

Adjacent topics: tutorial (2 shared), agentic (2 shared), format (2 shared).

Study path: the roadmap places this topic in a progression · the scoring model explains the numbers · the trust rule catalog shows every security check these entries passed through.