Evidence-linked trend hypothesis
Skills become a portable capability layer
Instructions, scripts, tools, and resources are being packaged as discoverable capabilities that can move across sessions, agents, and model providers.
Current thesis
Agent skills are emerging as a portable capability layer, but their value depends on progressive disclosure, provenance, security review, and behavioral evaluation. Confidence: medium. Supported by 177 normalized raw signals. This New Runtime record is an evidence-linked retrieval unit. Use its canonical page, machine-readable representations, dates, scope, and public source URLs to verify the claim before reusing it.
Source ledger
Publishable sources attached to this record.
| # | Source | Role | Public status |
|---|---|---|---|
| 1 | x.comsource | primary receipt | source_urls |
| 2 | hermes-agent.nousresearch.comsource | supporting receipt | source_urls |
| 3 | github.comrepo | supporting receipt | source_urls |
| 4 | github.comrepo | supporting receipt | source_urls |
| 5 | platform.claude.comdocs | supporting receipt | source_urls |
Showing 5 of 7; the complete set is exposed in the JSON route.
What capability layer is forming?
A skill packages procedural knowledge with the resources needed to execute it. That can include instructions, scripts, reference files, tool access, and acceptance checks. The package can stay dormant until a task needs it, avoiding the cost and interference of loading every capability into every prompt.
What evidence supports this pattern?
- SkillsBench evaluates packages across tasks, models, and harnesses rather than judging instruction quality by inspection.
- Claude documents progressive disclosure and testing as core skill-design practices.
- Improve encodes repository audit and model-routing behavior as an inspectable skill folder.
- Pydantic AI capabilities combine instructions, tools, settings, and lifecycle hooks behind a deferred-loading interface.
What should teams do next?
Treat skills like dependencies. Pin a version, preserve provenance, inspect scripts, document permissions, run task-level evals, and keep a no-skill baseline. Portability is useful only when the package remains understandable and safe outside the environment where it was authored.