--- type: "post" id: "state-of-agent-skills-analysis-5ce9ff" slug: "state-of-agent-skills-analysis-5ce9ff" title: "State of agent skills" description: "The early agent-skills market is becoming a distribution market for reusable operational judgment, not merely a larger library of prompts." retrieval_nugget: "The early agent-skills market is becoming a distribution market for reusable operational judgment, not merely a larger library of prompts." published_at: "2026-09-25" updated_at: "2026-09-25" record_date: "2026-09-25" date_kind: "published_at" topics: [] source_urls: ["https://vercel.com/blog/state-of-agent-skills"] schema_version: "newruntime-agent-readable-v0.2" stable_id: "post:state-of-agent-skills-analysis-5ce9ff" status: "published" visuals: [] editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:58f5a269fdd6baad6e8528ce134bf2a6e460f338a3a6928030288d5efa318a43","reviewed_at":"2026-09-25T17:03:54.891Z","source_evidence_count":1,"verified_claim_count":3,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":3,"implication_count":2,"watch_condition_count":2,"related_record_count":0} analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"The early agent-skills market is becoming a distribution market for reusable operational judgment, not merely a larger library of prompts.","observed_facts":[{"text":"Vercel reports that skills.sh reached one million listings and nearly 280 million installs in seven months.","source_urls":["https://vercel.com/blog/state-of-agent-skills"]},{"text":"Vercel reports that 375 skills, representing 0.04% of the registry, account for 62% of installs.","source_urls":["https://vercel.com/blog/state-of-agent-skills"]},{"text":"Vercel’s classified dataset assigns 14.8% of installs to agent workflows and automation.","source_urls":["https://vercel.com/blog/state-of-agent-skills"]}],"mechanism":"The mechanism is portability: a skill that teaches planning, routing, tool use, or browser automation can improve many different tasks, while a narrowly scoped job skill has a smaller addressable audience.","why_now":"The report matters now because the catalog has passed a scale at which discovery and quality selection, rather than raw supply, become central constraints.","implications":["The implication is that organizations should treat public skills as baseline infrastructure and reserve their differentiating effort for codifying company-specific decisions.","Skill marketplaces may increasingly compete on evaluation, maintenance, and discovery rather than listing growth alone."],"evidence_boundary":"The evidence boundary is important: the report uses Vercel’s aggregate registry counters and a classified sample, so installs do not equal unique users, independent adoption decisions, or verified task outcomes.","watch_conditions":["Watch whether maintainers and organizations begin publishing comparable skill evaluations that measure task success, reliability, and regressions rather than installation volume.","Watch whether proprietary company skills gain adoption through governance and integration rather than public-market install counts."],"related_records":[],"new_branch_reason":"This is a distinct analytical record because no prior New Runtime record was supplied, and the source introduces a registry-scale measurement of skill-market structure and adoption concentration."} editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]} routes: {"html":"https://newruntime.com/posts/state-of-agent-skills-analysis-5ce9ff/","markdown":"https://newruntime.com/posts/state-of-agent-skills-analysis-5ce9ff.md","json":"https://newruntime.com/posts/state-of-agent-skills-analysis-5ce9ff.json"} --- # State of agent skills ## Retrieval answer The early agent-skills market is becoming a distribution market for reusable operational judgment, not merely a larger library of prompts. The early agent-skills market is becoming a distribution market for reusable operational judgment, not merely a larger library of prompts. Vercel reports that skills.sh reached one million listings and nearly 280 million installs in seven months. Its classified dataset puts agent workflows and automation at 14.8% of installs, second to software engineering, while 375 skills—0.04% of the registry—account for 62% of installs. It also reports that cross-industry skills represent 87.5% of installs in the classified sample. These are registry-level signals, not a census of all agent deployments. The mechanism is portability: a skill that teaches planning, routing, tool use, or browser automation can improve many different tasks, while a narrowly scoped job skill has a smaller addressable audience. This makes reusable workflow knowledge compound through installation and through its role in helping agents create more skills. The report matters now because the catalog has passed a scale at which discovery and quality selection, rather than raw supply, become central constraints. The implication is that organizations should treat public skills as baseline infrastructure and reserve their differentiating effort for codifying company-specific decisions. Popularity alone will be an incomplete quality signal; Vercel argues that skills will need tests showing whether an agent performs better with the skill than without it. The evidence boundary is important: the report uses Vercel’s aggregate registry counters and a classified sample, so installs do not equal unique users, independent adoption decisions, or verified task outcomes. Watch whether maintainers and organizations begin publishing comparable skill evaluations that measure task success, reliability, and regressions rather than installation volume. Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json ## Continue in the graph Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`. - collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis. - collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph. - whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)