Anthropic's Claude Marketplace is live with more than 2,000 connectors and plugins, including ones published by Atlassian, Google, Microsoft and Salesforce. Each connector enabled from it adds a supplier that belongs in third-party and access reviews.
Reality
- Evidence40
- Adoption
- Insufficient
- Hype gap+15
- Incentives60
- Confidence45
Anthropic's open SKILL.md format is read by roughly forty agent tools, among them Codex, Cursor, Copilot and Gemini CLI. Each installed skill costs about 100 tokens a session until a task matches its description and the full workflow loads.
Reality
- Evidence45
- Adoption45
- Hype gap+20
- Incentives
- Insufficient
- Confidence35
Claude Marketplace groups connectors, partner products and consultants in one catalog, and eligible customers can direct part of an existing Anthropic commitment at the software listed there.
Reality
- Evidence52
- Adoption30
- Hype gap+8
- Incentives72
- Confidence60
GitHub's podcast companion post argues that a production authentication refactor and a CSS experiment need different review, and it puts the same conditional test to "RAG is dead" and "Skills killed MCP".
Reality
- Evidence44
- Adoption
- Insufficient
- Hype gap+6
- Incentives58
- Confidence63
Symfony AI Mate deleted its MCP server in August and now exposes profiler data through console commands that SKILL.md files tell the agent to run. The author of the community bundle Mate replaced has deprecated his.
Reality
- Evidence55
- Adoption68
- Hype gap+8
- Incentives55
- Confidence58
A Hook fires on a lifecycle event whether the model agrees or not, while a Skill is pulled in by a per-turn judgement on its description. The exit code that enforces a Hook can also deadlock it.
Reality
- Evidence58
- Adoption
- Insufficient
- Hype gap−5
- Incentives30
- Confidence48
Docs7 takes a Mintlify config, serves Markdown from the URLs agents already request, and counts which AI products fetch what, a metric Context7 itself says measures provider visits rather than readers.
Reality
- Evidence36
- Adoption18
- Hype gap+28
- Incentives80
- Confidence44
Lock-in migrated from the model to the runtime that holds your tool grants, approval rules and learned state. Six specifications aim to make that runtime's contents portable, and half of them are one person's drafts.
Reality
- Evidence36
- Adoption24
- Hype gap+27
- Incentives74
- Confidence42
A commit-crafter tutorial splits judgment from enforcement the right way, but only message formatting makes it inside the deterministic check. The approval gate stays a sentence the model can reinterpret.
Reality
- Evidence58
- Adoption
- Insufficient
- Hype gap+22
- Incentives38
- Confidence52
A developer spent a week on an agent that bumps vulnerable dependencies and repairs the breakage, and the repairs were the easy part; his log of how each failure reported success while being wrong is the useful artifact.
Reality
- Evidence48
- Adoption10
- Hype gap−15
- Incentives55
- Confidence55
One team cut its agent context file to 34KB without deleting a single rule, then wired a size check and a structure test so it cannot quietly regrow.
Reality
- Evidence42
- Adoption22
- Hype gap+12
- Incentives34
- Confidence46
Six vendors agreed on where a plugin's components live. The two specifications that define what those components do sit outside the project, and outside its steering committee.
Reality
- Evidence68
- Adoption55
- Hype gap+15
- Incentives70
- Confidence62
PDF4me's guide wires the same server into five clients using three structurally different config blocks. Get the shape wrong and no client raises an error.
Reality
- Evidence46
- Adoption
- Insufficient
- Hype gap+8
- Incentives68
- Confidence44
Nine of eleven MCP marketplaces accepted proof-of-concept malware with zero review, and a fake agent skill cleared both Cisco's and NVIDIA's scanners to reach roughly 26,000 corporate agents.
Reality
- Evidence24
- Adoption38
- Hype gap+26
- Incentives62
- Confidence30