Context7 vs Agent Skills
Updated : the last week a score, rank or safety result on this page changed.
- Maintenance 30%6712
- Adoption 30%3984
- Docs 20%6969
- Community 20%, not measured yet––
Context7 scores 4 points higher. Context7 leads on maintenance; Agent Skills leads on adoption.
What this does not tell you
Scores are percentiles of public GitHub signals. Nobody here tested these tools hands-on, so the higher score is not a verdict on which suits your project. Yellow marks the higher value.
Which one fits you
From measured data and licences, not from testing.
Pick Context7 if
- Recent activity and releases matter most to you (maintenance 67).
- You need a permissive open-source licence (MIT).
- You want to run it on your own machine (local install found in the README).
Pick Agent Skills if
- You want the more widely adopted option (adoption 84).
- You want the tool whose automated scan found no issues.
Safety side by side
Automated scan, 2 Nov 2026. Not a manual audit.
- CautionContext72 critical-severity known vulnerabilities in runtime dependencies (OSV)
- No issues foundAgent SkillsNo issues found in this week’s scan
Why different labels?
A label partly reflects how much of each tool is visible and scannable, not only how risky it is. A tool without a lockfile cannot get a dependency check.
- Context7: 2 critical-severity known vulnerabilities in runtime dependencies (OSV)
- Agent Skills: no issues found
Repo facts
Yellow = the higher value, where higher is better.
| Fact | Context7 | Agent Skills |
|---|---|---|
| Score | 57 | 53 |
| Stars | 64,060 | 186,457 |
| Last push | 1 Nov | 28 Oct |
| Releases, 90 days | 10+ | 0 |
| Licence | MIT | Apache-2.0 + proprietary |
| Open source | Open source | Mixed license (Apache-2.0 + proprietary) |
| Language | TypeScript | Python |
| Type | MCP server | Agent skill |
| Runs locally | yes | unknown |
| Hosted option | unknown | unknown |
“Runs locally” and “Hosted option” are read from each README automatically (or from the official docs where noted); “unknown” means no evidence was found, not that it is absent.
Questions about Context7 vs Agent Skills
Answers use this week's StackGrade data.
Context7 or Agent Skills: which scores higher on StackGrade?
Context7 scores 4 points higher in Week 45: Context7 57, Agent Skills 53 out of 100. The score combines maintenance, adoption and docs (percentiles of public GitHub signals): Context7 67, 39 and 69; Agent Skills 12, 84 and 69. Community (20% weight) is not measured yet. It is not a hands-on test, so a higher score does not say which tool suits your project.
Is Context7 or Agent Skills safer to use?
Safety labels from the automated scan of 2 Nov 2026: Context7: Caution, 2 critical-severity known vulnerabilities in runtime dependencies (OSV); Agent Skills: No issues found, no issues found in this week’s scan. It is an automated scan, not a manual audit.
Which is more widely used, Context7 or Agent Skills?
By GitHub stars: Agent Skills 186,457, Context7 64,060. Adoption score (percentile among all 52 tracked tools): Context7 39, Agent Skills 84. Stars are one public signal and do not measure real-world use.
Which licences do Context7 and Agent Skills use?
Context7: MIT; Agent Skills: Apache-2.0 + proprietary. Read each licence text before commercial use.
Should I pick Context7 or Agent Skills?
Pick Context7 if recent activity and releases matter most to you (maintenance 67); you need a permissive open-source licence (MIT); you want to run it on your own machine (local install found in the README). Pick Agent Skills if you want the more widely adopted option (adoption 84); you want the tool whose automated scan found no issues. This comes from measured public data and licences only, not from hands-on testing.
Full comparison table, every criterion
| Context7upstash/context7 | Agent Skillsanthropics/skills | |
|---|---|---|
| Score | 57 | 53 |
| Rank | #19 overall · #2 in use case | #25 overall · #3 in use case |
| Maintenance (30%) | 67 | 12 |
| Adoption (30%) | 39 | 84 |
| Docs (20%) | 69 | 69 |
| Community (20%) | not measured | not measured |
| Safety | Caution
| No issues found |
| License | MIT | Apache-2.0 + proprietary |
| Open source | Open source | Mixed license (Apache-2.0 + proprietary) |
| Language | TypeScript | Python |
| Stars | 64,060 | 186,457 |
| Last push | ||
| Type | MCP server | Agent skill |
| Runs locally | yes (README: "npm install -g") | unknown |
| Hosted option | unknown | unknown |
Get the board every Monday
One email a week: the new top 10, the biggest score changes and every safety label that changed.
Free. Double opt-in: you confirm by email first, unsubscribe in one click.