Crashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minuteWindows Errors? Fix Them Before They Spread
Repair common Windows errors and clear accumulated junk for a smoother, more stable PC - no reinstall needed.Free scan · no reinstalliTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
“38,000 searches” is a shorthand, not a count of searches observed in real time. SkillGild says its 2026 analysis covered 38,147 distinct US queries about skills, plugins, MCP and agents; the publisher’s Ahrefs estimates suggest about 650,000 US searches a month across that selected query set. Those figures describe a keyword database, not 38,147 people or a census of Claude use.
What the 38,147 figure counts
SkillGild reports 38,147 distinct US queries in its selected dataset. That is a count of different query phrases, not individual search events, users, or Claude customers. The count is separate from estimated monthly search volume.
![Claude AI for Beginners Bible: [5 in 1] The Ultimate Guide to Automate Your Work, Save Hours Every Week, and Use AI for Real-World Results](https://m.media-amazon.com/images/I/415+fSJacsL._SL160_.jpg)
Of those queries, SkillGild says 9,762 had measurable volume—defined in the report as at least 10 searches per month—while 28,385 had no measurable volume. A query below that threshold is not necessarily never searched; the database simply does not assign it measurable volume under the report’s definition.
The headline’s “38,000 searches” should therefore be read as an approximate reference to the number of distinct query terms analyzed. SkillGild’s export was dated 6 October 2026, and its monthly-volume figures are estimates from Ahrefs, not official Anthropic statistics.
#1 Best Overall
How much search demand SkillGild estimates
Across the selected query set, SkillGild reports about 650,000 estimated US searches per month. Within that total, it reports about 183,000 monthly searches for skill-specific queries and about 207,000 for MCP-specific queries. The categories are the publisher’s classifications of query topics, not a measure of how many people use those technologies.
The terms “claude skills” and “claude code skills” are each reported at about 10,000 estimated US searches per month. SkillGild also says four queries account for a third of the selected set’s estimated volume, which means the total is concentrated in a small number of terms rather than evenly distributed across all 38,147 queries.
What people appear to be looking for
SkillGild’s classification points to practical questions as well as broad interest in the subject. It reports about 10,200 estimated US searches per month across query variants about creating skills. Examples transcribed in the report include “how to create a claude skill,” “claude skill template,” “skill.md example,” and “claude code custom skills.”
Other reported query examples focus on setup and location: “install claude code skills,” “claude skills directory,” and “where are claude skills stored.” Comparison queries include “claude skills vs mcp,” “skills vs subagents,” and “claude code plugins vs skills.” These examples illustrate the kinds of questions in the selected dataset; they are not a complete query export.
For community-created skills, SkillGild reports 2,894 queries that name a particular skill and about 57,500 estimated US searches per month across them. Examples it identifies include Humanizer, Nano Banana, Stop Slop, Superpowers, Impeccable, Taste Skill, Anthropic’s document skills, Obsidian Skills, and Remotion Skills. SkillGild says almost all of these queries have an Ahrefs keyword difficulty score of zero on its 0–100 scale. That score is a database metric, not a guarantee that a page will rank or that a skill is useful or safe.
Which kinds of pages appear in the results
SkillGild classified pages ranking for its top queries and estimated their traffic share. These figures reflect the publisher’s classified sample and estimates, not all web traffic about Claude or skills.
| Page type | Estimated traffic share | Pages classified | Estimated traffic per page |
|---|---|---|---|
| Official documentation and vendors | 32% | 51 | 389 |
| Blog articles | 18% | 67 | 165 |
| 17% | 33 | 312 | |
| Directories and marketplaces | 14% | 38 | 224 |
| GitHub repositories | 9% | 19 | 303 |
| YouTube | 6% | 33 | 114 |
The reported shares do not sum to 100%, so they should not be treated as a complete breakdown of every result type. The per-page figures are SkillGild’s traffic estimates; the report does not establish that pages within a category perform uniformly.
How the trend and global figures should be read
SkillGild says monthly volume for “claude skills” rose after Anthropic launched Agent Skills in October 2025, reached a peak in January 2026, and was about 62% below that peak by the October 2026 analysis. This is a timing association in the publisher’s analysis, not evidence that the launch caused the rise or later decline.
The publisher estimates worldwide volume at about 3.7 times the US figure and names Japan, Brazil, and South Korea as the largest markets after the United States. It says English-language queries dominate in those markets. These are SkillGild’s interpretations of its keyword data, not a comprehensive measure of local-language interest or adoption.
What the analysis can—and cannot—tell you
What it can indicate
- Which query topics a keyword database estimates people search for, and how that estimated demand is distributed across the publisher’s selected terms.
- That searches in the dataset concern practical tasks such as creating and installing skills, as well as questions about adjacent concepts.
- Which types of pages SkillGild found among results for its top queries, under its own classification and traffic estimates.
What it cannot establish
- How many people searched, used Claude, installed a skill, or returned to one.
- Whether a particular skill works well, is trustworthy, or improves a user’s results.
- Whether search interest translates into product adoption, satisfaction, or business value.
- A complete, independently reproducible count of demand: SkillGild describes its methods, but the underlying exports and classification decisions were not available for independent reproduction.
Ahrefs keyword databases estimate demand, may omit queries, can round low-volume terms, and change over time. The findings should be treated as a dated snapshot from SkillGild’s selected dataset, not a definitive census of interest.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.How SkillGild says it assembled the dataset
SkillGild says it used Ahrefs Keywords Explorer exports with seed terms such as “claude skills,” “claude code skills,” “agent skills,” “claude plugins,” “mcp server,” and marketplace names. It reports expanding those terms with matching and related terms, search suggestions, country volume, and 24 months of monthly history. It also says it used Site Explorer exports for pages ranking on top queries.
Quick wins for a faster PC:
Clear out junk files and repair common Windows errorsFree Scan →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →The publisher classified queries by concept—including skills, MCP, plugins, agents, and marketplaces—along with intent and named skill or product. It dates its export 6 October 2026 and says its volumes are Ahrefs estimates for the United States unless otherwise specified. SkillGild says it plans to rerun the analysis as the data changes; future results may differ as both search patterns and database estimates move.
Best Value
How to interpret the adjacent-product questions
The dataset shows that people search for distinctions among skills, MCP, subagents, plugins, and commands, but the available evidence here does not support a definitive, current comparison of how each works, where it is configured, or which Claude product surfaces support it. Anthropic documents Claude Code setup and describes MCP separately as an open protocol for standardizing how applications provide context to language models. Anthropic also lists MCP integrations for Claude Code and Claude.ai. Those references do not establish a full feature-by-feature comparison across every category or product.
For current Claude Code installation, authentication, system requirements, and update options, consult Anthropic’s Claude Code setup documentation. For Anthropic’s description of MCP and its integrations, see Anthropic’s MCP documentation. Setup details and product support can change, so check the live documentation for the version and surface you use.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
Free tools Windows power users keep installed
One-click scans. No signup required.
