Blog
Guides, evaluations, and security notes on the agent-skill ecosystem.
βοΈ Article
The Best Resume Skill We've Reviewed Starts With Research, Not Rewriting
Most resume skills are rewriting engines. You hand over a resume and a job description, and you get back the same bullets with stronger verbs. [`resume-tailoring`](/skill/resume-tailoring) does something different: itβ¦
Nov 4, 2026
βοΈ Article
Seven Claudes Tried to Reject This Resume. Then It Rebuilt It.
Most resume feedback has one voice. A model reads the document, lists strengths and weaknesses, suggests stronger verbs, and stops. [`hiring-panel`](/skill/hiring-panel) takes the opposite approach: seven independent β¦
Nov 4, 2026
βοΈ Article
ATS Advice Is Everywhere. This Skill Makes It Auditable.
Resume advice is the most abundant and least operational genre on the internet. Everyone knows the resume should be "ATS-friendly"; almost nobody can say what that means in checkable steps. [`resume-ats-optimizer`](/sβ¦
Nov 4, 2026
βοΈ Article
Best Game Development Skills for Claude Code
Game development has two properties that most software domains struggle to offer an LLM agent. First, the surface area is aggressively documented: Roblox's Luau API, Unreal's C++ gameplay framework, Godot's GDScript, β¦
Nov 5, 2026
βοΈ Article
Best Interview and Resume Skills for Claude Code
Most domains where people apply Claude Code have a reality check built in. Generated code either compiles and passes tests or it doesn't. A generated migration either runs or it doesn't. The agent can be confidently wβ¦
Nov 5, 2026
βοΈ Article
The Best Obsidian and PKM Skills for Claude Code
For months, "Obsidian skills" meant community reverse-engineering. Then kepano β Obsidian's CEO/CTO β published an official trio, and it immediately redefined what the ceiling looks like in our six-dimension evaluation:
Nov 5, 2026
βοΈ Article
The Best Animation and Motion Skills for Claude Code
Ask an agent to "animate this" and you're really issuing two requests. The first is deterministic: easings, keyframes, timelines, timing curves β code with verifiable behavior. The second is judgment: does this feel rβ¦
Nov 5, 2026
βοΈ Article
Forty New Skills From Seven Repos: What This Batch Looks Like
The directory went from 769 to 809 skills today. The new material is not a random sample of the ecosystem. It is a deliberate attempt to fill domains where we had almost nothing: education, HR, CRM and sales operationβ¦
Oct 31, 2026
βοΈ Article
The New Batch Is Bimodal: 17 Skills Above 8, 10 Below 5
Here is the distribution, in half-point bands and coarser buckets.
Oct 31, 2026
βοΈ Article
Workflow Is the Weakest Dimension in the New Batch
Here are the six-dimension averages for the batch.
Oct 31, 2026
βοΈ Article
Trigger Quality Decides the New Batch Too
Trigger quality is the first dimension in the rubric and the one most people treat as documentation. It is not documentation. It is the routing layer: the sentence an agent reads to decide whether this skill is relevaβ¦
Oct 31, 2026
βοΈ Article
Tool Integrations Average 6.45. Methodology Skills Average 8.45.
We grouped the forty new skills into two rough types.
Oct 31, 2026
βοΈ Article
Jira at 9.5: Anatomy of the Best Skill in the Batch
The six dimensions:
Oct 31, 2026
βοΈ Article
Asana at 4.9 vs Jira at 9.5: Same Job, Different Engineering
| Dimension | [Jira](/skill/jira) | [Asana Automation](/skill/asana-automation) |
|---|---:|---:|
| Trigger | 9.5 | 2.5 |
| Structure | 9.0 | 6.0 |
| Workflow | 9.5 | 1.5 |
| Content | 9.5 | 6.5 |
| Engineering | 9.0 β¦
Oct 31, 2026
βοΈ Article
Anthropic's K-12 Skills Are the Strongest New Domain
| Skill | Trigger | Structure | Workflow | Content | Engineering | Security | Total |
|---|---:|---:|---:|---:|---:|---:|---:|
| [k12-check-for-understanding](/skill/k12-check-for-understanding) | 9.4 | 8.9 | 9.2 | 9.β¦
Oct 31, 2026
βοΈ Article
E-Commerce Is Bimodal: 9.1 Strategy, 3.2 Checkout
| Skill | Score |
|---|---:|
| [dynamic-pricing-ecommerce](/skill/dynamic-pricing-ecommerce) | **9.1** |
| [product-description-generator](/skill/product-description-generator) | **8.0** |
| [shopify-cart-abandonment]β¦
Oct 31, 2026
βοΈ Article
The 1,000 to 2,000 Character Trap
| Description length | Skills | Mean score |
|---|---:|---:|
| 1,000 β 2,000 chars | 5 | **3.40** |
| 2,000 β 4,000 chars | 8 | 6.14 |
| 4,000 β 6,000 chars | 3 | 8.53 |
| 6,000 β 10,000 chars | 24 | 7.50 |
Oct 31, 2026
βοΈ Article
Security Is a Floor in the New Batch Too
| Dimension | Mean | Std. dev. | Min | Max |
|---|---:|---:|---:|---:|
| Security | **9.17** | **0.58** | 8.0 | 10.0 |
| Workflow | 5.30 | 3.10 | 1.0 | 9.5 |
| Trigger | 5.96 | 2.66 | 1.5 | 9.5 |
Oct 31, 2026
βοΈ Article
The Thirteen Skills With Workflow Below 3
The thirteen:
Oct 31, 2026
βοΈ Article
Google Workspace Skills: Official, But Mid
| Skill | Trigger | Structure | Workflow | Content | Engineering | Security | Total |
|---|---:|---:|---:|---:|---:|---:|---:|
| [google-calendar](/skill/google-calendar) | 7.0 | 8.5 | 8.0 | 9.0 | 8.0 | 9.5 | **8.3** β¦
Oct 31, 2026
βοΈ Article
Spreadsheets Are Still the Biggest Supply Gap
| Skill | Score | What it covers |
|---|---:|---|
| [xlsx](/skill/xlsx) | **9.8** | Excel workbook files: read, edit, create, format |
| [google-sheets](/skill/google-sheets) | 6.6 | Google Sheets API operations |
| [β¦
Oct 31, 2026
βοΈ Article
Customer Support Is Still Two Skills
| Skill | Trigger | Structure | Workflow | Content | Engineering | Security | Total |
|---|---:|---:|---:|---:|---:|---:|---:|
| [zendesk](/skill/zendesk) | 6.5 | 7.0 | 5.5 | 7.0 | 6.0 | 9.5 | **6.9** |
| [zendesk-autβ¦
Oct 31, 2026
βοΈ Article
HR Skills: Good Content, Bad Routing
| Skill | Trigger | Structure | Workflow | Content | Engineering | Security | Total |
|---|---:|---:|---:|---:|---:|---:|---:|
| [job-description](/skill/job-description) | 7.5 | 8.5 | 8.0 | 9.0 | 8.5 | 9.5 | **8.4** β¦
Oct 31, 2026
βοΈ Article
CRM/RevOps Is Methodology, Not Automation
| Skill | Score |
|---|---:|
| [deal-qualification-gates](/skill/deal-qualification-gates) | **9.0** |
| [crm-migration-consolidation](/skill/crm-migration-consolidation) | **8.7** |
| [qbr-ebr-builder](/skill/qbr-ebrβ¦
Oct 31, 2026
βοΈ Article
Same Name, Different Skill: Job Descriptions and Lead Routing
| Skill | Source | Trigger | Workflow | Content | Total |
|---|---|---:|---:|---:|---:|
| [job-description](/skill/job-description) | genspark-ai/genoffice | 7.5 | 8.0 | 9.0 | **8.4** |
| Job Description Generator (reβ¦
Oct 31, 2026
βοΈ Article
What Forty New Skills Do to Category Averages
| Category | Before | After | Change | New skills |
|---|---:|---:|---:|---:|
| Marketing | 8.55 | **8.24** | β0.31 | 18 |
| Documents | 8.22 | **7.99** | β0.23 | 4 |
| Productivity | 8.44 | **8.36** | β0.08 | 18 |
| β¦
Oct 31, 2026
βοΈ Article
The Repo Average Hides the Spread
| Repository | Skills | Mean | Range | Spread |
|---|---:|---:|---|---:|
| anthropics/k12-teacher-skills | 4 | 9.07 | 8.7 β 9.3 | 0.6 |
| genspark-ai/genoffice | 4 | 8.50 | 8.4 β 8.6 | 0.2 |
| NEON-Rutger/B2B-revops-sβ¦
Oct 31, 2026
βοΈ Article
GEO Assumes Google. Half the Web Isn't.
Our directory has 765 skills. Of those, a meaningful cluster is SEO tooling β audits, keyword work, GEO content optimization. Sort that cluster by which search engine it targets, and you get Google, Google, Google, anβ¦
Oct 28, 2026
βοΈ Article
Core Web Vitals Reports Tell You What. Not How.
The Core Web Vitals workflow most teams run is: open Search Console, see which URL groups fail, feel bad, close Search Console. The report tells you a page group is failing LCP. It does not tell you *why*, and the thrβ¦
Oct 28, 2026
βοΈ Article
Your README Is a Landing Page Now
Say "SEO" to a developer and they picture content marketing β blog posts, keyword reports, the stuff that happens to other people. Say "repo SEO" and they'll assume it's a metaphor. It isn't. GitHub is a search engineβ¦
Oct 28, 2026
βοΈ Article
The Three-Piece Stack for AI Search Visibility: llms.txt, JSON-LD, and Citability
The chain matters because the failure is positional. A site with brilliant JSON-LD and no citable sentences gets parsed perfectly and never quoted. A site of perfectly quotable claims behind an unspecified robots.txt β¦
Oct 28, 2026
βοΈ Article
One Author vs. the SEO Catalogues: Who You're Actually Buying From
Two authors dominate the SEO shelf. seranking ships 15+ skills β the full bench: `seo-google` at 9.1, `seo-api` and `seo-keyword-niche` at 9.0, and eleven more (`seo-content-audit`, `seo-images`, `seo-technical-audit`β¦
Oct 28, 2026
βοΈ Article
Programmatic SEO Came Back. This Time It Has to Earn It.
The pattern is old: one template, N rows of structured data, N landing pages. It worked from roughly 2015 to 2021 for comparison pages, integration directories, and location pages. Then it stopped working, because theβ¦
Oct 28, 2026
βοΈ Article
Security Isn't the Boring Dimension: Why It Veto-Kills SEO Skills
Most skill categories touch one attack surface, maybe two. SEO is unusual because the job description itself requires all three.
Oct 28, 2026
βοΈ Article
Read-Only vs. Implementer: The Two Tribes of SEO Skills, Scored
Ask one question of any SEO skill: what exists after it finishes running?
Oct 28, 2026
βοΈ Article
11,302 Stars, No Verdict
Here are two data points from the SEO tooling space.
Oct 28, 2026
βοΈ Article
What a GEO Audit Score Actually Measures (and Why It Isn't an SEO Score)
`geo-optimizer-skill` runs 47 checks, and the count isn't arbitrary β it's a fairly faithful operationalization of the Princeton KDD 2024 paper that coined "generative engine optimization." That paper's central findinβ¦
Oct 28, 2026
βοΈ Article
Generate vs. Edit β The Two Kinds of Video Skills, and Why You Probably Need Both
The video category holds 43 skills in our directory. Sorted by what they actually do, they fall into two camps with almost no overlap β and the confusion between them is the most common mistake we see in skill requests.
Oct 23, 2026
βοΈ Article
Why Developer Tools Score 9.21 and Documents Score 8.26 β A Category Gap Autopsy
Across our top-50 per category, the averages run:
Oct 23, 2026
βοΈ Article
Skills That Touch Money β What 76 Finance Skills Taught Us About Letting Agents Near Your Wallet
The finance category is our clearest natural experiment in what happens as agent skills get closer to irreversible actions. Read as a spectrum, it runs from completely harmless to genuinely consequential β and the scoβ¦
Oct 23, 2026
βοΈ Article
Productivity Is Our Biggest Category β And It Isn't About Getting More Done
The Productivity category in our directory has 173 skills β bigger than Developer Tools' dedicated niches, bigger than Marketing. Its top-50 average score (9.15) is second only to Developer Tools itself (9.21). And alβ¦
Oct 23, 2026
βοΈ Article
You Can Now Build Your Own Skill on Skill123 β Scored Before You Download It
The most common feedback we get is some version of *"I love the directory, but I want a skill for my own workflow, and nobody's written it."* A skill for your particular ledger format. Your team's release checklist. Yβ¦
Oct 23, 2026
βοΈ Article
A Quarter of Skills State What They Won't Do β Just Not Where It Matters
Two counts across the same 765 skills:
Oct 23, 2026
βοΈ Article
A Ten-Minute Audit for Any Skill
This checklist is derived from the corpus patterns in this batch. It is ordered by impact per minute.
Oct 23, 2026
βοΈ Article
All Three Skills That Mention rm -rf Are Guarded
Three skills out of 765 contain the string `rm -rf`. Here is what each one actually does.
Oct 23, 2026
βοΈ Article
Almost a Quarter of Skills Have No Numbered Steps
Counting number-list items across 765 SKILL.md files:
Oct 23, 2026
βοΈ Article
Bash Appears in 1% of Skills. Read and Write Appear in a Quarter.
Counting explicit mentions of Claude Code tool names across 765 SKILL.md files:
Oct 23, 2026
βοΈ Article
Fewer Than Half of Skills Check Their Own Work
Three counts across the 765-skill corpus:
Oct 23, 2026
βοΈ Article
42 Skills Point at example.com. Which Ones Mean It?
Scanning the corpus for the reserved documentation domain:
Oct 23, 2026
βοΈ Article
How to Write a "When Not to Use" Clause
The boundary belongs in the description, not the body. A practical guide to writing the clause, with patterns that work, patterns that fail, and a three-request test you can run in five minutes.
Oct 23, 2026
βοΈ Article
21.8% of the Corpus Is Chinese β and Most of It Is One Author
167 of 765 SKILL.md files contain Chinese text. 119 of them come from a single catalogue, which turns what looks like a bilingual ecosystem into one author's translation decision.
Oct 23, 2026
βοΈ Article
Only 1.8% of Agent Skills Ask for Confirmation Before Acting
Across 765 SKILL.md files, exactly 14 contain an explicit instruction to confirm before the agent acts. It is the rarest structural feature in the corpus β and the one most associated with a higher score.
Oct 23, 2026
βοΈ Article
Only 22.7% of Skills Say What the Output Looks Like
174 of 765 SKILL.md files contain an output section. Without one, the last instruction in the workflow becomes the de facto contract β and the agent decides what "done" means.
Oct 23, 2026
βοΈ Article
Progressive Disclosure Is Mostly Aspirational
Only 4.2% of the 765 SKILL.md files reference an assets/ directory, 22.6% reference scripts/, and 53.5% reference references/. The pattern everyone recommends is the one almost nobody ships.
Oct 23, 2026
βοΈ Article
Every Structural Feature We Measured Fits Inside the Evaluator's Noise
We correlated ten structural features across 765 SKILL.md files with their scores. The largest gap is 0.55 points. Our own re-runs move scores by up to a full point. That makes the whole table directional at best.
Oct 23, 2026
βοΈ Article
30 Skills Call an API. Only 15 Document the Rate Limit.
Thirty skills in the corpus reference an api.* endpoint. 28 document auth, but just 15 mention rate limits and 14 describe environment variables. The missing third is where agents get stuck.
Oct 23, 2026
βοΈ Article
The Two Skills That Say "Ignore Previous Instructions" Are Defending Against It
A naive scan of 765 SKILL.md files found the classic injection phrase in two of them. Both occurrences are inside security rules telling the agent to treat such text as data. String matching cannot tell a warning from an attack.
Oct 23, 2026
βοΈ Article
Two "Standards" That Are Really One Author's Template
The "Skill Contract" heading appears in 119 files and "Data Sources" in 125. Both look like emerging conventions. 118 of the 125 and all 119 come from the same catalogue.
Oct 23, 2026
βοΈ Article
What 765 SKILL.md Files Actually Contain
Overview in 828 sections, Source in all 765, quick start in 162, instructions in 148. A frequency table of every heading in the corpus, and what the shape says about how skills are written.
Oct 23, 2026
βοΈ Article
What an LLM Judge Can and Cannot Tell You About 765 Skills
Our six-dimension rubric ranks skills consistently, but run-to-run movement of about a point is larger than every structural effect we measured. Here is how to read the scores β and what they are not.
Oct 23, 2026
βοΈ Article
What Changed After We Re-Evaluated 174 Skills
174 skills carried zeroes in three dimensions because an older evaluator never wrote those fields. Re-scoring them changed the bottom of the distribution, not the top β and exposed how a missing field can masquerade as a measurement.
Oct 23, 2026
βοΈ Article
What We Learned From Scoring 765 Skills
After 20 posts of corpus analysis, three themes hold up: routing is decided in the description, safety is mostly absent, and most "structural" effects are smaller than the measurement noise.
Oct 23, 2026
βοΈ Article
Score Predicts Downloads. Star Count Predicts Nothing.
Across 591 evaluated skills, our score correlates with downloads at r=0.47 while GitHub stars correlate with quality at r=0.02. But the relationship is a cliff, not a slope β the effect lives almost entirely above 9.5.
Oct 21, 2026
βοΈ Article
The Dimension That Predicts Downloads Is Not the One We Rank Highest
Across 591 evaluated skills, structure (r=0.56) and content (r=0.52) correlate with downloads far more than trigger quality (r=0.15) β even though trigger quality is the dimension we say decides whether a skill ever fires.
Oct 21, 2026
βοΈ Article
The Long Tail Isn't Winner-Take-All
In a directory of 765 skills, the top 10% account for only 31% of downloads and the top 50% for 79%. Twenty percent have never been downloaded at all. That is a much flatter distribution than app stores, and it changes how a new skill should think about competition.
Oct 21, 2026
βοΈ Article
Six Authors Supply Three Quarters of the Directory
765 skills come from 65 GitHub authors β but six accounts supply 535 of them, and the top ten account for 76%. The "ecosystem" is closer to a dozen publishers with large catalogues.
Oct 21, 2026
βοΈ Article
What 765 Taglines Reveal About How Skills Describe Themselves
23% of skills open their description with "Use when", but only 0.5% say what the skill should not do. The negative space we keep recommending is almost entirely absent from the corpus.
Oct 21, 2026
βοΈ Article
Longer SKILL.md Files Score Higher β Which Sits Awkwardly With Our Own Advice
Across 591 evaluated skills, SKILL.md length correlates with score at r=0.24, and the longest quartile averages 8.82 versus 8.14 for the shortest. Our rubric says to keep files lean. Both can be true, but only if you read "lean" correctly.
Oct 21, 2026
βοΈ Article
The 152 Skills Nobody Has Downloaded
19.9% of the directory has zero downloads β and those skills average a higher score (9.03) than the ones that have been downloaded (8.52). The number is measuring exposure, not quality.
Oct 21, 2026
βοΈ Article
Single-Skill Repos Beat Mega-Repos on Score β Barely
29 skills come from repositories that publish exactly one skill, and they average 8.69 with 10.5 downloads each. The 440 skills inside mega-repos average 8.49 and 7.5 downloads. The gap exists, but it is smaller than the narrative suggests.
Oct 21, 2026
βοΈ Article
A Category-by-Category Look at the Six Dimensions
Marketing skills lead on trigger quality (9.30) but trail badly on engineering (5.61). Finance is the mirror image. Documents score highest overall. The variation is mostly about who writes in each category, not what the category requires.
Oct 21, 2026
βοΈ Article
The 18 Skills That Scored 9.5 or Higher
Out of 591 fully-evaluated skills, 18 clear 9.5 β and 12 of them come from just two authors. What the elite set has in common, and why the list is narrower than it looks.
Oct 21, 2026
βοΈ Article
The 18 Skills That Scored Below 7.0
Two categories β design and finance β account for 10 of the 18 lowest-scoring skills, and five of those come from a single family. The common failure is not bad code; it is a file that is a knowledge dump instead of a workflow.
Oct 21, 2026
βοΈ Article
What the September and October Batches Look Like
555 fully-evaluated skills arrived in September, 36 in October β and the October batch averages 0.5 points higher but a third of the downloads. Little of that is about quality; almost all of it is about time and discovery.
Oct 21, 2026
βοΈ Article
Views and Downloads Move Together β But Neither Measures What You Think
Across 591 evaluated skills, views and downloads correlate at r=0.46. Median views is 2 and median downloads is 5 β which tells you more about what the counters measure than about what users want.
Oct 21, 2026
βοΈ Article
The Verified Badge Doesn't Predict Quality β and That's Fine
577 verified skills average 8.53; 14 unverified average 8.21. The gap is small, and the badge doesn't mean what readers assume. Here's what it actually says.
Oct 21, 2026
βοΈ Article
Twelve Skills Have a Placeholder Tagline β a Sign of What Breaks in Bulk Import
Twelve skills in the directory carry a tagline like "A skill from the GitHub repository X" instead of a real description. It is a small number, and a useful illustration of how bulk import fails silently.
Oct 21, 2026
βοΈ Article
Why 174 Skills Show Zeros in Three Dimensions
22.7% of the directory displays a score around 8 while structure, content, and engineering are all zero. They were imported but never evaluated. Here is the defect, its blast radius, and what we are doing about it.
Oct 21, 2026
βοΈ Article
Reading 765 Skills: What the Ecosystem Looks Like Now
765 skills, 65 authors, 66 repositories, a median score of 8.5 and a median of two views per skill. A compact snapshot of what a skill directory looks like after two months.
Oct 21, 2026
βοΈ Article
The Shape of a Skill Name
37 skills have single-word names. 16 end in -builder, 14 in -expert, 10 in -pro. Naming patterns cluster by category and by author, and the most common suffix is not the one that predicts a better score.
Oct 21, 2026
βοΈ Article
Skill Families and How They Grow
37 name-prefix families cover 214 of 591 evaluated skills. The largest β baoyu with 21 skills β averages 9.11. The widest spread inside a family is nearly three points. What that says about how catalogues age.
Oct 21, 2026
βοΈ Article
What a Placeholder Row Does to Your Averages
Adding 174 rows with zeroed dimensions moves the site-wide structure average from 8.37 to 6.47 β a 1.9-point distortion β while barely moving the overall score. A worked example of why completeness checks come before analysis.
Oct 21, 2026
βοΈ Article
Skills With a Built-In Verdict β The Ones That Can Say No
Most skills can only say yes β produce, generate, output. A small class encodes a standard strong enough to reject its own work: validators, auditors, reviewers. They score a full point above the directory mean, and they're the safest class we host.
Oct 21, 2026
βοΈ Article
One Skill, Two Languages β The Hidden Tax on Bilingual SKILL.md Files
Chinese-native skills for Chinese platforms score 9.1β9.4 β the language is load-bearing. Skills that merge two languages in one file pay a measurable tax on trigger and content quality. The data, and the fork-don't-merge pattern.
Oct 21, 2026
βοΈ Article
Super-Authors β The Handful of Names Behind a Third of Our Top 50
Sort 600+ evaluated skills by score and the author column collapses: eleven skills from one name, ten from another, eight from a third. What the top three multi-skill authors share β systems, not files.
Oct 21, 2026
βοΈ Article
The 21-Skill Personal Toolkit β One Author, Every Publishing Job, 8.9 to 9.5
The largest single-author skill family in our directory covers the entire bilingual content pipeline β translate, fetch, summarize, diagram, generate images, build slides, post to WeChat. Twenty-one skills, zero overlap, a masterclass in narrow triggers.
Oct 21, 2026
βοΈ Article
One Repo, 92,647 Stars, Four Skills β What Megarepos Actually Ship
The highest-starred repos in our directory ship few skills β a constraint methodology, an interviewer, a diagram tool. With the hype variable maxed out, what remains is the actual skill engineering, and it's not wrappers.
Oct 21, 2026
βοΈ Article
Skill Interference β Why Your Tenth Install Is Weaker Than Your First
Every skill is evaluated in isolation, but users install them in sets β and sets fail differently: trigger collisions, capability overlap, contradictory defaults. Four interference patterns and the loadout rules that avoid them.
Oct 20, 2026
βοΈ Article
The Skills That Interview You β And Why the Best Prompts Are Questions
A pattern hiding at the top of our directory: skills whose core mechanism is asking the user one sharp question instead of guessing. From academy-guide (9.6) to discernment-nudge to interview-me (9.4).
Oct 20, 2026
βοΈ Article
Agent Skills That Work on Your Machine, Not Just in Chat
A smaller class of skill operates the machine around the agent β driving a real logged-in Chrome, extracting from Electron apps, managing Obsidian vaults. They score well precisely because they define their side effects honestly.
Oct 20, 2026
βοΈ Article
Skills That Answer in HTML β The Highest-Scoring Pattern We Hadn't Named
A quiet pattern runs through our top scores: skills that turn an agent's answer into a one-page visual artifact β HTML explainers, isometric SVG figures, motion-graphics videos. Five skills from 9.3 to 9.6.
Oct 20, 2026
βοΈ Article
The HyperFrames Family β Ten Skills, One Video Pipeline, Scores From 5.7 to 9.7
One author shipped ten skills covering a complete agent video pipeline. Nine scored 8.7 or above β and the one that didn't shows exactly what a missing system looks like.
Oct 20, 2026
βοΈ Article
The Best Frontend and React Skills for Claude Code
Six frontend and React skills for Claude Code, scored 8.5 to 9.2 β what each one is actually good at, where they overlap, and which combination covers a real app.
Oct 17, 2026
βοΈ Article
The Best Security and Authentication Skills for Claude Code
Three security skills for Claude Code scored 8.5 to 9.3, what each covers, and why the security dimension's scores say less than the capability manifest does.
Oct 17, 2026
βοΈ Article
The Best Architecture and System Design Skills for Claude Code
Six architecture skills for Claude Code scored 9.0 to 9.4 β system design, cloud architecture, RAG, microservices, and the framework-specific architects that fill the gaps.
Oct 17, 2026
βοΈ Article
The Best Deploy and CI/CD Skills for Claude Code
Seven deploy and CI/CD skills for Claude Code scored 8.4 to 9.4 β infrastructure as code, containers, Kubernetes, Vercel deployment, and the one that ships an app end to end.
Oct 17, 2026
βοΈ Article
The Best LinkedIn Skills for Claude Code
Eight LinkedIn skills for Claude Code scored 8.5 to 9.5 β posting, commenting, replying, planning, hook extraction, and de-AI-ing drafts. What each does and which four cover a real workflow.
Oct 17, 2026
βοΈ Article
The Best Skills for Publishing to WeChat and Xiaohongshu
Eight skills scored 9.1 to 9.4 for Chinese social publishing β WeChat Official Accounts, Xiaohongshu image cards, Weibo, and the account-level strategy skills that surround them.
Oct 17, 2026
βοΈ Article
The Best User Research Skills for Claude Code
Eight user research skills scored 7.9 to 9.4 β interviewing yourself and users, simulated buyer panels, pricing, offers, and the interview scripts that produce better material.
Oct 17, 2026
βοΈ Article
The Best SEO Skills for Claude Code
Seven SEO skills for Claude Code scored 8.6 to 9.4 β technical audits, on-page audits, SERP markup, programmatic pages, keyword mining, and SERP analysis.
Oct 17, 2026
βοΈ Article
The Best Slide Deck Skills for Claude Code
Six slide deck skills for Claude Code scored 7.3 to 9.7 β native PPTX editing, image-based decks, article-to-deck conversion, and the narrative skills that decide what the slides should say.
Oct 17, 2026
βοΈ Article
The Best Meeting and Notes Skills for Claude Code
Four meeting and notes skills for Claude Code scored 7.9 to 9.3 β transcript capture, structured meeting summaries, interview notes, and release notes built from the same raw material.
Oct 17, 2026
βοΈ Article
The Best Database Skills for Claude Code
Four database skills for Claude Code scored 7.6 to 9.4 β query optimization, schema design, PostgreSQL operations, and natural-language SQL. Which one fits which problem.
Oct 17, 2026
βοΈ Article
The Best Code Review Skills for Claude Code
Six code review skills for Claude Code scored 8.7 to 9.4 β bug and security review, over-engineering review, diff comprehension, and the quality workflows that run before a merge.
Oct 17, 2026
βοΈ Article
The Best Image Generation Skills for Claude Code
Five image generation skills for Claude Code scored 8.2 to 9.3 β multi-provider generation, article covers, website assets, and the prompt guides that make the models behave.
Oct 17, 2026
βοΈ Article
The Best Diagram and Visualization Skills for Claude Code
Four diagram and visualization skills for Claude Code scored 8.2 to 9.4 β SVG diagrams, Mermaid rendering, 3D explainers, and d3 charts. Which output format fits which audience.
Oct 17, 2026
βοΈ Article
The Best Django and FastAPI Skills for Claude Code
Four Python web skills for Claude Code scored 9.0 to 9.4 β Django applications, Django storage configuration, FastAPI APIs, and the modern-Python baseline skill underneath them.
Oct 17, 2026
βοΈ Article
The Best Crypto and Trading Skills for Claude Code
Seven crypto and trading skills for Claude Code scored 8.6 to 9.3 β Solana DEX execution, prediction markets, DeFi analytics, DEX pair data, and AMM pool mechanics.
Oct 17, 2026
βοΈ Article
The Best Landing Page and Copywriting Skills for Claude Code
Five conversion skills for Claude Code scored 8.4 to 9.0 β landing page optimization, offer construction, conversion tracking QA, value mapping, and pre-launch experience checks.
Oct 17, 2026
βοΈ Article
The Best Testing and TDD Skills for Claude Code
Five software testing skills for Claude Code scored 9.0 to 9.1 β TDD workflow, E2E with Playwright, test generation, and full-flow click testing. Plus why "testing" skills for marketing are a different category.
Oct 17, 2026
βοΈ Article
The Best Data Visualization and Chart Skills for Claude Code
Five data visualization skills for Claude Code scored 7.9 to 9.3 β infographics, d3 charts, motion graphics, 3D explainers, and trading-specific charts.
Oct 17, 2026
βοΈ Article
The Best Podcast and Audio Skills for Claude Code
Seven audio skills for Claude Code scored 8.4 to 9.4 β text-to-speech in Chinese and English, music generation, audio-to-video, transcripts, and voice consistency.
Oct 17, 2026
βοΈ Article
Security Almost Never Separates a Good Agent Skill From an Average One
Across 628 scored agent skills, security is the least discriminating of our six dimensions β 92% score 9 or above, and it explains just 0.09 of the 1.97-point gap between top and median skills. Workflow design, trigger quality, and structure are what actually separate them.
Oct 17, 2026
βοΈ Article
How to Read a SKILL.md in 60 Seconds
A six-check reading routine for people choosing a skill, ordered by the dimensions that actually separate good skills from average ones β file structure first, security last, and the one question almost every description omits.
Oct 17, 2026
βοΈ Article
"Which Skill Category Is Best?" Is the Wrong Question
Across nine categories and 591 evaluated skills, the gap between the best and worst category is 0.59 points β while the gap inside a single category runs up to 4.1. Category averages mostly measure who happened to write the code.
Oct 10, 2026
βοΈ Article
The 20-Point Field Most Agent Skills Get Wrong
Across 591 evaluated skills, trigger quality is the weakest of our six dimensions at 7.74/10 β and it decides whether the skill ever fires. The most common failure is a missing "when NOT to use this" clause.
Oct 10, 2026
βοΈ Article
MCP Server or Skill? A Decision Rule That Actually Decides.
Both make your agent more capable and they fail in different ways. If you can write the capability as a function signature it is a server; if describing it takes conditions and exceptions it is a skill. Includes the five MCP-related skills we scored.
Oct 10, 2026
βοΈ Article
We Ran the Same Evaluation Twice. Seven of Eleven Scores Moved.
Same skills, same SKILL.md, same rubric, same model β re-run two hours later. Seven of eleven scores changed, the largest by a full point. What that means for reading any automated score, ours included.
Oct 10, 2026
βοΈ Article
We Scored 591 Agent Skills. Here's the Shape of the Data.
The score distribution across 591 evaluated skills and the six-dimension averages behind the headline number β including why our highest-scoring dimension is partly an artifact of how we score.
Oct 10, 2026
βοΈ Article
We Scored the Skills Inside the Most-Starred Agent Repos. Star Count Is Not a Score.
We pulled live star counts for the top agent-skill repos and compared them with our per-skill evaluations. Inside a single repo scores span 6.7 to 9.8 β starring a repo does not tell you which of its skills to install.
Oct 10, 2026
βοΈ Article
AI Agents Now Outnumber Human Users on Our Skill Directory
30 days of install data: agentsaccount for 87% of all skill installs. What that means for how you distribute agent skills.
Oct 8, 2026
βοΈ Article
What 600 Skill Evaluations Taught Us About Writing Good Agent Skills
Patterns from scoring 600+ skills: the top 1% verify their own output, trigger boundaries are the weakest link, and popularity correlates with nothing.
Oct 8, 2026
βοΈ Article
How We Dynamically Test Agent Skills (Not Just Read Them)
Static review catches what a skill says. Dynamic testing catches what it does. Our probe-based methodology, explained end to end.
Oct 8, 2026
βοΈ Article
The Best MCP Skills for Claude Code (Tested and Scored)
MCP skills teach your agent to build and use Model Context Protocol servers. The ones worth installing, evaluated.
Oct 8, 2026
βοΈ Article
The Best Email Skills for Claude Code (Deliverability, Campaigns, Compliance)
Email skills that survive contact with real inboxes β deliverability QA, rendering, and the consent gap in the category.
Oct 8, 2026
βοΈ Article
We Ran 384 Adversarial Probes Against 48 Agent Skills. Injection Wasn't the Problem.
Prompt injection hidden in artifacts failed 1.6% of the time; probes that simply pushed past a skill's declared scope failed 30%. Full per-probe dataset published under CC BY 4.0 β including the two ways our own grading flatters the skills.
Sep 29, 2026
βοΈ Article
We Injection-Tested the Legal Skills: What Actually Broke
We ran the legal-category skills through live adversarial probes β prompts hiding instructions in intake files, telling them to skip their own disclaimers. The readers held. The generators cracked. Full results inside.
Sep 28, 2026
βοΈ Article
The Security-Conscious Skill Loadout: What to Install, How to Contain It
After evaluating 600+ skills β including one credential harvester we delisted β the containment-first loadout, and how to read the new dynamic-injection badges on every skill page.
Sep 28, 2026
βοΈ Article
The Solo Founder Skill Stack: Product, Launch, Legal, Without Hiring Anyone
The cross-category loadout a one-person company actually needs β spec the product, build the funnel, paper the deals. Seven skills spanning four categories, tested and scored.
Sep 28, 2026
βοΈ Article
Ship a Side Project in a Weekend: The Deploy-It-Yourself Skill Loadout
You don't need to be an engineer to ship anymore β you need an agent with the right four skills. Spec, scaffold, deploy, polish. Tested scores and the one gotcha per skill.
Sep 28, 2026
βοΈ Article
The Content Repurposing Pipeline: One Idea, Every Platform, One Agent
Turn one YouTube video into an article, a slide deck, a LinkedIn post, and a WeChat piece β without writing any of them twice. The baoyu family tested and sequenced.
Sep 28, 2026
βοΈ Article
The Meeting-to-Deliverable Pipeline: Recording In, Documents Out
Meetings produce recordings; recordings produce nothing. The skill chain that turns a call into a recap, a spec, and a deck β with injection results for the document generators.
Sep 28, 2026
βοΈ Article
The Product Manager Skill Stack: Spec, Deck, Ticket, Numbers
The PM's actual week β PRD, review deck, tickets, retention numbers β covered by six tested skills across four categories. Includes injection-test results for the document generators.
Sep 28, 2026
βοΈ Article
The Research-to-Publish Workflow: Sources, Citations, Drafts, Done
For the grad student, the paralegal, the analyst: the skill chain from a pile of sources to a citation-clean, formatted document. Five skills, four categories, injection results included.
Sep 28, 2026
βοΈ Article
Skills That Call Other AIs: claude-api, dashscope, and the API-Reference Family
A quiet category of skills teaches your agent to call other models and APIs β image generators, market data, on-chain data, even Claude itself. Tested scores, plus why these deserve the strictest security review.
Sep 28, 2026
βοΈ Article
The Bilingual Publishing Stack: One Workflow, Both Internets
Publishing in both Chinese and English isn't translation β it's two platforms with different physics. The baoyu family, dashscope, and video-translate, sequenced for creators working both markets.
Sep 28, 2026
βοΈ Article
The Muse Skills: Session Memory for AI Pair Programmers (Evaluated)
Your AI coding agent forgets everything when the session ends. The MUSE family β /resume, layered context, strategic compaction, semantic search β is a complete memory system in plain Markdown. All six core skills evaluated.
Sep 27, 2026
βοΈ Article
The Jev Skill Family: Five Workflow Primitives for Coding Agents (Evaluated)
Most agent skills are single prompts. The Jev family arrived as a system β five skills that sort, find, judge and act, the first family to score 10/10 on security in every member.
Sep 24, 2026
βοΈ Article
Monthly Security Report: September 2026
611 skills evaluated, one credential harvester delisted, and what our capability manifests found in the agent-skill ecosystem.
Sep 24, 2026
βοΈ Article
The Complete Guide to AI Agent Skills
What AI agent skills are, where to find them, and the six-dimension framework for telling great skills from prompt-wrappers before you install.
Sep 10, 2026
βοΈ Article
I Found an Agent Skill That Harvests Browser Credentials
What checking the scripts β not the README β revealed about a popular research skill, and the three-step security check I now run before installing anything.
Sep 16, 2026
βοΈ Article
The 10 Claude Skills Worth Installing (And What Most People Get Wrong)
I evaluated 500+ agent skills on a six-dimension rubric. These are the ten I would actually install, each with the one mistake people make when using it.
Sep 17, 2026
βοΈ Article
The 10 Best Video-Generation Skills for AI Agents (Tested and Scored)
Video is where agent skills went from nice trick to production tool. I evaluated the full video category β 60 skills and counting. Here are the ten that hold up.
Sep 19, 2026
βοΈ Article
Document Skills for Claude Code, Tested: Excel, Word, PowerPoint, PDF
I tested every document skill in the ecosystem β Excel workbooks, Word documents, PowerPoint decks, and PDF workflows. Here are the seven worth installing.
Sep 22, 2026
βοΈ Article
Developer Tool Skills for Claude Code, Tested: Debugging, TDD, Architecture
The skills that teach your agent real engineering discipline β systematic debugging, test-driven development, architecture diagrams, and the API reference that scores 9.8.
Sep 22, 2026
βοΈ Article
Data & Analytics Skills for Claude Code, Tested: pandas, SQL, ML Pipelines
I evaluated every data skill in the ecosystem β pandas workflows, PostgreSQL optimization, Spark, ML pipelines, and A/B test statistics. Seven worth installing.
Sep 22, 2026
βοΈ Article
Design & Creative Skills for Claude Code, Tested: Diagrams, Images, Infographics
The creative category has the widest quality spread β for every skill that produces professional output, three produce generic AI slop. Here are the seven that cleared the bar.
Sep 22, 2026
βοΈ Article
Writing Skills for Claude Code, Tested: Content, Editing, Translation
Writing skills are the most crowded and most mediocre category β half are prompt-wrappers. Here are the seven that actually improve your agent's writing.
Sep 22, 2026
βοΈ Article
Marketing Skills for Claude Code, Tested: SEO, Ads, Email, Landing Pages
The marketing category is dominated by a single coherent skill family β a full growth stack covering SEO, ad testing, email, and audience research. Ten skills, tested and scored.
Sep 22, 2026
βοΈ Article
Legal Skills for Claude Code, Tested: Contracts, Compliance, Legal Research
Legal skills are the newest and most cautious category β CCPA compliance, Bluebook citations, NDAs, patent analysis, and complaint drafting. Six skills, evaluated.
Sep 22, 2026
βοΈ Article
Finance & Trading Skills for Claude Code, Tested: Crypto, DeFi, Market Data
The finance category leans into crypto infrastructure β Solana DEX execution, MEV protection, and free market-data APIs, plus systematic trading methodology. Ten skills, tested and scored.
Sep 22, 2026
βοΈ Article
Video Creation Skills for Claude Code, Tested: Explainers, Motion Graphics, 3D
Video creation is the fastest-growing skill category β code-drawn frames, music-synced visuals, 3D scenes, and mathematical animation. The full collection, evaluated.
Sep 22, 2026