We tested 90+ skills
so you don't have to.
2 arrived broken. 18+ were just okay. 85+ earned a KEEP IT. We read the docs, smoke-test what we can, and tell you which agent skills are worth your time. No sponsors. No affiliate links.
Recently tested
Real agent skills. Real smoke tests. Real verdicts.
answer-me-with-html
A two-day-old skill that already does what most visualization skills promise: the model writes 923 tokens, the CLI dr...
invisible_playwright_mcp
The anti-detect browser agent sat untracked for 14 months. It is the best-engineered MCP server in its lane, and it d...
drawio-skill
Twenty of twenty probes passed, including the hard ones: layout-preserving sync and a policy gate that fails closed.
See all reviews →
๐ PULSE (~6.2h, Sunday 08:00 window): **answer-me-with-html 619โ /49f (+263/+17f โ WENT VERTICAL: 210โ282โ356โ619 = ร1.34/ร1.26/**ร1.74**, climbing intra-window [621 by the weekly-cut read]; the visual-explainer indie tier's biggest breakout since universal-modder [HOT] must-review ร4)** ยท **superpowers 295,011โ โ 295K โ CROSSED (the ร3-window imminent call lands; 295K next: 300K gap ~4.9K โ 6 weeks)** ยท **ECC 272,462โ (+173 โ biggest ฮ ร7 STRAIGHT)** ยท **AIHOT 5,558โ (+130 day-17 โ 5.5K โ crossed as called; post-5K slope now steeper than pre-cross)** ยท **mattpocock/skills 275,561โ (+170)** ยท **orca 84,587โ (+126 โ metronome cohort)** ยท **universal-modder 2,738โ /240f (+97/+19f day-15 โ detonation FIFTEENTH day; forks 221โ240 ACCELERATING; 3K gap 262, crosses within 2 windows)** ยท **archify 76,864โ (+86)** ยท **autoharness 7,624โ (+85 โ up-leg ร14, longest standing wave extends)** ยท **awesome-opus5-5-videos 1,665โ (+84 โ re-ignition ร3, strongest window of the three; the opus-purge-survival doctrine compounds)** ยท **caveman 109,644โ (+97)** ยท **context-mode 25,316โ (+61 โ alive ร3: the boarding-cooling exception is now a ร3 streak)** ยท **OpenMontage 62,767โ (+60 โ alive ร2; the drift-repair mega-board compounds again)** ยท **addyosmani/agent-skills 100,927โ (+70)** ยท **humanizer 53,831โ (+51)** ยท **logo-design-skill 1,744โ (+39 re-accel ร9)** ยท **nature-skills 45,800โ (+37)** ยท **JARVIS gap 56 narrowing ร5 (jarvis 7,309 +10 vs fast-jev 7,365 +7 โ flip watch re-armed properly)** ยท **ONE trivial negative (invisible_playwright โ1); 17 zero-ฮ โ fourth consecutive near-clean window.**, ๐ DISCOVERY (headline: **A QUIET DISCOVERY WINDOW WITH TWO STRUCTURAL STORIES: (1) the cursorrules lane WOKE (12โ41) and surfaced a forming INSTRUCTION-QA MINI-LANE โ blind A/B eval, deterministic scoring, linting, and rules-sync for the instruction files (CLAUDE.md/AGENTS.md/.cursorrules) that all agents now read โ skills-ops demand extends from SKILL.md files to the whole agent-config surface; (2) ONE true-new drift giant: xianyu110/awesome-openclaw-tutorial 4,565โ /677f, ZERO mentions, the CN guide lane's second face (book-published author), boarded. The push-sort windows were all-known-faces (roster coverage at 686 is now dense enough that today-push top-100s return ~zero un-rostered skill faces โ the drift class is starving; watch whether discovery yield shifts permanently to created-cuts + directories).**):, ๐ก SIGNALS:, Signals & flags summary...
How we test
Every skill goes through our testing pipeline. We're transparent about what we could and couldn't test. Each review is labeled with its test depth.
Read the docs, check the code
We load the full SKILL.md, every script, every reference file. We check dependencies, look for footguns, and map out what the skill actually does vs what it claims.
Test in an isolated sandbox
Every install runs inside a clean, throwaway Linux sandbox. Nothing touches our machine, and the full session (test script, commands, raw log) is published with the review so any reader can re-run the exact test that produced the verdict. When a skill can't be sandboxed (desktop apps, GPU-heavy workloads), we test live and explain why on the page. Every review labels its tier: sandboxed, hands-on, smoke test, or desk review.
Rate across four dimensions
1 to 5 gears each for docs, setup, value, reliability. No inflated scores. A 3 is average. Most skills land there.
Ship the verdict
KEEP IT, TRY IT, SKIP IT, or BROKEN. Popular skills get SKIP IT when they deserve it. Honest beats nice.
The skill install graveyard
Every hour spent untangling a broken skill is an hour not building. Here's what we catch before you do.
Why this exists
One weekend, one too many broken installs.
2
3
4
5
6
7
8
9
10
11
const broken = 12; // setup steps were wrong
const crashes = 6; // agent died on launch
const useful = 3; // actually saved time
if (broken + crashes > useful * 5) {
buildReviewSite("GearScope");
promise("no sponsors");
promise("real errors");
promise("honest ratings");
}
Questions you'll probably ask
Get the skill digest
The best and the broken from 100+ hands-on tests. One email a week.
Keep the reviews honest
No sponsors, no affiliate links โ 90+ hands-on reviews and counting. If one saved you an hour, kick back a fraction of it.