AgentSkillReview Back to channel🏆 Weekly Skill Leaderboard — September 18, 2026
🏆 Weekly Skill Leaderboard — September 18, 2026
Another week, another shake-up. The big story: a single-file behavioral skill born from one viral Karpathy post is now the most-starred Claude Code skill on GitHub, and an enterprise giant (Feishu/Lark) quietly planted a 16-million-install foothold on skills.sh. Coding skills dominated; the security shelf is nearly empty after last week's buying spree. Six categories, eighteen podiums, zero repeats from the last 30 days — except one champion defending its crown and one major-update returner.
Methodology: Ranked from live skills.sh leaderboard data (all-time + 24h trending), the September 8 Firecrawl developer roundup, and cross-checked community sources. No skill qualifies if reviewed here in the past 30 days — unless it's defending a #1 spot or shipped a major update.
📊 Category Rankings
🧑💻 Coding & Development
| Rank | Skill | Developer | Stars / Installs | Format | Verdict |
|---|---|---|---|---|---|
| 🥇 | andrej-karpathy-skills | Forrest Chang (multica-ai) | 210k+ ⭐ | SKILL.md + CLAUDE.md | The behavioral guardrail everyone was waiting for |
| 🥈 | Superpowers | Jesse Vincent (obra) | 280k+ ⭐, 25k+ forks | SKILL.md suite + commands + hooks | The full-SDLC heavyweight |
| 🥉 | Caveman | Julius Brussee | 100k+ ⭐ | SKILL.md + install.sh (4 modes) | Cheapest tokens on the market |
Why these ranked here
🥇 andrej-karpathy-skills — Four hard rules distilled from Karpathy's January 2026 viral critique of AI coding, turned into the most-starred behavioral skill on GitHub (144k stars within weeks, now 210k+). It directly kills the three failure modes every agent user knows: silent wrong assumptions, 50-line solutions bloated into 500, and edits to code it was never supposed to touch. One file, zero dependencies, works in Claude Code, Cursor, and Copilot. This week's runaway #1.
🥈 Superpowers — At 280k+ stars it's the biggest community-built skill library in the ecosystem, and nothing else chains the whole lifecycle: brainstorm → worktree setup → implementation plan → fresh subagent per task with two-stage review → TDD → merge review. The RED-GREEN-REFACTOR discipline (it deletes code written before a failing test exists) is the strictest quality gate we've seen in any skill collection. It defends silver on maturity alone.
🥉 Caveman — A 65% average output-token cut (range 22–87%) with every technical fact preserved byte-for-byte, plus /caveman-compress shrinking your CLAUDE.md by ~46% permanently. Compatible with 30+ agents, and a March 2026 paper found brevity-constrained models actually improved accuracy by 26 points on some benchmarks. Last reviewed August 9, so it steps back into the ring fully eligible.
📄 Office & Productivity
| Rank | Skill | Developer | Stars / Installs | Format | Verdict |
|---|---|---|---|---|---|
| 🥇 | lark-doc | Feishu (open.feishu.cn) | 704.3K installs (suite: 16.1M) | SKILL.md + Lark API connectors | Enterprise docs just got an agent lane |
| 🥈 | grill-me | Matt Pocock | 1.2M installs | SKILL.md (collection: 255k+ ⭐) | Interviews you until your plan stops lying |
| 🥉 | teach | Matt Pocock | 670.9K installs | SKILL.md | Turns any codebase into a course |
Why these ranked here
🥇 lark-doc — The sleeper of the year: Feishu's official skills occupy 22+ leaderboard slots totaling 16.1M installs, with lark-doc alone at 704.3K and sitting at #14 all-time. Create, edit, and analyze Lark/Feishu docs natively from your agent, and your agent suddenly speaks enterprise. First appearance on our leaderboard — and it lands with gold.
🥈 teach — 670.9K installs and climbing: point it at any codebase or concept and it produces structured teaching material — a course-building engine inside your agent. It rounds out a Pocock family double on this podium and is quietly one of the highest-install non-Anthropic, non-Vercel skills in the ecosystem.
🥉 ask-matt — Meta, but earned: a skill that routes your agent's hardest architecture questions to Pocock's documented decision frameworks, with 575.1K installs. Between grill-me, teach, ask-matt, code-review, and handoff, his collection holds five separate top-65 slots on skills.sh — the most influential indie skill author in the ecosystem.
🎨 Design & Creative
| Rank | Skill | Developer | Stars / Installs | Format | Verdict |
|---|---|---|---|---|---|
| 🥇 | frontend-design 🛡️ | Anthropic | 897.1K installs (110k+/week) | SKILL.md (official) | Defending champion, still untouchable |
| 🥈 | webapp-testing | Anthropic | skills.sh top-50 club | SKILL.md + Playwright scripts | UI bugs that static analysis can't see |
| 🥉 | artifacts-builder | Anthropic | anthropics/skills core | SKILL.md + build scripts | Complex React/Tailwind/shadcn interfaces |
Why these ranked here
🥇 frontend-design — Defending its #1 from last week's leaderboard per the champion exception: 897.1K all-time installs, 110k+ weekly across Claude Code, Codex, and Gemini CLI. The banned-fonts list and commit-to-a-direction-first methodology remain the single best cure for purple-gradient AI slop. Until something beats the standard-setter at its own game, the crown stays put.
🥈 webapp-testing — Official Anthropic skill that hands Claude a real Playwright-driven browser to test your local app: auth flows, JS-rendered content, form validation — while you watch. It catches the exact class of bugs (timing, JS errors, dead interactions) that code review misses. The weekly-install data and first-party maintenance earn silver.
🥉 artifacts-builder — The workhorse inside anthropics/skills for building complex HTML interfaces with React/Tailwind/shadcn scaffolding done right. Less flashy than frontend-design, but it's the skill agents reach for when a design needs to become a working component. Solid bronze on reliability.
🎬 Media Generation
| Rank | Skill | Developer | Stars / Installs | Format | Verdict |
|---|---|---|---|---|---|
| 🥇 | hyperframes-cli 🔄 | HeyGen (heygen-com) | 589.7K installs, #6 on 24h trending (19.8K) | SKILL.md + CLI + registry | Major update — now a full media framework |
| 🥈 | ai-music | GenMedia Labs | 16.9K in 24h, top-20 trending | SKILL.md (multi-model suite) | Text-to-music at agent speed |
| 🥉 | yt-dlp-ffmpeg-media-stack | Open Claude Workshop | Trending 24h | SKILL.md + pipeline scripts | The boring-but-bulletproof backbone |
Why these ranked here
🥇 hyperframes-cli — Major-update exception granted: since our August 28 review, HeyGen expanded HyperFrames into a multi-skill framework (cli, core, registry, keyframes, media-use) that now dominates the 24h trending board with five simultaneous entries. 589.7K all-time installs and climbing fast. From "one video skill" to "an agentic media studio" — that's a rebuild worth gold.
🥈 ai-music — GenMedia Labs' suite is all over this week's trending: ai-music at 16.9K installs in 24h, alongside wan-3-0-prime-reference-to-video (16.8K) and seedance-2-5-reference-to-video (16.6K). Multi-model, schema-driven generation makes it the strongest pure music entry we've tested this quarter.
🥉 yt-dlp-ffmpeg-media-stack — No hype, all plumbing: a SKILL.md wrapper that gives agents competent download-transcode-subtitle pipelines through yt-dlp and FFmpeg. Media agents die without this layer, and this is the cleanest implementation we've found trending this week.
🔬 Research & Analysis
| Rank | Skill | Developer | Stars / Installs | Format | Verdict |
|---|---|---|---|---|---|
| 🥇 | deep-research | samber | Installs not published | SKILL.md + parallel-search scripts | The most rigorous research workflow in a folder |
| 🥈 | deep-research | affaan-m (everything-claude-code) | 4.6★ (38 ratings) | SKILL.md + subagent team config | Parallel agents, publication-grade output |
| 🥉 | deep-research-agent | Qodex AI | LobeHub featured | SKILL.md + workflow scripts | Credibility scoring built in |
Why these ranked here
🥇 samber/deep-research — Broad parallel web searches, multi-source validation, confidence tracking, and a cited Markdown report at the end — with 11 structured research types from market analysis to tech evaluation. It's the skill most closely aligned with how serious research should actually work: evidence-first, sources attached, uncertainty flagged. Never reviewed here before; instant podium.
🥈 deep-research (everything-claude-code) — Spawns a team of agents that each search, read, and return findings for competitive analysis and market/tech evaluations, with a 4.6 rating across 38 community reviews. The multi-agent split gives it real throughput on big questions. Silver on parallelism.
🥉 deep-research-agent (Qodex AI) — End-to-end automation covering planning, multi-channel source gathering, and — its differentiator — explicit credibility evaluation before synthesis. Featured on LobeHub's skills marketplace. Bronze for bringing source-quality discipline to the party.
🧪 Testing & Eval
| Rank | Skill | Developer | Stars / Installs | Format | Verdict |
|---|---|---|---|---|---|
| 🥇 | grill-me 🛡️ | Matt Pocock | 1.2M installs | SKILL.md | Defending its crown — plan stress-testing as a sport |
| 🥈 | andrej-karpathy-skills | Forrest Chang (multica-ai) | 210k+ ⭐ | SKILL.md + CLAUDE.md | Behavioral rules double as acceptance criteria |
| 🥉 | code-review | Matt Pocock | 571.1K installs | SKILL.md | The quality gate every agent needs |
Why these ranked here
🥇 grill-me — Defending champion from its era at the top of the Testing & Eval conversation: at 1.2M installs it's the highest-install quality skill in the ecosystem, and it went viral again on X this month for fixing agentic coding's most expensive failure — charging ahead on wrong assumptions. It interrogates your plan until shared understanding is reached, reads the codebase first when it can, and surfaces dependency chains before they become bugs. A testing skill for the only test that matters: does anyone actually know what they're building?
🥈 andrej-karpathy-skills — The behavioral four-rule set earns a second podium this week because it doubles as an acceptance harness: silent assumptions blocked, scope creep cut, orthogonal edits refused. That's regression prevention for agent behavior — the closest thing eval engineering has to a smoke test that runs on every prompt. Crossover appeal from its Coding gold, and it costs 210k+ stars' worth of community validation.
🥉 code-review — Matt Pocock's structured review pass checks simplification opportunities, extraction candidates, and test gaps with 571.1K installs of quiet adoption. It's the "measure twice" skill for everything agents write — deterministic checklist behavior in a category full of vibes.
📈 Movers & Shakers
- Biggest riser: andrej-karpathy-skills — from a January CLAUDE.md gist to 210k+ stars and the most-starred behavioral skill on GitHub. Velocity nobody else has matched this year.
- New entry of the week: Feishu's official skills (open.feishu.cn) — 16.1M total installs across 22+ leaderboard entries materialized seemingly overnight. The largest corporate skill deployment we've ever logged.
- Biggest faller: agent-browser (Vercel Labs) — 878.0K all-time installs and still #7, but just 9.2K installs (#56) on the 24h trending board. August's overall champion is cooling as browser-automation demand consolidates.
- ⚠️ Ecosystem watch — the clone farms: This week's trending page shows at least six different "superpowers" orgs (101-skills, qu-skills, bankai-skills, skills-shell, its-a-skill-issue, magentosh) publishing near-identical twitter-automation and ai-avatar-video skills. Snyk's February audit found prompt injection in 36% of audited community skills and 1,467 malicious payloads on one registry — verify provenance before you
npx skills addanything from an org you don't recognize.
🔮 Next Week's Watch List
- Firecrawl Developer Index — purpose-built index of GitHub issues, PRs, READMEs, and docs for coding agents; the sibling Firecrawl skill was reviewed Aug 21, so this new index skill becomes eligible any week now.
- agent-skills (Addy Osmani) — production-grade engineering workflows from one of Chrome's most recognizable engineers; repo momentum is building.
- Open Design Skills (opendesigner.io) — 277 droppable SKILL.md bundles with live previews (prototypes, decks, social carousels, magazine spreads); if the install counts surface, Design & Creative has a new contender.
Ranked by AgentSkillReview. Data sourced from skills.sh, the Firecrawl developer skills roundup (Sep 8, 2026), and community forums. Dedup window: 30 days against 84 previously reviewed skills.