Skill & MCP deep dives
We read the actual SKILL.md and source files of the most-installed agent skills and MCP servers, quote them line by line, and report what they really make your agent do.
Every quote is verified against the origin on the day we publish and links to the exact commit and lines it came from, or, for skills served off-registry from a vendor domain, to the canonical file and the date we verified it. Read how we write a deep dive. Ranked adoption data lives on the Top 25 leaderboard; how-to articles live in the guides. A deep dive is the third thing: what the file actually says.
13 deep dives published so far, newest first. Every quote is verified against the origin repo before publishing.
Deep dive: how does video-edit actually work?
video-edit is RunComfy's agent skill for editing existing video from a coding agent: restyle a clip, swap a background, transfer motion from a reference. It has 405,497 installs as of August 20, 2026 (Skillselion catalog). Its primary job is choosing which paid model to spend your money on, and most of its links are tagged so RunComfy can attribute the click.
Deep dive: how does impeccable actually work?
impeccable is Paul Bakaus's agent skill that hands your coding agent a design director's judgment and twenty-three named commands to apply it with. It has 238,573 installs as of August 20, 2026 (Skillselion catalog) and is one of the fastest-trending skills in search. It also has a second life: a licensed rebrand of its playbooks, published under a different name, currently out-installs the original in our own catalog.
Deep dive: how does supabase-postgres-best-practices actually work?
supabase-postgres-best-practices is Supabase's agent skill that loads Postgres rules into your agent before it writes SQL, designs a schema, or ships a migration. It has 356,210 installs as of August 19, 2026 (Skillselion catalog). The most interesting thing about it is not any single rule: it is that this file and Vercel's React skill are the same document with different subject matter, and Vercel published the shape first.
Deep dive: how does design-taste-frontend actually work?
design-taste-frontend (the file calls itself "tasteskill") is an agent skill that fights AI-looking landing pages with rules specific enough to grep for. It has 374,370 installs as of August 20, 2026 (Skillselion catalog). Where the top skills ship thin routers, this one ships the whole doctrine in a single 1,206-line SKILL.md, and its sharpest rules are mechanical checks, not vibes.
Deep dive: how does caveman actually work?
caveman is an agent skill that makes your agent answer in ultra-compressed caveman speak ("Bug in auth middleware. Fix:") while keeping every technical fact intact. It has 3,148 installs as of August 19, 2026 (Skillselion catalog) and is one of the fastest-trending skills in search. The joke lands, but the file underneath is serious token engineering, down to tokenizer-level measurements.
Deep dive: how does microsoft-foundry actually work?
microsoft-foundry is Microsoft's official agent skill for running their Foundry AI platform from a coding agent: provisioning, deploying agents, evaluating them, fine-tuning models, managing quota and RBAC. It has 537,735 installs as of August 20, 2026. It is less a skill than a platform operating manual: 187 files, twenty sub-skills, its own version number, and an installer script it runs the moment it loads.
Deep dive: how does lark-doc actually work?
lark-doc is ByteDance's agent skill for reading, creating, and editing Lark/Feishu cloud documents from a coding agent, and it is unlike anything else near the top of the catalog: the file is written in Chinese, requires a vendor CLI binary, is served from the vendor's own domain instead of GitHub, and leads a 27-skill suite. It has 590,814 installs as of August 19, 2026.
Deep dive: how does vercel-react-best-practices actually work?
vercel-react-best-practices is Vercel Engineering's agent skill that turns their internal React and Next.js performance doctrine into rules your coding agent applies while it writes, reviews, or refactors code. It has 643,942 installs as of August 20, 2026. Unlike the shims we have covered in this series, this one ships the entire method: 70 rule files, a priority order, and a build pipeline that compiles and tests them.
Deep dive: how does grill-with-docs actually work?
grill-with-docs is Matt Pocock's agent skill that runs the same relentless planning interview as grill-me, and writes the documentation while you talk: a glossary of your project's terms and architecture decision records. It has 763,728 installs as of August 20, 2026. The installed file is seven lines long and composes two other skills to do it.
Deep dive: how does agent-browser actually work?
agent-browser is Vercel Labs' agent skill that gives your coding agent a real browser: navigate, click, fill forms, extract data, take screenshots, all from a CLI. It has 697,825 installs as of August 20, 2026. And the installed file is not the manual: it is a 52-line discovery stub telling the agent to fetch real instructions from the CLI at runtime.
Deep dive: how does grill-me actually work?
grill-me is Matt Pocock's agent skill that makes your coding agent interview you relentlessly about a plan or design before it writes any code. It has 897,689 installs as of August 20, 2026. Here is the part almost nobody who installed it knows: the file is seven lines long, and its only instruction hands off to a sibling skill called grilling, where the whole method lives.
Deep dive: how does Anthropic's frontend-design skill actually work?
frontend-design is Anthropic's official agent skill for making AI-built web UI look designed instead of templated. It casts your agent as a design lead at a small studio, forces a token-system design plan before any code, and names the three cliché "AI looks" to steer away from, hex codes included. It has 792,364 installs as of August 2026 (Skillselion catalog), the third most-installed skill overall.
Deep dive: how does find-skills actually work?
find-skills is a Vercel Labs agent skill that turns your coding agent into a skill-discovery assistant. When you ask "how do I do X", the agent searches the open skills ecosystem with the
npx skillsCLI, vets the results by install count and source reputation, and offers to install the best match. It has 3,009,777 installs as of August 2026 (Skillselion catalog), which makes it the most-installed agent skill in existence.