# Claude Code skills Hacker Approved page: https://hackerapproved.com/p/claude-code-skills/ 17 people recommended Claude Code skills in Hacker News comments, 3 had mixed feelings and 4 criticized it, November 2025 to October 2026. It was recommended in 8 of 12 months, in 14 threads. It meets the Hacker Approved badge rule. **Verdict:** People recommend Claude Code skills for packaging repeatable workflows into reusable commands that load only when needed. The most common caveat is that Claude sometimes fails to activate them. Summary written by Claude from 27 comments. It was written before the November 2026 recount, and 25 of those comments still count. ## Why people recommend it - Packages repeatable workflows as commands (4 comments in the sample): "Skills are basically like scripts for LLMs - package repeatable behavior into single commands." ([source](https://news.ycombinator.com/item?id=47808424)) "It's just a shortcut so you don't have to keep rewriting a prompt all over again" ([source](https://news.ycombinator.com/item?id=47549030)) "Skills on the other hand are commands ON STEROIDS." ([source](https://news.ycombinator.com/item?id=46531548)) - Loads context only on demand (2 comments in the sample): "it's cool because the llm will load the whole context on how to use it only on demand" ([source](https://news.ycombinator.com/item?id=46964347)) "The skill lets you compress the amount loaded to just the briefest description" ([source](https://news.ycombinator.com/item?id=45787798)) - Tested process, fewer surprises (2 comments in the sample): "The agent follows a tested process instead of guessing and leads to fewer surprises." ([source](https://news.ycombinator.com/item?id=47475932)) "Having a "mvvm" rule and skill that defines the boundaries keeps the llm from writing a bunch of nonsense code that happens to work." ([source](https://news.ycombinator.com/item?id=47554762)) - Easy to set up (2 comments in the sample): "This takes 10 minutes to set up, you just need to run something like /skill-builder and describe the desired workflow." ([source](https://news.ycombinator.com/item?id=48061086)) "The easiest way to on-ramp people to try it out for the first time is to write a claude code skill." ([source](https://news.ycombinator.com/item?id=47477006)) ## What people warn about - Claude doesn't reliably activate skills (2 comments in the sample): "Skills seem like the way forward, but Claude still needs to be convinced to activate the skill." ([source](https://news.ycombinator.com/item?id=45793897)) "skills are definitely not working even on the initial prompt of a new session" ([source](https://news.ycombinator.com/item?id=46045902)) ## Other agent skills people recommend - [Superpowers](https://hackerapproved.com/p/superpowers/): 105 recommend, 24 mixed, 71 criticize - [Claude Skills](https://hackerapproved.com/p/claude-skills/): 46 recommend, 9 mixed, 23 criticize - [grill-me skill by Matt Pocock](https://hackerapproved.com/p/grill-me-skill/): 36 recommend, 2 mixed, 2 criticize - [Matt Pocock's skills](https://hackerapproved.com/p/matt-pocock-s-skills/): 24 recommend, 2 mixed, 2 criticize ## The badge A product earns the Hacker Approved badge when at least 10 people recommend it, recommenders outnumber critics at least 2 to 1 (mixed feelings count toward neither side), it was recommended in at least 4 of the 12 months and in at least 5 different threads, and no single thread supplies more than half of the people who recommend it. Health and money products are never badged. ## Cite as Hacker Approved, "Claude Code skills", https://hackerapproved.com/p/claude-code-skills/ (17 recommend, 3 mixed, 4 criticize; Hacker News comments, November 2025 to October 2026). Counts updated 2 Nov 2026, with data through October 31, 2026.