Claude Code skills
Hacker ApprovedRanked 6 of 23 agent skills by recommenders
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.
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.
26 people gave an opinion
- recommend it
- 21
- criticize it
- 5
- approval share
- 81%
Recommended in 8 of 13 months
- November 2025: recommended
- December 2025: not recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: not recommended
- July 2026: recommended
- August 2026: not recommended
- September 2026: recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 21 people recommend itNeeds 10 or more, met.
- 4.2 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 8 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Loads context only on demand
“it's cool because the llm will load the whole context on how to use it only on demand”
Comment from 10 Feb 2026 in “ClawHub” “The skill lets you compress the amount loaded to just the briefest description”
Comment from 2 Nov 2025 in “How I use every Claude Code feature” Packages repeatable workflows as commands
“Skills are basically like scripts for LLMs - package repeatable behavior into single commands.”
Comment from 17 Apr 2026 in “Claude Opus 4.7” “It's just a shortcut so you don't have to keep rewriting a prompt all over again”
Comment from 27 Mar 2026 in “Anatomy of the .claude/ Folder” “Skills on the other hand are commands ON STEROIDS.”
Comment from 7 Jan 2026 in “Opus 4.5 is going to change everything” - Comment from 11 Jul 2026 in “Write code like a human will maintain it”
Tested process, fewer surprises
“The agent follows a tested process instead of guessing and leads to fewer surprises.”
Comment from 22 Mar 2026 in “Claude Code and the Great Productivity Panic of 2026” “Having a "mvvm" rule and skill that defines the boundaries keeps the llm from writing a bunch of nonsense code that happens to work.”
Comment from 28 Mar 2026 in “Anatomy of the .claude/ Folder” Easy to set up
“This takes 10 minutes to set up, you just need to run something like /skill-builder and describe the desired workflow.”
Comment from 8 May 2026 in “Agents need control flow, not more prompts” “The easiest way to on-ramp people to try it out for the first time is to write a claude code skill.”
Comment from 22 Mar 2026 in “Professional video editing, right in the browser with WebGPU and WASM”
What people warn about
Each mark is one comment
Claude doesn't reliably activate skills
“Skills seem like the way forward, but Claude still needs to be convinced to activate the skill.”
Comment from 2 Nov 2025 in “How I use every Claude Code feature” “skills are definitely not working even on the initial prompt of a new session”
Comment from 25 Nov 2025 in “Claude Advanced Tool Use”
Other agent skills people recommend
The four most recommended other agent skills, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Superpowers | 138 | 72 | 66% | 12 | 4 mo7 owners | — |
| Claude Skills | 59 | 26 | 69% | 11 | — | Approved |
| grill-me skill by Matt Pocock | 39 | 2 | 95% | 8 | — | Approved |
| Get Shit Done | 31 | 32 | 49% | 7 | — | — |
| Claude Code skillsThis page | 21 | 5 | 81% | 8 | — | Approved |
What people said
All 27 comments that mention it, newest first. Each links to the original comment.
“Stuff that would have taken me months, maybe a year, of solo work got done super fast.”
“You should use skills instead of commands”
“reproducing cargo cult practices that are only suited for certain use cases”
“It's obviously something that can be done as a python or bash+jq script and run deterministically.”
“This takes 10 minutes to set up, you just need to run something like /skill-builder and describe the desired workflow.”
“Skills are basically like scripts for LLMs - package repeatable behavior into single commands.”
“Having a "mvvm" rule and skill that defines the boundaries keeps the llm from writing a bunch of nonsense code that happens to work.”
“It's just a shortcut so you don't have to keep rewriting a prompt all over again”
“The easiest way to on-ramp people to try it out for the first time is to write a claude code skill.”
“The agent follows a tested process instead of guessing and leads to fewer surprises.”
“a Claude skills pipeline would help move things faster”
“one-shoting games WITH ASSETS.. seems pretty impressive to me.”
“can't even produce a single decent game”
“This works in my experience”
“I have not had much success with skills that have tree based logic (if a do x, else do y), they just tend to do everything in the skill”
“they still need an out-of-band process to keep them updated as the codebase evolves”
“it's cool because the llm will load the whole context on how to use it only on demand”
“Subagents/MCP/Skills are all pretty mid”
“Skills on the other hand are commands ON STEROIDS.”
“they blew me away, because I wasn't aware that those skills are injected automatically”
“Claude offers a fantastic way for this using "skills" and now a "marketplace"”
“skills are definitely not working even on the initial prompt of a new session”
“skills are superior to MCP”
“Skills seem like the way forward, but Claude still needs to be convinced to activate the skill.”
“They are composable and you can build the logic table of when an instance is”
“The skill lets you compress the amount loaded to just the briefest description”
“I'm excited for it not really as a "new thing" (as mentioned in the post)”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.