Loading video...

Video Failed to Load

Go Home

Claude Code just shipped a new /skill-doctor command It shows which skills are loaded in your session, which ones haven’t been used, and how many context tokens each is costing you Now you know exactly what to remove

70,188 views • 1 month ago •via X (Twitter)

26 Comments

suqitah's profile picture
suqitah1 month ago

the unused skill list is the real feature, most people's setup is just cruft nobody prunes

Yuv Bindal's profile picture
Yuv Bindal1 month ago

tracking token cost per skill is clever, let's connect soon

Luis's profile picture
Luis1 month ago

After using Astra yesterday, I'm starting to think figuring out which instructions to remove matters as much as knowing what to add. I'm doing a full cleanup of my skills and agent instructions now. Astra in Codex feels like a new platform.

Gabriele Spata's profile picture
Gabriele Spata1 month ago

cost visibility is good, it just answers what's expensive, not what's working

9h0st's profile picture
9h0st1 month ago

skill-doctor 最有用的输出不只是“删哪些技能”,而是按触发频率/上下文成本/实际收益排序;高 token 但低命中率的规则,应该先懒加载或拆到子技能。

Ehsan Azish's profile picture
Ehsan Azish1 month ago

a command whose whole job is telling you what to delete, that's a first for a cli tool

Tri's profile picture
Tri1 month ago

cc @wjayesh

elian's profile picture
elian1 month ago

pr #867 for a slash command, this repo moves faster than most seed stage roadmaps

Hussain Hashim | Building SundayBack's profile picture
Hussain Hashim | Building SundayBack1 month ago

@dani_avila7 love it! it’s like decluttering for your AI setup. this would've saved me so much time debugging last month!

Ned Palmer's profile picture
Ned Palmer1 month ago

Now if only I could actually delete shared skills, that would be great. Also better organization of org level skills so you can limit them to LOBs not the entire firm.

Marwan Atef's profile picture
Marwan Atef1 month ago

skill-doctor is the audit every agent stack was missing. load list, unused skills, token burn per skill. finally a reason to prune the skill graveyard instead of pretending it is free context.

Catalin's profile picture
Catalin1 month ago

Great thanks

Umang's profile picture
Umang1 month ago

“Last used: never” as the default row is a pretty good roast of most Claude Code setups.

weigi's profile picture
weigi1 month ago

this is such a good diagnostic — seeing unused skills and their context cost makes cleanup way less guessy

Vishnu Aniyan's profile picture
Vishnu Aniyan1 month ago

Is this the same as /doctor ?

AI Mastery Guide's profile picture
AI Mastery Guide1 month ago

skill doctor is exactly what i needed

Saikat | GoShipped's profile picture
Saikat | GoShipped1 month ago

This is a good feature to have. Spending unnecessary tokens is like a death warrant.

Silk Song's profile picture
Silk Song1 month ago

Why is the command reporting usage reports are not available on this connection

Mircea Sandu's profile picture
Mircea Sandu1 month ago

nice! maybe this will finally convince me to try removing all my skills and adding them back as needed

👽 John Mac's profile picture
👽 John Mac1 month ago

Quite lovely Sir! Been waiting for this. Thanks for being a news channel worth paying attention to.

Chaminda's profile picture
Chaminda1 month ago

unused this session and unused are different things. the skill you only load during an incident will look like dead weight.

Bessi with black hoodie's profile picture
Bessi with black hoodie1 month ago

I've left dead skills loaded for weeks. /skill-doctor is the cleanup I needed.

Cikocisco's profile picture
Cikocisco1 month ago

Handy. But does it flag skills silently bloating context without pulling weight? Or just list 'em?

MARUF's profile picture
MARUF1 month ago

pruning unused context tokens saves money and avoids hallucinations

John Rood's profile picture
John Rood1 month ago

unused in one session doesn't mean removable. rare guardrails and dead weight look identical at the token-count level. the doctor needs to show which skill prevented which failure.

Monaal's profile picture
Monaal1 month ago

token count is only the first part of what a skill costs. Cached and uncached input bill at different rates, so a large skill sitting in a stable prefix is far cheaper than the raw number suggests. And a rarely-used one may be preventing a failure that only shows up downstream.

Related Videos

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this

Yarchi

56,568 views • 4 months ago

this is pure f*cking treasure Anthropic devs just posted 20 GitHub repos that turn your Claude Code into a f*cking engineering team: Exposed for Opus 5.5 1. rtk: squeezes command output before it hits your context. the authors claim 60-90% fewer tokens 2. claude-mem: memory across sessions. records what the agent did and brings back what matters 3. ccusage: shows where your tokens and money went. one command, npx ccusage 4. Serena: search and edit code by meaning, not by text 5. Context7: up-to-date library docs, so Claude stops writing for last year's API 6. claude-context: your whole codebase searchable through MCP 7. Repomix: packs an entire repo into one AI-friendly file skills and method 8. superpowers: a skills framework and a full development methodology. the one almost everyone installs 9. skills: the official Agent Skills repo from Anthropic 10. spec-kit: spec-driven development, from GitHub itself 11. agents: a plugin marketplace for Claude Code and six other harnesses 12. claude-code-templates: ready configs and monitoring from one CLI 13. claude-code-hooks-mastery: hooks explained with working examples 14. awesome-claude-code: the hand-picked map of everything else running more than one agent 15. container-use: a separate container for every agent, so they stop breaking each other 16. claude-squad: several terminal agents in one window 17. Happy: control your agents from your phone, iOS and Android 18. claude-code-router: route requests across different models 19. ccstatusline: a status line that shows what your session is doing 20. tweakcc: edit Claude Code's own system prompts, toolsets and themes the stack in one line: memory keeps the context, skills set the method, containers let you run five agents instead of one. check each repo before you install. save this.

kiosa

70,094 views • 23 days ago