{"slug": "captain-caveman-claude", "title": "Captain Caveman Claude", "summary": "A developer has released \"Claude-ITect-Skill,\" a one-command starter pack that installs 54 skills, 4 agent definitions, and 6 hook files into any project's `.claude/` directory. The tool includes a \"caveman\" family of skills that reduces token usage by roughly 75% while maintaining technical accuracy, along with auto-triggering workflow orchestration skills and engineering skills for tasks like debugging and issue tracking. The pack supports both PowerShell for Windows and bash for macOS/Linux, with flags for force installation and skipping hooks.", "body_md": "\"People assume that configuration is a strict progression of cause to effect, but actually, from a non-linear, non-subjective viewpoint, it's more like a big ball of wibbly-wobbly... skilly-willy... stuff.\"\n\n— a Time Lord, probably, if Time Lords shipped install scripts\n\nThere is a particular flavor of pain known only to people who run Claude Code seriously: the slow, soul-eroding ritual of configuring fifty-one little things by hand. You wire one hook. You forget the second. You discover the third only exists in a Discord message from four months ago. Somewhere, a yak grows another inch of fur specifically so you can shave it.\n\n`Claude-ITect-Skill`\n\nexists to make that ritual unnecessary. It is a one-command starter pack that drops a curated arsenal of skills, agents, and session hooks into any project's `.claude/`\n\ndirectory, and then, with the smug confidence of someone who has clearly been burned before, tells you to run `/audit`\n\nto make sure it actually worked. The author calls people like himself \"Claude-ITects™,\" which the industry refuses to call us, and honestly, after using this, the industry should reconsider.\n\nThis is the update, the *regeneration*, if you will. Same face-of-the-project, new internals. Let's open the TARDIS doors and see how much bigger it is on the inside.\n\nInstall it. It deposits a `.claude/`\n\nfolder containing **54 skills, 4 agent definitions, and 6 hook files** into your project, patches your `settings.json`\n\nto wire up the session hooks, and gets out of your way. The README's entire onboarding flow is two words long: run `audit`\n\n. That restraint is the first sign you're dealing with someone who has actually used the thing he built rather than someone who just wanted a README with a lot of headers.\n\nThe install story is genuinely good. PowerShell for Windows, bash for macOS/Linux, sensible `--force`\n\nand `--skip-hooks`\n\nflags, and a thoughtful `-ProjectPath`\n\noption so you can aim it at a project other than your current directory. The `-ExecutionPolicy Bypass`\n\nnote even reassures nervous Windows users that nothing permanent is happening to their system. It's the kind of small kindness that separates a tool someone made *for themselves* from a tool someone made *for other people too*.\n\nThe 54 skills are organized into sensible tribes, which is where Captain Caveman would put down his club and nod approvingly. (Captain Caaaaaveman! Sorry. It happens.)\n\n**Superpowers — the workflow orchestration layer.** This is the cleverest part of the whole pack and the part that most people will underestimate. Fourteen skills that *auto-trigger at key moments* rather than waiting to be summoned. `brainstorming`\n\nfires before implementation. `systematic-debugging`\n\nruns a real hypothesis loop. `verification-before-completion`\n\nis the digital equivalent of a Weeping Angel standing behind you whispering *\"don't declare it done yet.\"* These aren't tools you reach for; they're behavioral guardrails that shape the agent before it does anything dumb. Borrowed and adapted from the excellent `superpowers`\n\nproject, they're the connective tissue of the pack.\n\n**Engineering.** Ten skills covering the unglamorous, load-bearing parts of real work: `diagnose`\n\n(reproduce → minimise → hypothesise → fix → regression-test, a loop with actual discipline), `to-prd`\n\nand `to-issues`\n\nfor turning a conversation into shippable GitHub work, `improve-codebase-architecture`\n\n, `zoom-out`\n\nfor when you've been heads-down so long you've forgotten whether the approach was ever correct. This is the section that earns the \"architect\" in Claude-ITect.\n\n**Caveman — token compression.** Here is the headline act, and the source of every pun in this review. The caveman family cuts token usage by roughly 75% while keeping full technical accuracy, communicating in a deliberately compressed register with modes named `lite`\n\n, `full`\n\n, `ultra`\n\n, and the gloriously over-the-top `wenyan-*`\n\n. There's `caveman-commit`\n\nfor compressed commit messages, `caveman-review`\n\nfor terse PR comments, and `caveman-stats`\n\nto show you the real token savings from your session log. Unga bunga, big save. This is the feature that justifies the whole bundle existing, because token efficiency isn't a nice-to-have at scale, it's the difference between a session that finishes and a session that runs out of context two steps from the finish line.\n\n**The CaveCrew agents.** Four subagents, three of them genuinely well-scoped:\n\n`file:line`\n\ntable and, crucially, offers no fix suggestions. It finds; it does not editorialize.**The rest:** utilities (`adr`\n\n, `audit`\n\n, `tools`\n\n, `phase`\n\n, `setup-pre-commit`\n\n), productivity (`grill-me`\n\n, the relentless interview skill that stress-tests your plans until they cry), and a small writing suite (`edit-article`\n\n, `writing-beats`\n\n, `writing-shape`\n\n). Plus `thefuck`\n\n, which diagnoses your last failed shell command and proposes the correct one — and, refreshingly, *never executes destructive corrections silently.* It confirms first. Even the joke tool has manners.\n\nThree design decisions stand out as evidence of real taste rather than just enthusiasm.\n\nFirst, **audit-first onboarding.** Most skill packs assume installation equals success. This one ships duplicate skills *on purpose* so the `/audit`\n\nskill has something to react to, verifying that the pack nests cleanly inside whatever skills your repo already has. That's a tool designed to survive contact with a messy real-world project, not a pristine demo repo.\n\nSecond, **agents that refuse.** The Builder's hard cap on file count and the Reviewer's no-praise rule are constraints, and constraints are where quality lives. A sonic screwdriver that did literally everything would be a worse plot device; the good ones have rules.\n\nThird, **readable-code discipline runs underneath everything.** The `karpathy`\n\nskill operates as an internal reasoning layer, and the broader architecture leans on three-law readable-code rules and ADR-backed decisions. The pack doesn't just generate code — it generates code it can stand behind later.\n\nThe best part about reviewing something built in public is that the rough edges aren't flaws, they're the next update, just sitting there waiting to be claimed. Here are a few friendly ones, offered in the spirit of *\"Because I ran out of time, and couldn't shipt them myself.\"*\n\n**Lock the headline number down.** The skill count appears in a couple of places and they don't all agree yet, the live README says **54**. For a project whose whole charm is \"you don't have to track 54 things by hand,\" making that number identical everywhere is a five-minute win that'll make the front page feel airtight. Pick the true count, paste it everywhere, never blink.\n\n**The em-dash easter egg.** v1 shipped a `check-encoding.js`\n\nhook that cheerfully *blocked any file write containing em-dashes or smart quotes.* If you want the cosmic balance restored, it's a perfect first task to hand to `/audit`\n\n. (Or not. Some of us think the dashes earned their place.)\n\n**Let the personal bits raise their hand.** The Geometry Solver agent and the Project Specific pieces are deeply specific to the author's own engine, and the README is refreshingly upfront that the NgonENGINE commands stay opt-in. That honesty is exactly right. The natural next step is letting the install flow *ask* which flavor of Claude-ITect you are, so the bespoke bits show up only for the people who'll cheer to see them. The author already wants this thing custom to whoever's using it, which is the whole reason it has a soul in the first place.\n\nNone of these are knocks. Every great TARDIS starts as a battered blue box that somebody loved enough to keep flying.\n\n`Claude-ITect-Skill`\n\nis what happens when someone who actually does the work gets tired of doing the *setup* for the work; and then, instead of grumbling about it forever, fixes it once, properly, and hands the fix to everyone else for free. That generosity is the throughline. The caveman compression layer alone is worth the install. The superpowers orchestration is the quiet genius humming underneath. The CaveCrew agents demonstrate the rarest virtue in any tool, knowing what to refuse. And the whole pack carries a readable-code, ADR-backed discipline that means it generates work it can still stand behind a month later.\n\nIt's an arsenal assembled by one practitioner with real taste and then opened up to the rest of us, inside jokes and all. If you run Claude Code and you've ever felt that yak-shaving despair, that slow drip of *one more thing to configure*; clone it, run the install, and (say it with me) run `/audit`\n\n. You'll be set up in the time it takes to make coffee.\n\nThen go build something wonderful. The clubs are optional. The token savings are not. Captain Caaaaaveman would be proud.\n\n*Written against the live repository: 54 skills, 4 agents, 6 hooks. Numbers subject to regeneration without notice.*\n\nAre you a Claude Architect or as the industry refuses to call us: Claude-ITects™ Good. You're in the right place.\n\nWelcome to Claude-ITect-Skill\nThe \"I don't want to configure 54 things manually\" starter pack for [Claude Code](https://claude.ai/code).\nPowered by Captain Caveman energy -- one club, infinite tools, zero yak-shaving.\n\nWhat you get (whether you deserve it or not):\n\nBut don't get distracted by the features.\n\nThe real sorcery happens during setup when everything just… works.\n\nNo funny dances. No ritual sacrifices.\n\nInstall it. Try it. Judge me harshly afterward.\n\nAfter installation start with these skills:\n\n`/onboard`\n\n<- run first`/audit`\n\n<- run next", "url": "https://wpnews.pro/news/captain-caveman-claude", "canonical_source": "https://dev.to/scythe2/captain-caveman-claude-nng", "published_at": "2026-05-29 15:38:43+00:00", "updated_at": "2026-05-29 16:13:51.993872+00:00", "lang": "en", "topics": ["ai-tools", "ai-agents", "ai-infrastructure", "ai-products", "mlops"], "entities": ["Claude Code", "Claude-ITect-Skill", "Claude-ITects", "Discord"], "alternates": {"html": "https://wpnews.pro/news/captain-caveman-claude", "markdown": "https://wpnews.pro/news/captain-caveman-claude.md", "text": "https://wpnews.pro/news/captain-caveman-claude.txt", "jsonld": "https://wpnews.pro/news/captain-caveman-claude.jsonld"}}