caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
TurinTech AI Artemis - code optimization, analysis, and validation at scale
Plugin artemis from marketplace skills in turintech/skills. Commands read from the repo's manifest — 29 days ago.
artemisClassify an Artemis request, check workflow readiness, surface consequential choices before long-running work begins, and route to the appropriate task-specific skills. Use whenever a user wants to set up, run, resume, inspect, validate, optimize, or maintain code with Artemis.
change-validateCheck whether a local code change really makes a project faster (or better on any metric), measured on an Artemis runner. Puts the uncommitted change on a new Artemis branch, measures the starting commit and the change the same number of times on the same runner and script, and reports the platform'
cli-follow-alongWhile the CLI does the work, show the user the Artemis Web UI page that matches each step, in one browser tab, navigating only. Use when the user has chosen to follow along in their browser and a browser-control tool such as Claude in Chrome is connected. Do not use it to change settings or start wo
cli-setupInstall, update, and authenticate the Artemis CLI by direct download from the Artemis file server, then log in with an API key the user creates. Use when the CLI is missing, older than the skills' minimum, or not signed in to the target deployment, and once per session to check that the Artemis skil
discovery-inspectInspect and interpret the results of an Artemis discovery run — is it done, did versions actually pass, what are the real numbers, and what code changed. Use when the user wants to check on a discovery run, read its results, see which versions won, or understand why a run produced nothing.
discovery-startStart an Artemis discovery run: create a Script, pass it to discovery create, wait for the baseline to finalize, and verify it actually explored. Use when the user wants to start discovery, launch a discovery run, or create a discovery experiment.
discovery-steerContinue, expand, or redirect an Artemis discovery run, verify its child agent run was attached, and check whether later experiments follow new guidance. Use when the user wants to add budget, steer, redirect, or change the focus of an existing discovery run.
discovery-visualizeCollect a normalized Artemis discovery snapshot and render it as a host-native chart or report. Use when the user wants to graph, chart, plot, compare, visualize, or build a discovery report, canvas, or artifact from a discovery run, or chart a project's Maintain issues by severity and triage.
execution-log-inspectRetrieve and interpret Artemis runner task logs through the platform when compile, test, benchmark, validation, or Discovery execution fails. It reads the task's own output through the platform, with or without access to the runner host.
maintainRun Artemis Maintain end to end on a project. Author or import Rules, Scan the code for Issues, triage them, fix them with the fix agent, in Discovery or with your own coding agent, ship each fix as a branch or PR, and re-sync outdated Issues as the code moves on. Use when the user wants to scan a p
platform-tourShow someone how to do a task on the Artemis platform by doing it in their Chrome while they watch, through the Web UI and without the CLI. Use only when the user asks to be shown in their browser ("show me in my browser", "use computer use", "give me a tour of the platform"), names this skill, or a
project-importImport an existing remote Git repository into Artemis as a fresh project, using an explicit branch and reusable Git credential, then capture and verify the project UUID. Use when a repository is ready for a new unit of Artemis work, even if other projects already exist for the same repository.
quickstartTake a user to a first measured Artemis result from wherever they are starting, whether a machine with nothing installed, a returning user with a new project, a repository that is not yet a project, or an existing project URL or id. Works in the terminal by default, offers to show each step in the b
repo-command-setupDerive, verify, and configure a project Script's commands: the build and test that gate Discovery, and a benchmark that writes numeric artemis_results metrics. Use when preparing a repository for validation or discovery, making a repo Discovery-ready, authoring a benchmark harness, fixing project co
runner-setupInstall, register, start, update, and verify a supported Artemis custom runner. Use when an end user needs to set up or manage a runner.
workspace-setupPrepare and verify a runner-owned persistent build workspace for Artemis. Use when a clean build of each version is prohibitively expensive, a repository needs incremental builds, or compile/test/benchmark commands must bridge Artemis task checkouts into a stable cache.
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.