evals
Skill21k starsChanged todayLicence not identifiedView on GitHub
The Kortix eval system (flag `evals`): Harbor-format tasks, suites under `evals:` in kortix.yaml, the trial runner on the worker, scoring, the Evals page, `kortix evals`, and the My Kortix benchmark in evals/my-kortix. Load before you change anything under apps/api/src/projects/evals, routes/evals.ts, worker/jobs/eval-runner.ts, packages/api-contract/src/evals.ts, packages/manifest-schema/src/evals.ts, the SDK evals client or hooks, apps/cli/src/commands/evals.ts, apps/web/src/features/workspace/evals or evals/; before you change My Kortix (run its benchmark before and after); and when an eval job hangs, errors or scores wrong.
- Reads credentials
9 other projects use a version of this.
Trending
More talk lately.thin dataabout the whole repository
Most recently taken up by
- kortix-ai/sunaword for word, first seen Nov 15, 2026
- scottlivingston/claude-skillstheir own version, first seen Nov 8, 2026
- renzrollon/interlocktheir own version, first seen Nov 5, 2026
- jstilb/ai-assistanttheir own version, first seen Nov 1, 2026
- rterakedis/leanwheel-skillstheir own version, first seen Oct 17, 2026
- muggl3mind/career-managertheir own version, first seen Oct 1, 2026
Who's talking about kortix-ai/CompanyOS
- @github-trending-js.bsky.social“📦 kortix-ai / CompanyOS ⭐ 20,553 (+92) 🗒 TypeScript Kortix CompanyOS – the open-source operating system …”Bluesky · Nov 8, 2026 · 3 likes
- sudosubin/agents.nix“agent-skills.github.kortix-ai.companyos: 0.15.1 → 0.15.2”GitHub · Nov 9, 2026
- ARUNAGIRINATHAN-K/awesome-ai-agents-2026“🔗 Broken links detected”GitHub · Nov 8, 2026
- sudosubin/agents.nix“agent-skills.github.kortix-ai.companyos: 0.15.0 → 0.15.1”GitHub · Nov 7, 2026
- 1shiharat/awesome-agent-clients“Add Kortix to Web & self-hosted dashboards”GitHub · Nov 7, 2026
The biggest 5 of 11 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 11
Talked about on GitHub, the web and Bluesky (11 times).
On GitHub · 8
- Nov 9, 2026agent-skills.github.kortix-ai.companyos: 0.15.1 → 0.15.2 — sudosubin/agents.nix0 reactions
- Nov 8, 2026🔗 Broken links detected — ARUNAGIRINATHAN-K/awesome-ai-agents-20260 reactions
- Nov 7, 2026agent-skills.github.kortix-ai.companyos: 0.15.0 → 0.15.1 — sudosubin/agents.nix0 reactions
- Nov 7, 2026Add Kortix to Web & self-hosted dashboards — 1shiharat/awesome-agent-clients0 reactions · 1 comment
- Nov 6, 2026agent-skills.github.kortix-ai.companyos: 0.14.19 → 0.15.0 — sudosubin/agents.nix0 reactions
3 more on GitHub
- Nov 6, 2026Add Kortix to Human Approval and Workflow Control — natnew/awesome-agentops0 reactions
- Nov 4, 2026agent-skills.github.kortix-ai.companyos: 0.14.18 → 0.14.19 — sudosubin/agents.nix0 reactions
- Nov 3, 2026agent-skills.github.kortix-ai.companyos: init at 0.14.18 — sudosubin/agents.nix0 reactions
On the web · 2
- Nov 11, 2026CompanyOS — Claude skill graded C, 4848 tokens resident — seoagent.com
- Nov 9, 2026kortix-ai/CompanyOS · 20.6K Stars · GitHub 趋势 | open-repo — open-repo.com
On Bluesky · 1
- Nov 8, 2026📦 kortix-ai / CompanyOS ⭐ 20,553 (+92) 🗒 TypeScript Kortix CompanyOS – the open-source operating system for your company. Multiplayer AI… — @github-trending-js.bsky.social3 likes and reposts
Other versions9 projects use a version of this.
Word for word · 1
- kortix-ai/suna★ 21k100% same
Edited · 0
None found.
Wrote their own version · 8
- renzrollon/interlock★ 62same name
- muggl3mind/career-manager★ 24same name
- johnviklund/agent-skills★ 2same name
- rterakedis/leanwheel-skills★ 2same name
- scottlivingston/claude-skills★ 1same name
- Troy-LL/Unfurnished★ 1same name
- jstilb/ai-assistant★ 0same name
- mj-deving/pai-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository35 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .deepsec/AGENTS.mdAGENTS.md
- agent-browserSkill
- billingSkill
- claude-codeSkill
- codex-cliSkill
- commit-disSkill
- complianceSkill
- composioSkill
- contributingSkill
- create-prSkill
- dotenvx-secretsSkill
- e2eSkill
- genuiSkill
- kortix-brandSkill
- kortix-captureSkill
- kortix-chromeSkill
- kortix-design-systemSkill
- kortix-imageSkill
- kortix-presentationSkill
- kortix-releaseSkill
- kortix-rollbackSkill
- kortix-socialSkill
- learningsSkill
- migrationSkill
- network-policySkill
- ponytail-auditSkill
- ponytail-debtSkill
- ponytail-reviewSkill
- ponytailSkill
- product-analyticsSkill
- sdkSkill
- testingSkill
- white-labelSkill
- worktreeSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.
“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

