skills
llms.txt9 starsChanged 42 days agoMITView on GitHub
You say the job; the playbook runs. Installable workflows for Cursor, Claude Code, Codex CLI, and Gemini CLI: 159 agent skills, 63 slash commands, 6 subagents, and MCP templates for React / Next.js / Supabase. Full pack: npx @kensaurus/skills --all (skills + commands; kenji --all = four tools). Skills only: npx skills add kensaurus/skills (that CLI's --all means every skill to every agent). Claude Code plugin: /plugin marketplace add kensaurus/skills. Re-check: npx @kensaurus/skills --verify --all. Validated against the Agent Skills…
In this repository163 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/approved-plan-execution.mdcCursor rule
- .cursor/rules/skill-workflows.mdcCursor rule
- .cursor/rules/verification-before-completion.mdcCursor rule
- audit-accessibilitySkill
- audit-agent-speedSkill
- audit-analyticsSkill
- audit-auth-flowsSkill
- audit-backend-architectureSkill
- audit-bundle-sizeSkill
- audit-cicdSkill
- audit-codemod-safetySkill
- audit-code-qualitySkill
- audit-code-reviewSkill
- audit-db-schemaSkill
- audit-doctrineSkill
- audit-env-paritySkill
- audit-fe-apiSkill
- audit-gate-logicSkill
- audit-i18nSkill
- audit-infra-costSkill
- audit-langfuse-llmSkill
- audit-llm-securitySkill
- audit-monetization-iapSkill
- audit-payment-systemSkill
- audit-performanceSkill
- audit-realworldSkill
- audit-registry-listingSkill
- audit-resilienceSkill
- audit-responsiveSkill
- audit-securitySkill
- audit-skill-conflictsSkill
- audit-ui-statesSkill
- audit-uiux-design-systemSkill
- audit-ux-journeysSkill
- audit-uxSkill
- backend-db-performanceSkill
- backend-error-handlingSkill
- backend-observabilitySkill
- backend-patternsSkill
- backend-realtimeSkill
- burndown-fullSkill
- complete-everythingSkill
- data-pipelineSkill
- data-visualizationSkill
- debug-errorSkill
- debug-fe-be-integrationSkill
- debug-sentry-monitorSkill
- deploy-npmSkill
- deploy-verifySkill
- design-apiSkill
- design-canvasSkill
- design-emailSkill
- design-frontendSkill
- design-generative-artSkill
- design-mobile-firstSkill
- design-motionSkill
- design-prdSkill
- design-systemSkill
- design-themeSkill
- The first 60 shown.
The file
Files
# kenji > You say the job; the playbook runs. Installable workflows for Cursor, Claude Code, Codex CLI, and Gemini CLI: 159 agent skills, 63 slash commands, 6 subagents, and MCP templates for React / Next.js / Supabase. > > Full pack: `npx @kensaurus/skills --all` (skills + commands; kenji `--all` = four tools). Skills only: `npx skills add kensaurus/skills` (that CLI's `--all` means every skill to every agent). Claude Code plugin: `/plugin marketplace add kensaurus/skills`. Re-check: `npx @kensaurus/skills --verify --all`. Validated against the [Agent Skills specification](https://agentskills.io/specification) on every commit. npm package: `@kensaurus/skills`. Runs on Claude Opus 5.5 — the Claude Code default since 2.1.280 and a Cursor agent model — with effort routing declared per skill: audit / plan / judge at high, implementation at the medium default, inventory / handoff at low. Prompts do not steer thinking on Opus 5.5; effort does. ## Install - [README.md](https://github.com/kensaurus/skills/blob/main/README.md): Quick start, install modes, FAQ, skill taxonomy - [docs/GETTING-STARTED.md](https://github.com/kensaurus/skills/blob/main/docs/GETTING-STARTED.md): First-time install, first phrases, typical session ## Reference - [docs/CATALOG.md](https://github.com/kensaurus/skills/blob/main/docs/CATALOG.md): Full skill list with trigger phrases and composition patterns - [docs/THIRD-PARTY-SKILLS.md](https://github.com/kensaurus/skills/blob/main/docs/THIRD-PARTY-SKILLS.md): Vendored upstream skills (`thirdparty-*`), attribution, update policy - [docs/TRIGGER-CHEATSHEET.md](https://github.com/kensaurus/skills/blob/main/docs/TRIGGER-CHEATSHEET.md): Plain lookup table for skill triggers - [docs/PLAN-LOOPS.md](https://github.com/kensaurus/skills/blob/main/docs/PLAN-LOOPS.md): 23 `plan-*` audit skills in grouped loops (approve before execution) - [docs/AGENTS.template.md](https://github.com/kensaurus/skills/blob/main/docs/AGENTS.template.md): Project constitution template for consumer repos - [docs/MODEL-AND-EFFORT.md](https://github.com/kensaurus/skills/blob/main/docs/MODEL-AND-EFFORT.md): Default model per host, how to set effort (`/effort`, `modelSettings`, frontmatter `effort:`), the pack's routing table, what changed for Opus 5.5 ## MCP & security - [mcp/README.md](https://github.com/kensaurus/skills/blob/main/mcp/README.md): MCP server setup, pinned package versions - [SECURITY.md](https://github.com/kensaurus/skills/blob/main/SECURITY.md): Secrets hygiene, `.mcp.json` guidance, reporting vulnerabilities ## Distribution & publishing - [docs/DISTRIBUTION.md](https://github.com/kensaurus/skills/blob/main/docs/DISTRIBUTION.md): Install channels, directory listings, discovery status - [skills.sh listing](https://www.skills.sh/kensaurus/skills): Live installable catalog page (`npx skills add kensaurus/skills`) - [SkillsMP pack page](https://skillsmp.com/creators/kensaurus/cursor-kenji): Aggregator crawl of this repo’s `SKILL.md` files (their count can lag) - [docs/PUBLISHING.md](https://github.com/kensaurus/skills/blob/main/docs/PUBLISHING.md): Maintainer release guide (GitHub Release → OIDC-staged npm publish → owner approves with 2FA) - [docs/PROMOTION.md](https://github.com/kensaurus/skills/blob/main/docs/PROMOTION.md): Listing copy for skills.sh, cursor.directory, marketplace, Claude plugin - [Claude Code plugin](https://github.com/kensaurus/skills/blob/main/.claude-plugin/marketplace.json): `/plugin marketplace add kensaurus/skills` (community catalog is a separate submit) - [docs/examples/plan-audits/](https://github.com/kensaurus/skills/tree/main/docs/examples/plan-audits): Sample `plan-*.md` audit outputs - [CHANGELOG.md](https://github.com/kensaurus/skills/blob/main/CHANGELOG.md): Release history - [CONTRIBUTING.md](https://github.com/kensaurus/skills/blob/main/CONTRIBUTING.md): Adding skills, validation, PR workflow
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.

