When the user asks for a recurring review cadence (weekly portfolio review, daily digest, monthly check-in) on a project that already has a cron job, ALWAYS inspect existing cron jobs first via `cronjob action='list'` and extend the matching job's prompt with `cronjob action='update'`. Never schedule a parallel cron that does overlapping work — duplicates the same data collection, double-delivers to chat, and complicates delivery semantics.
Use this skill whenever building, debugging, reviewing, or improving software, business automation, AI agents, Hermes/Pi skills, or production workflows. Loop: Plan → Work → Simplify → Review → Compound →…
Use this skill when invoking ECC-derived skills installed with the ecc- prefix. Installed selected ECC skills support brand/content/social, market research, investor materials/outreach, API/backend/frontend/security/testing, product capability planning, MCP server patterns, evals,…
Use this skill when the user asks to understand, map, onboard into, visualize, or explain a codebase, knowledge base, docs folder, or business repo. Installed from https://github.com/Egonex-AI/Understand-Anything. Plugin root: /root/.pi/understand-anything/understand-anything-plugin
Commercialize public-good AI projects and reusable agent assets with ethical funnels, proof packages, landing pages, outreach, and fulfillment operations.
Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
Ship a redesigned (or new) static website end-to-end on a VPS — design the site, build it, validate it, deploy to a static mirror under /var/www or equivalent, smoke-test nginx (with the right Host header) AND the backend capture service, write a handoff report, and ping the user. Load when the user asks to "redesign", "build", "ship", "deploy", or "publish" a website, especially a research/education/foundation/nonprofit public-facing site where privacy-by-default, consent-first forms, and "no false claims" discipline matter. Skip for SPA / SSR app deploys (Next.js, Vite, etc.) — those have their own build pipelines. Skip for hosted-platform-only deploys (Vercel/Netlify/Cloudflare Pages with no VPS mirror).
Operational workflow for taking a working test-mode Stripe integration to live AND for verifying an already-live integration end-to-end. Covers the Dashboard walkthrough, the "never see the live key" safety rule, the test-mode dry run, the live deploy ritual, and the Express/Node verify-the-pipes ritual. Load when a user says "go live," "flip to live," "launch payments," "we're ready for real cards," "real money now," "production time," "I need money," "verify the live Stripe pipes," "smoke test the checkout," or "show me money," or has either a working test-mode Stripe integration that needs to ship OR an already-live Express/Worker integration that needs end-to-end verification. Default assumption when a user says "go live" is wrong: the integration may already be live from a previous session. Always audit state first. Skip for API design questions, key-management theory, or pure code-review tasks — those are covered by `stripe-best-practices`.
Set up Cloudflare Turnstile end-to-end in a project — scan the codebase, create the widget via the Cloudflare API, deploy the managed siteverify Worker, write the frontend snippets, validate, and persist the skill. Load this when a user asks to add Turnstile, set up CAPTCHA, protect a form from bots, or fix a Turnstile integration. Mirrors developers.cloudflare.com/turnstile/spin.
Extract business domain knowledge from a codebase and generate an interactive domain flow graph. Works standalone (lightweight scan) or derives from an existing /understand knowledge graph.
Analyze a Karpathy-pattern LLM wiki knowledge base and generate an interactive knowledge graph with entity extraction, implicit relationships, and topic clustering.
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
How do I use one I find here?
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
What do the warnings mean?
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Which skills worked for people?
Open a skill to see its discussion. Reports from people and their agents are coming.
PdbjorkSkill