Ingest a YouTube source into a CoreWise Academy guide — transcript, notes, MDX draft, source log, review PR (never publishes). Use when the user says /ingest, gives a YouTube URL to build a guide from, or asks to add a guide from a video.
Use once in a spawned starter repo when the user asks to initialize or configure it, or when FILL IN markers remain; never auto-run in a claude-starter template checkout.
Peer swarm on a long-horizon run: Opus, Sol and Astra contribute ideas, critique and code throughout; disagreements are flagged to the user, never blocking. Use on /long-horizon-swarm or to bring Sol/Astra into long-horizon.
Merge PRs through a Codex review loop: /codex-fullreview, fix, then /codex-review reruns (3 max) until clean, then CI and squash-merge. Runs only when the user types /merge; from then on, every PR in the session goes through the same loop and merges.
Use when the user asks to reduce per-turn context or token load, trim kernels, skills, or connectors, or propagate a generic context optimization to the starter.
Sitewide sweep of shipped site copy for fancy, Latinate, or insider words. Use when the user says /plain-words or asks for a sitewide fancy-word sweep. The word test and trap list live in the writing skill, pattern 31.
Use before unfamiliar project-area work, when retrieving project decisions or pitfalls, when saving an authorized durable fact, or when a quirk just cost a retry, a backed-out change, or a user correction and belongs in pitfalls.
Coordinate parallel Claude Code sessions via a shared append-only HTML hub. Use on /session-hub, 'run parallel sessions on this', joining a hub, or proactively when edits or commits this session did not make appear in the checkout.
Always-on AI-tell stripper: apply its pattern check to everything written for humans (chat prose, commits, PR bodies, docs, UI text). Also use when the user says /unslop, \"unslop this\", or points at text or a file to clean.
Use only when the user explicitly invokes /why to challenge the assistant's immediately prior recommendation; never trigger from ordinary why questions or paraphrases.
Use for /wow-loop, wow-factor requests, or substantial visual work needing independent review and repeated correction. Skip routine cosmetic edits and discussion of this skill.
Use when a clear task needs a multi-step implementation plan, dependency ordering, or a durable handoff. Skip for routine changes that can be executed directly.
Use for text that leaves the session (READMEs, docs, site and UI copy, emails, release notes, application answers) or to unslop, humanize, voice-match, or audit a draft for AI tells. Ordinary session replies use Caveman with built-in Unslop.
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.