Use when the user requests independent review of code, a diff, or recent changes. Requires fresh reviewer context through exposed agents or an authenticated Codex CLI.
Use when work spans context windows or sessions, progress is lost after compaction or retries, or the user invokes $long-horizon or asks to work in verified rounds.
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.
Run measured optimization rounds with independent review for FPS, loading, latency, throughput, and resource use; with no named target, triage every dimension first. Use for $perf-loop or broad performance requests; skip isolated fixes.
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.
Use for an explicit workflow-improvement review, turning the user's preferences into rules or a skill, or recurring task friction that may justify a narrow change to skills or project references.
Coordinate parallel agent 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.
Create distinctive, crafted artifacts in any medium. Use for $showpiece, ambitious creative direction, portfolio-quality work, or substantial cleanup of generic AI styling. Skip routine edits unless explicitly invoked.
Fresh critical second look at a recommendation: on $why, or before presenting your own weighty pick (hard to undo, two or more real options, or real time or money at stake). Never from ordinary why questions.
Use for $wow-loop, wow factor, a target score (\"get it to 8/10\"), or visual work needing reference fidelity or repeated correction, on one deliverable or a set of like items. Skip routine cosmetic edits and discussion of the 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. Use normal prose for deliverables.
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.