Choose by the work you need to do

Compare AI skills

Choose up to three resources. Compare their purpose, license and requirements, then read the scope of any recorded checks before installing.

Clear selectionBrowse the library →

This comparison does not rank or certify resources. Client labels are declared targets, not compatibility test results. Recorded outcomes can include passes and failures; they cover only the stated scenario and current package.

Images

Discernment Nudge

After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.

Purpose
Brand assets
Author / publisher
anthropics
License
Apache-2.0 · License guidance
Version
8a1541c4.bb1
Access
Free download. External tools and services may have separate costs.
Declared clients
Claude Code, Codex, Cursor, OpenClaw, Hermes, Gemini CLI, OpenCode

Source & package

Inspect the original source ↗

6 files · 0 script/code files. License file detected.

Current package SHA-2564e39575d7d1ef8a5342cc517a644597db4b28419c70935642df7e3bb59b124c0

Tools & requirements

No current structured source review is recorded. Read the instructions, dependencies and original source before choosing.

Evidence & limits

No current full-skill evaluation is recorded by this catalog.

0 current outcome records. No published pass/fail record matches this version and checksum.