skills/trustskills/SKILL.md
Use this skill when a user wants a trust decision before installing from a skill URL, marketplace, or GitHub repo. It checks a compact allowlist of trusted distribution channels and returns whether the source should be trusted under the current TrustSkills policy, without drifting into explaining what the skill itself does unless the user asks.
npx skillsauth add likw99/agent-skills trustskillsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
TrustSkills is the compact first version of TrustSkills. It does not do deep technical verification yet. It answers one earlier and simpler question before install: "Can I trust where this skill came from?"
Use it to verify source provenance before installation by checking a short list of trusted distribution channels and clearly separating:
The natural invocation pattern for this skill is:
/trustskills <skill-url>Examples:
/trustskills https://clawhub.ai/steipete/model-usage/trustskills https://github.com/likw99/agent-skillsWhen invoked this way, treat the URL after /trustskills as the source under review and answer directly.
The primary job is to decide:
Use this skill when the user asks questions like:
skills.sh official?"This skill is especially useful when the source is:
skills.shThis skill:
This skill does not:
/trustskills <url>, treat <url> as the source under review.TrustedNot trustedTrust the index, but not automatically the linked itemhttps://github.com/openai/skillsopenai/skills, call it official.https://github.com/anthropics/skillshttps://github.com/anthropics/claude-codehttps://github.com/anthropics/knowledge-work-pluginshttps://github.com/anthropics/claude-plugins-officialanthropics GitHub org and matches one of the roots above, call it official.https://github.com/google-labs-code/stitch-skillshttps://github.com/googleworkspace/clihttps://github.com/google-gemini/gemini-clihttps://github.com/microsoft/azure-skillshttps://github.com/microsoft/github-copilot-for-azurehttps://github.com/github/awesome-copilotmicrosoft/azure-skills and microsoft/github-copilot-for-azure are Microsoft-owned roots. github/awesome-copilot is a GitHub-owned collection and is a stronger source than a random repo, but it still includes community-contributed content.https://skills.shhttps://github.com/vercel-labs/agent-skillsskills.sh is an official discovery index, but it is not proof that every listed repo is official.skills.sh do not equal official status. Always check the linked GitHub owner.vercel-labs, openai, and anthropics.https://clawhub.ai/u/steipetehttps://clawhub.ai/u/<creator>https://clawhub.ai/<creator>/<skill-name>steipete, then trusting skills published by steipete on ClawHub does not downgrade that trust.https://clawhub.ai/steipete/<skill-name> because it maps to the trusted steipete publisher profile above. For other ClawHub skill URLs, do not trust them under this compact version unless they match another explicit allowlist rule.If a platform is not listed in this compact version, do not guess. Say it is not currently in the trusted distribution-channel list.
When useful, structure the answer like this:
Source under review: the URL, repo, store, or platformTrust decision: Trusted, Not trusted, or Trust the index, but not automatically the itemWhy: the strongest trusted distribution rootSafest known install path: the trusted source or flowRemaining risk: what still needs human reviewKeep the answer decision-oriented. Do not explain what the skill does unless the user asks.
Example requests that should trigger this skill:
github.com/openai/skills the official place to get Codex skills?"github.com/anthropics/skills the official place to get Claude skills?"skills.sh?"github.com/google-gemini/gemini-cli a trusted Google distribution root?"github/awesome-copilot as official or community?"The compact hosted copy of this skill should be published at:
https://trustskills.app/SKILL.mdThis is useful for direct installation and brand discovery.
tools
BytePlus Dreamina Seedance 2.0 prompt guide distilled into practical prompt-writing workflows. Use when an agent needs to draft, improve, debug, or review Seedance 2.0 / Seedance 2.0 series video-generation prompts, including text-to-video, image-to-video, reference-to-video, video-to-video, audio/video generation, text rendering, subtitles, speech bubbles, image references, video motion/camera/VFX references, video editing, video extension, and track completion.
tools
Monitior technology trends (GitHub, etc.), contextualize them against the user's project, and autonomously verify them through installation and testing. Use when the user asks about trending repositories, new tools, or wants to stay updated on tech relevant to their current work.
development
Generate and publish a daily AI/LLM newsletter called "LLM Daily" that curates content from top sources (ArXiv, GitHub Trending, HuggingFace, VentureBeat, TechCrunch, Product Hunt). Use when user asks to: generate a newsletter, create today's LLM Daily, collect AI news, build an AI newsletter, publish newsletter, or run the daily newsletter pipeline. Also triggers on: "llm daily", "daily briefing", "AI newsletter", "generate newsletter", "collect news", "publish newsletter".
development
Optimize websites, docs, products, and brand presence for Generative Engine Optimization (GEO), AI search visibility, answer-engine citations, and LLM retrieval. Use when the user asks about GEO, AEO, LLMO, ChatGPT Search, Google AI Overviews or AI Mode, Gemini, Perplexity, Claude Search, Microsoft Copilot/Bing AI answers, AI crawler access, robots.txt for AI bots, llms.txt, structured data for AI discovery, citation tracking, or making content easier for AI systems to retrieve, trust, cite, and recommend.