Loading...
Loading...
Found 977 Skills
Creates PR review reports. In addition to investigating bugs and vulnerabilities, it verifies the consistency between exported conversation contexts, PR descriptions, and implemented code, and critically scrutinizes the soundness of the implementer's work. Used when users say things like "Write a PR review report", "Conduct a code review with conversation context", or "Question the sanity of this PR".
WeChat Official Account Layout Theme Studio · Modify the **default layout style** (colors / headings / quotes / captions) of your WeChat articles based on your spoken descriptions, with instant local preview. The result is finally saved in two places: back to the server + a local theme file. Uses doubaoya.com, authenticate with your own DOUBAOYA_API_KEY. Trigger phrases: /dby-theme, change WeChat article layout, customize theme style, change WeChat color scheme, adjust layout theme, change default layout. Trigger words: customize WeChat article theme, change layout / palette / heading style.
End-to-end open-source contribution for Agent/LLM projects: discover GitHub repos (stars, downloads/usage, recent commits, issue close ratio, PR merge speed, release cadence) and rewrite each project description in the user's language (what it does, problem, scenarios), analyze an Agent/LLM repo, write a scoped PR plan, implement it, open a GitHub PR, then write a PR summary from saved artifacts. Use when the user wants to search for contributable projects, find open source projects, Agent open source, MCP/LangChain repositories, star 1000, GitHub repo search; pastes a GitHub URL for open source contribution analysis, PR direction, good first issue, Agent architecture flaws; asks for technical solution, implement the plan, submit PR with feat/fix/refactor/test/docs; or produce PR summary, summary.md, review submitted PR, pastes a pull request URL / previously mentioned project. Trigger even without the word skill. Do not use for private product feature work or non-Agent general OSS drive-bys.
Use when public pages should be found in search, and titles, meta descriptions, canonicals, robots.txt, sitemap.xml, indexing directives, and URL consistency need to be correct and agree with each other. It checks rendered output and the relationships between files, and repairs localhost canonicals, private routes in sitemaps, and starter metadata. Do not use it to promise indexing or ranking, to keyword-stuff, or on a product that is intentionally private.
The Synthesia craft skill — produce avatar video (training, onboarding, explainers, localized series, faceless educational content) with the consent-first architecture and honest fit boundaries. Use when someone wants to make videos with Synthesia/AI avatars, create a personal avatar/digital twin, localize one video into many languages, build training/L&D video at scale, or asks whether an avatar should replace them on camera. Uses the HUMAN framework. Reads the content skill + brand-profile + voice-builder first. The agent scripts and plans (API where connected); the HUMAN approves every video; WoopSocial publishes. Spines: the fit test (avatars win at scale/localization/training, lose to a real face for trust-led content); consent-first likeness; the script is most of avatar quality — lock copy before generating. Never impersonate, fake endorsements, or skip AI-disclosure. Distinct from heygen, talking-head-and-piece-to-camera, ai-video/luma, ai-voiceover, and descript.
Build or transform lightweight realtime voice-chat apps with a talking character avatar from either a user-supplied photograph or a text description. Use when Codex is asked to create a talking avatar, photo avatar, character chatbot, roleplaying voice companion, mouth-sprite animation, or reusable OpenAI Realtime avatar app in Vite/Next.js, including BYOK API-key intake, identity-consistent image generation, audio-driven lip sync, testing, and deployment.
Transform feature descriptions into well-structured project plans following conventions
[BETA] Transform feature descriptions or requirements into structured implementation plans grounded in repo patterns and research. Use when the user says 'plan this', 'create a plan', 'write a tech plan', 'plan the implementation', 'how should we build', 'what's the approach for', 'break this down', or when a brainstorm/requirements document is ready for technical planning. Best when requirements are at least roughly defined; for exploratory or ambiguous requests, prefer ce:brainstorm first.
Client-facing red-team deliverable format — codifies the Subject / Observations / Description / Impact / Recommendation / PoC structure used for external red-team engagements (not bug-bounty platform reports). Different audience, different tone, different cadence. Built from an authorized engagement deliverable where 14 findings were packaged into a 52KB MD + 2.2MB DOCX with 16 embedded screenshots. Use when the engagement is "external red team for an enterprise client" (not H1/Bugcrowd/Intigriti), when generating the final report, when the client has specified a custom report format, or when packaging findings into DOCX/PDF.
Load when operating a Quilium CMS site that already runs — writing or editing content blocks, managing pages, uploading media, adding items to a collection, translating, reordering navigation, auditing or filling SEO metadata, importing from a file. Covers the working discipline of a content session and the mistakes that corrupt data without raising an error. Triggers on "add a page", "edit this block", "add a field to the form", "change the form validation", "the form email", "upload an image", "add an article", "translate this", "publish this", "fill the meta descriptions", "import this spreadsheet", "reorder the menu". For structural work — YAML types, routes, templates, a site that doesn't exist yet — use quilium-builder instead.
Use when a public site should be found and shared correctly, or when titles, descriptions, canonicals, robots.txt, sitemap.xml, social previews, favicon, and indexing directives need one coordinated review. It runs one shared sweep, then routes only to the specialists whose findings need work. Do not use it as a ranking promise, for a private or intentionally unindexed product beyond confirming it is consistently noindex, or for a single-file fix a specialist already owns.
Use when a public page may be shared in chat, social, or search previews and its Open Graph and Twitter card tags need to be correct: title, description, absolute image URL, and canonical alignment. It reads rendered output and repairs missing or placeholder tags with product-specific copy. Do not use it to invent preview copy that misdescribes the product, to point images at localhost, or for pages that will never be shared.