Loading...
Loading...
Found 1,039 Skills
Generate complete business proposals for client projects. Takes client requirement documents (docx/pdf/md) or verbal descriptions as input, outputs a professionally formatted proposal with technical architecture, budget, timeline, risk analysis, and team introduction. Automatically calls illustrate for images and any2pdf for final PDF delivery. Trigger when user mentions "商务方案", "合作评估", "项目评估", "报价方案", "proposal", "需求评估", "给客户出方案", or wants to generate a client-facing project proposal from requirements.
Use when grooming hair or fur in Maya with XGen (Interactive Groom splines or legacy descriptions): scalp hair, eyebrows, eyelashes, fur, guides, clumps, noise, parting, density maps, a fill layer, aiStandardHair shading, noisy or flickering hair renders, hair that must move (Linear Wire, nHair, Alembic caches), or a groom for Unreal (groom Alembic, cards). Also when XGen hair looks CG, clumps look uniform, the scalp shows through, or an XGen script fails.
Turns a plain-language description of a data/statistics task into correct, runnable Stata code — a .do file or command sequence, not pseudocode. Use this whenever the user asks how to do something in Stata, wants a Stata command or .do file written or fixed, mentions Stata alongside a modeling task (regression, panel data, time series, ARDL, fixed effects, diff-in-diff, matching, etc.), or wants Stata and Python working together (running Python from inside a .do file, pulling Stata's dataset into pandas, or driving Stata from a Python script via pystata/stata_setup or batch mode). Also trigger when the user pastes Stata code that errors or gives wrong-looking results and wants it debugged, or asks 'is this good Stata style' / 'what's wrong with this command'. Covers a growing library of named recipes for common econometric workflows (ARDL modeling shipped now; more added over time) that produce a ready-to-run script, not just an explanation.
Files GitHub issue(s) for work already done (or about to be done) on a branch/PR, grouping related issues under a parent epic when there's a genuine hierarchy — using GitHub's native parent/child issue relationship, not just labels — and then updates that pull request's title (kept short) and description so the description lists every issue in the exact format '- Closes #{{issue-number}} -- {{issue-title}}', indented to match parent-child nesting. Use this whenever the user asks to file issue(s) for a PR, 'add gh issues for this', 'track this as issues', link a PR to tracking issues, or update a PR's title/description to list the issues covering its changes — including when they invoke /create-issues-update-pr directly. Also trigger when a PR description is stale or generic relative to its actual current commits and the user wants it brought up to date alongside issue creation.
Create working interactive network and architecture diagrams with moving packets, orthogonal connections, scenario playback, and selectable nodes. Use when the user invokes /network-flow or asks for live flowing diagrams, animated system architecture, request flows, RAG pipelines, or agent workflow visualizations. Accept descriptions, reference images, source material, or graph JSON. Deliver a self-contained HTML file with a working preview when supported; complete rendering, browser verification, and file delivery rather than stopping at a diagram description.
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.
Decode a reference image or brief description into an editable halftone paper-collage specification. By default, use the Codex built-in `image_gen` to create brand-consistent stills and transparent layers, then use local FFmpeg or HyperFrames to produce a deterministic motion video that assembles piece by piece from an empty background. Use this when the user mentions halftone collage, paper collage, paper-cut collage, editorial collage, magazine collage, retro print collage, collage motion, collage animation, paper-cut animation, paper-piece assembly, layer-by-layer assembly, from nothing to something, elements flying in and assembling, stop-motion collage, stop-motion animation, Arcads style, reference-image breakdown, style breakdown, reverse-engineering a visual, “make it in this style,” “make something similar,” “generate collage stills,” “animate this image,” “make these elements assemble,” or “create a collage ad or collage explainer video.” English trigger semantics include editorial collage, halftone collage, paper collage, paper-cut motion, stop-motion graphic, assemble from empty, build-on motion, analyze this, break this down, reverse-engineer this look, generate the stills, animate this, and make these move. By default, do not invoke Arcads, Nano Banana, Seedance, or Kling. Enter an external generation path only when the user explicitly requests it and the corresponding connector is available.
Trigger this skill when facts with legal significance need to be extracted from unstructured text such as case descriptions, party statements, chat logs, and media reports. Typical trigger scenarios include, but are not limited to: - The user provides a case description in everyday language and asks for legal facts to be extracted - The user asks to convert a colloquial or emotional narrative into a fact structure suitable for legal analysis - The user asks to distinguish “objective facts,” “subjective judgments,” and “legal evaluations” in a case narrative - The user asks to map extracted facts to the constitutive elements of a specific legal relationship - The user asks to organize a case chronology or create a fact-summary table - The user asks to convert everyday language into legal language, such as “he kept putting off repayment” → “the debtor failed to perform after the repayment deadline expired” The core value of this skill is to organize narratives that mix everyday life into a fact structure that can feed into legal reasoning. It is a prerequisite for legal analysis.
A CVE (Common Vulnerabilities and Exposures) is a unique identifier assigned to a publicly known cybersecurity vulnerability. CVEs help standardize the naming and tracking of vulnerabilities, making it easier for organizations, security professionals, and software vendors to share information and manage risks associated with these vulnerabilities. Each CVE entry includes a brief description of...
Audit and upgrade a candidate's GitHub profile the way recruiters and interviewers see it, covering profile README, pinned repos, repo READMEs, descriptions, topics, commit history and red flags, then draft the fixes (profile README, repo READMEs, descriptions) and apply them only with permission. Use when the user wants to improve their GitHub profile, make GitHub recruiter-ready, write a profile README, choose pinned repos, or get feedback on their GitHub.
Use when an agent must make TwelveLabs do real video-understanding work: indexing footage, semantic/visual search across an archive, generating descriptions, summaries, chapters, highlights, and tags from video, producing multimodal embeddings, or wiring TwelveLabs into a media-production pipeline (NLE panels, logging, compliance review, metadata). Covers the current model families (Marengo for search/embeddings, Pegasus for video-to-text analysis), the v1.3 Video Understanding API (indexes, assets, tasks, search, analyze, embed), prompt construction for analysis, capability and format limits, pricing/quota math, output quality review (hallucination and timestamp accuracy), and privacy/rights obligations when footage shows real people. Not for generating or editing video pixels — this is analysis and retrieval.