Loading...
Loading...
Found 2,838 Skills
Bun runtime API reference for TypeScript scripts. Covers Bun.file(), Bun.write(), Bun.$() shell, Bun.spawn(), Bun.Glob, Bun.env, bun:sqlite, Bun.sql() for PostgreSQL/MySQL via DATABASE_URL, Bun.s3 for S3-compatible storage, Bun.redis for Redis/Valkey, Bun.Archive for tarballs, Bun.Image image processing, Bun.WebView headless browser automation, Bun.cron in-process scheduler, JSONC/JSON5/JSONL/markdown (named imports), Bun.hash, Bun.password, compression, and scripting utilities. Use when writing scripts, automating tasks, querying databases, working with S3 storage, Redis caching, processing images, automating a headless browser, parsing markdown/JSON variants, or doing file processing in a Bun project. Signals: bun.lock, bunfig.toml, DATABASE_URL, REDIS_URL, AWS_ACCESS_KEY_ID, Bun.$ usage Not for bun CLI commands (bun-cli skill), non-Bun runtimes, or ORM CLI tooling
Index of ImageKit SDKs, plugins, and integrations — front-end, back-end, mobile, CMS, external storage, video player, media library & upload widgets, AI/automation, and URL generation. Use to find the right integration for a technology and what it covers, then query search_docs for implementation details.
AWS-curated copy-paste prompts for AI coding agents (MVP scaffolding, RAG chatbot with Claude on Bedrock, security baseline evaluation, cost anomaly detection, GPU quota requests, EKS deployment, Well-Architected review, etc.) plus downloadable installable agents (Multi-Account Transition Advisor, Bill Shock Preventer, Service Quota Agent, Bedrock Model Availability Agent, AWS DB Advisor). Use when the user asks for a prompt to do X on AWS, wants an installable agent for multi-account / cost monitoring / quota management / Bedrock model availability / database selection, or asks how to use AWS prompts. For migration intent (GCP to AWS, OpenAI/Gemini to Bedrock), route to the migration-to-aws skill. Do not use for: factual AWS Activate / programs / credits questions, learn articles, sample architectures, or for prompts that are not in the bundled `references/prompt-library/` tree.
Use when auditing domain authority, trust, or citation credibility; runs a peer-relative 40-item CITE profile with evidence coverage and verified manipulation/penalty veto checks. Not for page-level content quality — use content-quality-auditor; not for backlink profiling alone — use offsite-signal-analyzer. 域名权威/网站可信度
Define and use segments — named, saved filters over a Cargo model that become the audience for a batch run, a play trigger, or an export. Triggers: "build a segment of", "filter my contacts where", "who matches this criteria", "save this as a list", "how many companies match", "the Closed-Won segment", "everyone who has not been emailed", "target only accounts that", "what is in this segment", "narrow this down to". Filter JSON uses `conjonction` (not `conjunction`) — misspelling it fails silently. Skip when: running something over the segment — use cargo-orchestration; exporting its rows — use cargo-analytics; ad-hoc SQL over the model — use cargo-storage.
Audit and reduce AI agent runtime spend in dollars. Use for AI costs, agent spend, token waste, runtime attribution, detector coverage, and FinOps. Works with OpenClaw, Hermes, QM, Claude Code, Cursor, and generic event ingest.
Alibaba Cloud SLS (Simple Log Service) index configuration manager skill. Use this skill to help users inspect, create, update, or delete a Logstore index, generate an index configuration from user-provided structured log samples, and optimize an existing index configuration for given query/SQL workloads, write throughput, and storage cost — all through the aliyun CLI. Triggers: "SLS 索引", "索引配置", "create index", "update index", "delete index", "generate index", "optimize index", "全文索引", "字段索引", "log index config", "aliyun sls index".
Factorial Code platform architecture and core concepts — processes, modules, execution context, team variables and their inheritance from parent workspaces, datastore, file storage, workspace structure, and naming conventions. Use when building, editing, or reasoning about any Factorial Code (fcode) process, module, or workspace; start here before writing process or module code.
Build, scaffold, refactor, debug, review, and visually validate production Rust desktop interfaces with GPUI. Use for setting up a production-ready GPUI starter app; new GPUI apps or components; Entity, Context, action, async, and lifecycle architecture; Apple-style macOS UI, Liquid Glass or translucent materials, motion, gestures, focus, keyboard, accessibility, text input, IME, clipboard, drag and drop, menus, multi-window behavior, and restoration; packaging, CI, performance, and testing work; or translating selected Paper.design frames into maintainable GPUI code with screenshot comparison. Covers published GPUI and pinned Zed revisions, macOS/Linux/Windows boundaries, narrow AppKit interop, and stability audits.
Detects prompt injection using regex signature matching, heuristic scoring for structural anomalies, and DeBERTa-based transformer classification, flagging direct injections (system-prompt overrides, role-play escapes) and indirect injections (encoded payloads, obfuscation) per OWASP LLM Top 10 (LLM01:2025). Use for input validation layers in chatbots/agents/RAG pipelines, or for retrospectively classifying injection attempts in logs or incident investigations.
Use to ride a trend — a trending sound, format, meme, hashtag, news moment, or cultural conversation — to earn reach by attaching the brand to something already getting attention (a.k.a. trendjacking / newsjacking). Run when the user says "trend," "trending," "jump on this trend," "trendjack," "newsjack," "is this trend worth doing," "make this go viral," or wants to react to a current moment. Reads brand-profile, voice, and audience first, then runs three gates — FIT, SAFETY, and TIMING — before executing a fast, on-brand remix and handing to the right content skill (tiktok-script, reels-script, caption-writer) and scheduling-and-queue. Refuses to trendjack tragedies or divisive moments and won't force irrelevant trends; live trend discovery needs current scanning — this skill vets and executes. For meme-format craft, cultural fluency, and meme IP/likeness judgment ("make a meme," "is this meme safe"), route to meme-and-culture.
Focused Signals scout for PostHog projects using session replay. Watches two promises the replay product makes: that sessions are actually being recorded (capture integrity — recording volume vanishing while site traffic doesn't), and that the friction evidence inside recordings gets seen (rage-click / dead-click clusters concentrating on a page or element, error-after-interaction cohorts, recurring replay vision themes nobody aggregates). Emits findings only when they clear the confidence bar; otherwise writes durable memory and closes out empty. Self-contained peer in the signals-scout-* fleet.