Loading...
Loading...
Found 946 Skills
Use this skill when the user asks to call an authenticated HTTP API (for example "call the GitHub/OpenAI/Slack API", "hit an endpoint that needs a bearer token") and the `sesame` CLI is already installed on this device. The agent invokes `sesame request`, which forwards the HTTP call through the user's own broker and attaches the auth header server-side. The skill does not install software, does not read credentials from the environment, and runs shell only within the fixed `sesame` subcommand surface (`request`, `status`, `hostnames`, `login`, `refresh`). Skip for unauthenticated public endpoints, localhost services, or when the user has already exported a token in the environment for direct use.
Obtains a valid Adobe IMS access token for the DA (Document Authoring) API. Use this skill as a prerequisite step whenever another skill needs to call admin.da.live — for example, before pushing HTML content, listing documents, or triggering a DA preview. Do NOT use this skill if you already have a valid DA_TOKEN in scope from a previous step in the same session.
Query and analyze distributed traces and spans using DataPrime syntax. Use this skill whenever the user wants to investigate request latency, find slow operations, debug service-to-service calls, look up a trace ID, analyze span durations, check error spans, examine distributed traces, investigate OpenTelemetry/Jaeger tracing data, or query Coralogix spans in any way - even if they don't explicitly mention "DataPrime" or "cx spans".
Applies QML best practices when producing or working with QML source code. Use whenever QML code is the primary subject: writing, reviewing, fixing, refactoring, optimizing, or debugging QML files, components, or bindings. Do NOT trigger for purely conversational QML questions where no code is produced or examined (e.g. "explain how anchors work").
Every Google Search Console feature you'd reach for, plus an offline SQLite cache that powers period compare, quick... Trigger phrases: `search console performance for example.com`, `quick wins for sc-domain:example.com`, `cannibalization audit on this site`, `compare last 28 days to prior period in GSC`, `why did traffic drop on this property`, `which pages are decaying`, `use google-search-console`, `run gsc`.
Query historical search volume of Jungle Scout keywords, returning the exact search volume trend of Amazon keywords on a 7-day cycle, covering 10 marketplaces including the US, UK, Germany, Japan, etc. This skill is triggered when users mention keyword search volume trends, historical search volume, changes in search popularity, keyword seasonality, search volume fluctuations, Jungle Scout search volume, keyword search volume history, keyword trend, search volume over time, seasonal search volume, keyword popularity trend. Even if users do not explicitly mention "Jungle Scout", this skill should be triggered as long as their needs involve viewing the search volume change trend of a certain Amazon keyword over a period of time.
从Eureka专利数据库查询专利著录项目（Bibliography）信息，包括标题、摘要、申请人、发明人、分类号、优先权、引用文献等。当用户提到专利著录项目、专利基本信息、专利标题摘要、专利申请人发明人、专利分类号、IPC分类、CPC分类、专利代理、审查员、优先权、引用文献、关联文件、预估到期日、patent bibliography, patent basic info, patent title and abstract, patent applicant/inventor, patent classification, IPC/CPC, patent agent, patent examiner, priority claims, cited references, related documents, estimated expiry, Eureka patent data时触发此技能。即使用户未明确提及"Eureka"或"著录项目"，只要其需求涉及查询专利的基础著录信息（标题、摘要、申请人、分类号等），也应触发此技能。
Create a comprehensive brand design guide — color palette, typography pairings, UI component previews, and visual identity rules with example mockups.
Required reading before writing any HogQL/SQL or calling execute-sql against PostHog. Use whenever the user wants to search, find, or do complex aggregations PostHog entities (insights, dashboards, cohorts, feature flags, experiments, surveys, hog flows, data warehouse, persons, etc.) and query analytics data (trends, funnels, retention, lifecycle, paths, stickiness, web analytics, error tracking, logs, sessions, LLM traces). Covers HogQL syntax differences from ClickHouse SQL, system table schemas (system.*), available functions, query examples, and the schema-discovery workflow.
Adversarial robustness engineering for ML/AI—evasion, poisoning, extraction, membership-inference threat models; robust training, sanitization, detectors; ASR/certified evals; lab model attacks; data-pipeline integrity; production I/O guardrails (classical ML and LLM/multimodal). Use for adversarial examples, robustness suites, poison audits, deploy guardrails—not LLM app red team (ai-redteam), governance (ai-risk-governance), safety classifier R&D (ml-research-engineer-safeguards), safeguard serving (ml-infrastructure-engineer-safeguards), privacy research (privacy-research-engineer-safeguards), AppSec pentest (penetration-tester).
Orchestrate same-repository GitHub issue work from branch setup through local review and PR readiness. Use when the user invokes `/develop-issue #123`, `/develop-issue https://github.com/<owner>/<repo>/issues/123`, or asks to develop exactly one issue end to end.
Use when the user asks about 高考 (Chinese college entrance exam) data — score lines, one-score-one-rank tables, university info, or admission guidance. Invoke when user mentions "高考", "分数线", "一分一段", "志愿填报", "大学排名", "985", "211", or asks about college admission in China.