Agent Skills portable format router. Use when creating cross-client skills, validating portable frontmatter, packaging skills for upload or API use, or implementing skill discovery and activation.

Download videos, audio, subtitles, and clean paragraph-style transcripts from YouTube and any other yt-dlp supported site. Use when asked to “download this video”, “save this clip”, “rip audio”, “get subtitles”, “get transcript”, or to troubleshoot yt-dlp/ffmpeg and formats/playlists.

Use the smallest visual when prose must carry structure—control flow, call depth, module ownership, or change shape: pseudocode, call tree, component/file tree, Mermaid diagram, or diff. Skip it when prose already answers the question.

Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution

Simulates plan mode with a teaching-first approach. Use when onboarding to a new codebase, exploring architecture, or seeking guided understanding of any project area. Produces high-level overviews with diagrams, drills into details on request, and offers follow-up exploration questions.

Build, install, launch, screenshot, and cleanup mechanics for automated reproduction of site breakage on Cursor self-hosted Android agents in `ddg-native-android`. Use when setting up a device for automated site breakage triage repro runs.

Hunt threat-intelligence indicators of compromise (IoCs) across Dynatrace logs and spans and produce a 0-100 threat-exposure score. Extracts and normalizes IoCs — IPs, Domains (hostnames included), URLs, Emails, CVEs, File hashes (md5/sha1/sha256), MITRE TTPs — from unstructured reports, advisories, advisory URLs, pasted text, or STIX, then hunts them in fetch logs and fetch spans. Trigger: hunt these IoCs, am I exposed to this threat, check these indicators in my logs and traces, threat exposure report, extract IoCs from this advisory URL, search these hashes/domains/IPs in my environment. Routes CVE-to-vulnerability, IP/Domain/URL/MITRE-to-detection legs to dt-sec-insights. Do NOT use for: querying security.events directly (vulnerabilities, detections, compliance, THREAT_REPORT — use dt-sec-insights); general log queries not tied to an IoC hunt (use dt-obs-logs); general span/trace analysis (use dt-obs-tracing); explaining DQL syntax (use dt-dql-essentials).

Analyze dashboards and notebooks using Davis analyzers — anomaly detection, novelty scoring, and correlation. Use when the user references a specific Dynatrace dashboard or notebook (by URL, UUID, or name) and asks what it shows, which DQL queries it runs, whether a tile looks off, or wants to find anomalies, score novelty, or correlate its metrics. The trigger is a dashboard or notebook as the data source, not a general DQL question. This skill extracts timeseries queries efficiently without reading the full raw document JSON, then optionally runs Davis analyzers on the extracted metrics. Trigger phrases: "what's wrong on this dashboard", "analyze this notebook", "find anomalies", "novelty score", "correlate metrics", "extract DQL from dashboard", "dashboard URL", "tile", "run-analyzer", "timeseries extraction", "Davis analyzer".

Navigate Langfuse repositories, code areas, and agent skills. Use to locate code, choose the right repo or skill, search across the Langfuse organization, or orient before implementation, debugging, documentation, support, or operations.

Design a goal-oriented agent loop or review one for failure modes: spinning, Goodhart-gaming the verifier, or running a wrong answer to completion. Covers machine-decidable goals, loop types, plan/build/judge skeletons, and runaway prevention; mechanism wiring lives in autonomous-loops. Use when designing, writing, or checking an agent loop. 中文触发：写 loop、设计 loop、做一个 loop、检查 loop 对不对、loop 体检、loop 会不会跑飞、可判定目标、五个崩法、plan build judge。

Convert 'make it faster' requests into a bounded measured optimization loop — baseline first, generate one-hypothesis variants, benchmark each against a correctness gate, and promote the fastest safe variant with reproducible commands. Use when asked to speed something up, try many variants, run recursive optimization, benchmark latency/throughput/cost, or pick the best implementation by repeated measured tests.

Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.

Diagnose interface errors, drops, CRCs, duplex mismatches, flapping, speed negotiation issues, and counter trends on routers, switches, and Linux hosts. Use when an interface shows errors, drops, CRCs, flapping, or a duplex or speed mismatch.

Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.

Instrument a LaunchDarkly metric event in a codebase by adding a track() call. Use when the user wants to wire up an event, instrument an action for a metric, add tracking to a feature, or confirm that an event is flowing to LaunchDarkly.

Turn docs/product/SCENARIOS.md into testable claims for the deployed-stand suite — QA scenario design for Insight. Pick a scenario (S-1…S-10), a persona (EXEC/LEAD/IC/ADMIN), an invariant (§5 rules 1-12) or an Appendix A question (A1…G4), ground it in the seeded roster, and emit claims with an oracle, a layer and a priority that stand-api-test / stand-ui-test can implement. Use when the task is deciding WHAT to test: 'what should we test for S-9', 'design e2e scenarios from the product doc', 'which product rules are unverified', 'is the IC boundary covered', 'plan coverage for the reach matrix', 'convert the scenarios doc into tests'. Not for writing test code — that is stand-api-test and stand-ui-test; for scoping tests from a GitHub issue or an unbuilt feature use scope-feature-tests instead.

Fetch a real product's current price, stock, rating, or images from retailer pages over the Apify MCP server, and return them as typed fields rather than prose. Use when someone asks what a product costs right now, whether it is in stock, how it is rated, to compare a product across retailers, or to check a product URL they pasted. Also use when an agent would otherwise answer a product question from training data. Not for managing your own store's catalog, not for payments, and not for questions answerable without live retailer data.

Control-plane workflow for coordinating multi-agent, multi-session project work from a single Codex, GitHub Copilot, or agent-app control session. Use this skill whenever the user asks to orchestrate agents, create or steer worker sessions, run a workflow-like effort, fan out audits/research/migrations, coordinate parallel implementation streams, monitor other project sessions, or compare this control-session pattern to Claude Code dynamic workflows. This skill is especially relevant when the current session can spawn persistent project sessions and those sessions can spawn their own subagents, creating a two-level orchestration hierarchy.

Audita o peso de contexto carregado na sessão — CLAUDE.md, agents, MCP descriptions, rules ativas, skills invocadas e histórico acumulado. Estima tokens por componente, reporta headroom disponível e emite alertas de overflow. Distinto do cost-tracker (skill 30) que rastreia tokens gastos em completions runtime. Trigger em: "contexto inchado", "context overflow", "quanto contexto estou usando", "peso do contexto", "context budget", "tokens carregados", "sessao lenta", "respostas degradadas", "headroom de contexto", "custo fixo de contexto", "overhead de rules", "overhead dos agents", "impacto do MCP no contexto", "espaco no context window", "quanto cabe no context window"

Captura screenshots via Playwright MCP de URLs/elementos pra usar em posts de blog ou documentação. Lida com viewport, cookie banners, full-page vs section, scroll a âncora, formatos PNG/JPG. Compõe com skill 41 (blog-publisher). Trigger em: "tira print", "screenshot do site", "captura tela", "screenshot da página", "print da landing", "print do dashboard", "screenshot pro blog".