AI skill registry

End-to-end Agent Observability pipeline for an instrumented mlapp — classify production traces, root-cause failures, bootstrap evaluators, then (optionally) sample + publish a dataset, generate + run an experiment, and analyze results. Six narrated phases with a standardized banner and a "continue" checkpoint between each. Pure orchestration over the agent-observability sub-skills (agent-observability-session-classify, agent-observability-trace-rca, agent-observability-eval-bootstrap, agent-observability-experiment-py-bootstrap, agent-observability-experiment-analyzer). Use when user says "run the eval pipeline", "go from traces to evals", "bootstrap evals end to end", "classify then RCA then bootstrap", "build an eval set from scratch", "onboard me to datasets and experiments", "walk me through experiments", "I have an mlapp, now what", "Agent Observability onboarding", "guided experiment setup", "from traces to experiments", or wants a deterministic, narrated tour from production data through evaluators, datasets, and experiments. Stop early with --stop-after <phase> to short-circuit at evaluators or dataset, or resume mid-flow with --start-at <phase>.

Datadog CLI (Rust). OAuth2 auth with token refresh.

Agent Skill for Baidu Netdisk (百度网盘) — upload, download, transfer, share, search files via natural language.

Analyze LLM experiment results. Handles single or comparative experiments, exploratory or Q&A modes. Use when user says "analyze experiment", "compare experiments", "analyze against baseline", or provides one or two experiment IDs for analysis.

Investigate a potentially compromised Datadog API key — timeline of actions, geo/IP breakdown, endpoints called, anomaly flags, and remediation steps.

Datadog skills for AI agents. Essential monitoring, logging, tracing and observability.

Recommends the right Datadog products for a codebase and/or a stated goal — grounded in a tech-stack→product map and a use-case→product map built from Datadog product capabilities and common technology patterns. Recommendation only; no setup instructions. Use when a user asks which Datadog products fit their app, what to monitor, or which products serve a goal like security, cost, or LLM observability.

Verify Single Step Instrumentation (SSI) is working end-to-end on Kubernetes — SSI automatically instruments applications for APM without code changes. Only use after enable-ssi has run.

Agent Skill for Baidu Netdisk (百度网盘) — upload, download, transfer, share, search files via natural language.

Investigate a Datadog product usage or cost spike by correlating Usage Metering data (when/what spiked) with Audit Trail config changes (who changed what in the preceding window).

Diagnose and fix Single Step Instrumentation (SSI) issues on Kubernetes — SSI automatically instruments applications for APM without code changes. Only use if the agent and SSI are already configured but traces are missing or instrumentation is not working.

Publish Markdown/HTML articles to WeChat Official Account (微信公众号) drafts via API

APM - install, onboard, instrument, enable, set up, configure, traces, services, dependencies, performance analysis. Use for any request involving Datadog APM setup, instrumentation (SSI, ddtrace, agent install), or analysis.

Load when investigating a failing PR CI pipeline or checking PR health. Attributes each CI failure as flaky, infra, or regression, proposes a targeted action, and reports code coverage and quality/security status.

Imagine your project has failed spectacularly—then work backward to identify why. Apply Gary Klein's "prospective hindsight" technique to catch failures before they happen. Use when: Before launching a product, campaign, or major initiative; Before making an important decision (hiring, investment, partnership); Starting a project to identify risks the team hasn't considered; When overconfident and everyone agrees the plan is great; Before committing resources to a signific...

Install the Datadog Agent on Kubernetes using the Datadog Operator — required before enabling Single Step Instrumentation (SSI), which automatically instruments applications for APM without code changes. Only use if no Datadog Agent is deployed on the cluster yet.

Generates a self-contained Python experiment client that uses the ddtrace.llmobs SDK. Emits either a runnable .py script or a Jupyter .ipynb notebook matching the canonical DataDog reference notebook style. Use when the user says "generate Python experiment", "write an SDK experiment", "create a ddtrace experiment", "Python notebook experiment", "use the Agent Observability SDK", or has ddtrace installed and wants idiomatic SDK code.

Create research-backed buyer personas that drive real marketing and product decisions. Combine Buyer Personas methodology with Jobs-to-be-Done to build profiles based on actual behavior, not demographics fiction. Use when: Starting customer discovery to define who you're validating with; Marketing campaign planning to target the right messages to right people; Content strategy to create content that resonates with specific audiences; Product roadmap prioritization to build fea...

Create and manage APM service remapping rules — rewrite service names at ingestion time to collapse noisy inferred entities, clean up auto-generated names, handle org renames, or normalize naming conventions. Use for any request involving service renaming, service mapping, inferred service cleanup, peer.service normalization, or collapsing fragmented service names.

Log management - search, archives, metrics, and cost control.

Use when rewriting AI-generated text to match a specific person's or brand's authentic voice. Use when AI output sounds generic, corporate, or detectable. Unlike generic "humanizers," this skill requires voice analysis input and produces voice-consistent output, not fake imperfections.

Guides developers building Datadog Apps with TypeScript, React, the @datadog/apps scaffolder, and @datadog/vite-plugin. Use when a user wants to scaffold, run, debug, upgrade, build, upload, publish, upload without publishing (draft upload), add an upload-no-publish script, set up CI/CD, use OAuth or API/application key auth, trigger/poll Workflow Automation, choose DDSQL or Action Catalog for backend data access, or query app datastores with DDSQL, including backend function troubleshooting.

Root cause analysis on production LLM traces. Diagnoses why an LLM application is failing — works from eval judge verdicts, runtime errors, or structural anomalies depending on what signals are present. Walks the span tree from symptom to root cause. Use when user says "what's wrong with my app", "why is my eval failing", "analyze errors", "root cause analysis", "diagnose failures", or wants to understand production failure patterns.

Know when to move fast and when to move carefully. Master Jeff Bezos' framework for distinguishing high-stakes irreversible decisions from low-stakes reversible ones. Use when: Prioritizing decisions to know where to invest time; Team empowerment to understand what to delegate vs. escalate; Avoiding analysis paralysis on decisions that don't matter; Risk management to identify where caution is truly warranted; Speed vs. thoroughness trade-offs in any context

Audit Trail investigations - who changed what, key compromise, cost spike root cause, compliance evidence (SOC 2/PCI), and AI activity auditing.

Monitor management - list, search, file-based create, and alerting best practices.

Ensure GDPR compliance for marketing activities including consent management, data processing, privacy notices, and data subject rights

Audit what the Bits AI assistant (MCP server) has done in your Datadog org — tool calls by user, resources accessed, and anomaly flags for AI governance.

Bootstrap evaluators from production traces — by default propose online LLM-judge evaluators and, after you confirm, create them in Datadog as disabled drafts (never auto-enabled); on request emit Python SDK code or a framework-agnostic JSON spec instead. Use when user says "bootstrap evaluators", "generate evaluators", "create evals from traces", "eval bootstrap", "write evaluators", "build eval suite", "publish evaluators", or wants to generate BaseEvaluator/LLMJudge code or online judge configs from production LLM trace data. Works with ml_app and optional RCA report or failure hypothesis.

Master the consultative sales methodology trusted by enterprise sales teams worldwide. Use Neil Rackham's research-backed question sequence to uncover needs and close complex deals. Use when: Complex B2B sales with long sales cycles; High-value deals requiring multiple stakeholders; Solution selling where discovery is critical; Enterprise sales with sophisticated buyers; Consultative positioning to differentiate from competitors

Generate auditor-ready compliance evidence from Datadog Audit Trail for SOC 2 and PCI DSS. Maps framework controls to specific query patterns and produces formatted output.

Generate a live Single Step Instrumentation (SSI) onboarding confirmation report — verifies APM instrumentation is working end-to-end with deep links into the Datadog UI. Only use after agent-install and enable-ssi have both completed successfully.

Process video files with ffmpeg automation. Use when: compressing videos for upload; extracting audio from video; resizing for social formats; clipping segments; merging multiple videos; generating thumbnails

Answer "who did what" security questions from Audit Trail — deletions, config changes, login activity, permission changes, actions from a specific user or IP.

Load when investigating a specific flaky test. Gets history, failure pattern, and category, then recommends fix, quarantine, or escalate.

Use when optimizing for AI search visibility where individual experts and entities outperform generic brand pages. Use when building cross-platform authority for people, organizations, or products that AI models should recognize and cite.

Datadog docs lookup using docs.datadoghq.com/llms.txt and linked Markdown pages.

Discover where your audience actually pays attention online using Rand Fishkin's behavioral intelligence methodology—beyond demographics to actionable media affinity data. Use when: Find where to reach your audience beyond Google and Facebook ads; Discover podcasts, YouTube channels, and publications your audience follows; Identify influencers and accounts with real audience overlap; Plan PR and media outreach with data-backed target lists; Improve ad targeting on YouTube,...

Collect and organize user-generated content. Use when: gathering customer testimonials; collecting product photos; organizing social mentions; building UGC campaigns; managing brand mentions

Manage the customer renewal process with health-based playbooks, timeline tracking, and risk mitigation strategies

Transformez l'attention en conviction avec des séquences email evergreen qui font progresser les leads de curiosité → confiance → call booké, basé sur la méthodologie A5 du Marketing Swarm de Lasse Flagstad. Use when: Créer une séquence evergreen - Emails automatiques qui tournent indéfiniment; Réactiver une liste froide - Réveiller des leads dormants sans spam; Structurer le nurturing post-lead-magnet - Que se passe-t-il après l'opt-in?; Définir les segments et triggers - HOT...

Process large codebases (>100 files) using the Recursive Language Model pattern. Orchestrates parallel sub-agents to map-reduce across files without context rot. Use when: analyzing large repositories; auditing security or auth across many files; finding patterns across 50+ files; processing large log files or data dumps

Use when analyzing server logs to understand how AI crawlers (GPTBot, ClaudeBot, PerplexityBot) interact with your site. Use when optimizing content placement for LLM retrieval, diagnosing why AI search isn't citing your content, or auditing crawl patterns to find optimization gaps.

Build marketing that people actually want using Seth Godin's Permission Marketing methodology—earn attention instead of demanding it, turning strangers into friends and friends into customers. Use when: Build an email list that's engaged and valuable; Design lead magnets that earn real permission; Create content strategy based on earning attention; Evaluate marketing tactics for permission vs. interruption; Improve email marketing by increasing anticipation and relevance

Extract structured data from websites. Use when: collecting competitor pricing; scraping product listings; extracting contact information; gathering research data; monitoring website changes

"What is important is seldom urgent and what is urgent is seldom important." Master Dwight D. Eisenhower's prioritization framework to focus on what truly matters. Use when: Feeling overwhelmed by too many tasks and not enough time; Weekly planning to set priorities for the week ahead; Daily triage when everything seems urgent; Delegation decisions to identify what others should handle; Saying no by recognizing tasks that shouldn't be done at all

Build and apply lead scoring models combining firmographic fit, behavioral signals, and intent data for sales prioritization

Model best-case, worst-case, and likely revenue scenarios with sensitivity analysis for strategic planning. Use when: building financial forecasts; presenting board scenarios; planning headcount around revenue uncertainty; modeling pricing changes impact; preparing investor updates with upside/downside ranges