Menu
Skills dans ce dépôt
SkillsMP a collecté 1 540 skills depuis MadewellRD/skills-lab. Ouvrez un skill pour examiner sa source et ses détails.
MadewellRD/skills-labAffichage de 40 skills collectés sur 1 540.
design and review on-call rotations and escalation including coverage and follow-the-sun arrangements, primary and secondary tiers with acknowledgement and response expectations, shift handoff and transfer of open state, page load budget and out-of-hours…
Langue du texte source : anglais
write and facilitate blameless postmortems and incident reviews with a timeline anchored to timestamped evidence, contributing factors across technical detection and process dimensions, counterfactual discipline that resists the single root cause story, a…
Langue du texte source : anglais
run a production readiness review or support acceptance review with a gate set scored pass, waived, failed, or not assessed against named evidence, a launch or acceptance decision with conditions, waivers carrying a named owner and an expiry date, hand-back…
Langue du texte source : anglais
run the recurring service reliability review covering error budget attainment and burn across the period, error budget policy adjudication including whether a freeze applies and its exception path, incident page and toil trends, open postmortem actions and…
Langue du texte source : anglais
design timeout and retry budgets, circuit breakers, bulkheads, load shedding and admission control, backpressure, cache and stale-serve fallbacks, idempotency and replay safety, and graceful degradation modes, and record whether each control is configured,…
Langue du texte source : anglais
write and review operational runbooks keyed to the alert or failure mode that triggers them, with the first mitigating action stated before diagnosis, diagnostic decision trees carrying exact queries and dashboards, escalation and rollback branches, access…
Langue du texte source : anglais
map critical user journeys to the services on their path, assign criticality tiers using an explicit tiering rule, attribute ownership and pager rotation per service, and name every service with no owner, no tier, or a rotation that resolves to nobody. use…
Langue du texte source : anglais
specify service level indicators per critical user journey including the good-event and valid-event definitions, the measurement point and its bias, the implementation query or export behind each indicator, and the split between measured, partially measured,…
Langue du texte source : anglais
set service level objectives with windows, define and compute the error budget and its balance, account for burn rate over multiple windows, write an error budget policy with consequences that bind someone, and separate objectives agreed with the owner from…
Langue du texte source : anglais
orchestrate site reliability engineering work across slis, slos, error budgets, capacity planning, load and performance testing, chaos and resilience testing, dependency and failure-mode analysis, disaster recovery, backup and restore, alerting quality,…
Langue du texte source : anglais
account for operational toil with measured hours and how they were established, classify each recurring task as automatable partially automatable or inherent, define the elimination path per task through automation self-service or a design change that removes…
Langue du texte source : anglais
define accessibility and seo requirements for web surfaces including wcag, semantic html, keyboard navigation, focus, screen-reader behavior, metadata, structured data, canonicals, sitemaps, robots, crawlability, localization, and page-type search…
Langue du texte source : anglais
plan web backend integration across api contracts, auth, sessions, bff layers, cms connections, data models, caching, rate limits, pagination, failure modes, and ownership. use when a web surface depends on services, databases, third-party systems, identity,…
Langue du texte source : anglais
define cms and content operations for web properties including structured content models, editorial workflow, publishing rules, approvals, localization, migration, governance, content debt, metadata ownership, and day-two content maintenance. use for…
Langue du texte source : anglais
create implementation-ready frontend engineering plans for web surfaces including rendering strategy, routing, layouts, components, state, forms, data fetching, framework constraints, accessibility hooks, performance controls, and coding-agent handoffs. use…
Langue du texte source : anglais
design web information architecture including sitemap, route hierarchy, navigation, url taxonomy, content relationships, wayfinding, content hierarchy, and findability. use when the assistant needs to structure websites, portals, dashboards, docs sites,…
Langue du texte source : anglais
create web-specific product requirements, page and route scope, user journeys, acceptance criteria, success metrics, analytics intent, source facts, risks, open questions, and downstream handoff notes for websites, web apps, landing pages, portals,…
Langue du texte source : anglais
define ux/ui design system guidance for web surfaces including component inventory, responsive behavior, design tokens, interaction states, accessibility-aware patterns, brand consistency, and design governance. use before frontend implementation or…
Langue du texte source : anglais
orchestrate complete web development workflows across product, information architecture, ux/ui design systems, frontend engineering, backend integration, cms/content operations, web security/secops, performance, accessibility, seo, testing, observability,…
Langue du texte source : anglais
coordinate post-launch web maintenance and growth including analytics-informed backlog, experiments, conversion optimization, content refresh, seo iteration, accessibility remediation, performance regression follow-up, dependency upgrades, refactors,…
Langue du texte source : anglais
design production web observability including rum, synthetic checks, availability, frontend errors, api errors, latency, core web vitals, analytics events, dashboards, alerts, ownership, incident hooks, launch monitoring, and post-launch review. use before…
Langue du texte source : anglais
plan and gate web performance using core web vitals, performance budgets, rendering cost, hydration, bundle size, images, fonts, scripts, cdn, caching, data fetching, latency, field and lab measurement, launch thresholds, and regression controls. use before…
Langue du texte source : anglais
plan web release and deployment across ci/cd, preview environments, build commands, environment promotion, hosting, cdn, edge config, cache invalidation, feature flags, launch checklist, rollback, post-release validation, and release-to-observability handoff.…
Langue du texte source : anglais
review and plan web security and secops controls across auth, sessions, browser storage, cookies, csp, security headers, cors, csrf, dependency risk, secrets, third-party scripts, cdn/edge hardening, abuse prevention, monitoring hooks, and incident readiness.…
Langue du texte source : anglais
define web testing and qa strategy across browsers, devices, responsive layouts, visual regression, forms, auth flows, integrations, accessibility checks, seo checks, performance checks, smoke tests, regression tests, release signoff, and defect triage. use…
Langue du texte source : anglais
design AI agent architecture including planning boundaries, execution loops, memory and state strategy, tool routing, approval gates, retries, delegation, and halt behavior.
Langue du texte source : anglais
design observability for AI agents and workflows including traces, prompts, model calls, tool calls, retrieval events, approvals, errors, eval probes, cost, latency, and safety signals.
Langue du texte source : anglais
orchestrate AI engineering workflows from capability intent through model, prompt, tool, agent, retrieval, eval, safety, inference, observability, release, and incident stages using connector-grounded evidence, workflow packets, stage advancement, and halt…
Langue du texte source : anglais
triage AI production incidents involving hallucination spikes, safety failures, prompt injection, tool misuse, data leakage, model regressions, cost spikes, latency degradation, eval regressions, or user harm reports.
Langue du texte source : anglais
assess readiness to release AI capabilities across requirements, evals, safety review, red-team status, inference ops, observability, rollback, docs, support handoff, and owner approval.
Langue du texte source : anglais
review AI capability risks including misuse, policy compliance, privacy, security, hallucination harm, data leakage, autonomy, tool-use risk, user impact, and mitigations.
Langue du texte source : anglais
optimize AI system cost and latency using model routing, caching, prompt compression, context pruning, batching, streaming, parallelism, retrieval tuning, and fallback tiers while preserving quality and safety gates.
Langue du texte source : anglais
plan and review AI datasets for source selection, labeling, balancing, privacy, deduplication, train and eval splits, drift, provenance, consent, and retention.
Langue du texte source : anglais
design AI evaluation plans with goals, datasets, rubrics, grading methods, thresholds, regression slices, safety checks, human review, and reporting requirements.
Langue du texte source : anglais
analyze completed AI eval runs, regression deltas, failure clusters, grading reliability, threshold status, release blockers, and rerun recommendations.
Langue du texte source : anglais
assess and plan fine tuning only when prompt, retrieval, tool, model routing, and eval evidence justify training a specialized model.
Langue du texte source : anglais
plan production inference operations including deployment topology, rate limits, quotas, retries, caching, streaming, fallbacks, batching, timeouts, secrets, logging, and SLOs.
Langue du texte source : anglais
select model candidates, routing constraints, fallback behavior, and model tradeoffs for AI capabilities using task fit, quality, latency, cost, safety, modality, context, and deployment evidence.
Langue du texte source : anglais
design prompt systems, instruction hierarchy, context assembly, prompt contracts, refusal and defer behavior, prompt evaluation fixtures, prompt injection defenses, and prompt observability hooks for AI capabilities.
Langue du texte source : anglais
plan and analyze adversarial AI testing for jailbreaks, prompt injection, data exfiltration, harmful instructions, over-permissioned tools, and policy evasion.
Langue du texte source : anglais