skills

Install, update, or verify the complete SylphxAI/skills managed environment for the current Codex, Claude Code, or Grok runtime, including AutoSync and canonical Sylphx Enact SaaS enrollment. Use when a user gives this repository and says "install this", asks to update Sylphx Skills, or requests installation readback. Read the repository's INSTALL.md before choosing any generic Skill installer; folder copies alone are incomplete, and other runtimes stay untouched unless the user explicitly includes them.

Shipped-state proof across source landing, artifacts, deployment, rollback, and production readback. Use when delivering a change or deciding whether it is truly released or live. Do not use when only local implementation is in scope.

Connect, operate, or audit agent work through the Sylphx Enact operating graph using explicit Tenant, Workspace, and optional Project identity; Work proposals, claims, runs, checkpoints, evidence, effects, subscriptions, and external-provider observations. Use when implementing an Enact client or adapter, binding a repository or agent workflow to Enact, recovering a missing MCP work loop, or verifying Enact work provenance. Do not use for portable work-ledger design, ordinary Git operations, or static Skills authoring.

Design or critically review a complete app as a coherent, agent-first App Design Blueprint: user job and promise, workflows and information architecture, first-use activation, capability portfolio, retention and durable ownership, commerce and social integration, feedback and review loops, responsive HTML5/mobile/desktop experience, desktop OS integration semantics, offline and sync, accessibility, localization, low-end performance, privacy, safety, autonomous construction, and validation. Use for a new consumer or productivity app, whole-app redesign, cross-platform app system, a bounded macOS/Windows integration design that must remain consistent with app state, or an audit of whether product capabilities form one scalable experience. Use specialist procedures for one payment, refund, notification, review, campaign, store submission, exact release artifact, or file-level interface artifact unless whole-app coherence is also being decided.

Design or audit the end-user developer journey for an API, SDK, CLI, plugin, app integration, or developer platform across discovery, docs, installation, credentials, sandbox, first success, production readiness, diagnostics, support, certification, recertification, and retained use. Use when the primary artifact is a Developer Adoption Contract joining those surfaces into one measurable experience. Do not use for API or SDK implementation, API versioning policy alone, infrastructure capacity, developer quota or credit abuse policy, generic product abuse, or product analytics instrumentation alone.

Design or audit a game soft-launch learning and exposure program across regions, cohorts, acquisition sources, FTUE, core/meta loops, retention, economy, IAP/IAA, live events, store creative, crashes/performance, support/community, global-transfer risk, and automated scale/hold/pause/withdraw gates. Use when a production-shaped game is entering bounded real-player exposure; use Game Design for the game itself and Distribution Readiness for store submission/certification.

Produce or audit one cross-domain launch admission verdict for an app, game, SaaS, desktop product, developer tool, marketplace, major release, beta, or campaign. Integrate exact product, quality, performance, security/privacy, payments, distribution, analytics, support, marketing, legal/authority, rollback, and post-launch evidence into go, conditional-go, hold, or no-go gates. Use when launch-day decision ownership is the artifact; use specialist skills to create missing domain evidence.

Design or critically review a complete autonomous marketing operating system across truth-bound positioning, audiences and consent, owned/earned/paid channels, creative and content, SEO/AEO, stores, lifecycle messaging, referrals, cross-promotion, creators, community, partnerships, reputation, attribution, incrementality, budget allocation, experiments, and autonomous maintenance. Use when the primary artifact is a multi-channel marketing control plane or full go-to-market operating blueprint. For one campaign, official social-account operating model, referral, listing, notification, review/feedback loop, or distribution package, use the specialist procedure.

Create or audit one exact, localized, accessible, rights-safe Product Asset Production Pack for apps and games: deterministic product captures, screenshots, icons/key/capsule art, feature graphics, trailers, demos, short/long video, captions, audio description, alt text, and store, website, YouTube, X, social, PC, console, mobile, and HTML5 variants. Use when approved product truth and Marketing or Store Listing briefs must become finished media files with provenance and QA. Marketing owns message and campaign briefs; Store Listing owns narrative, selection, order, and metadata; Distribution owns upload, certification, release, and live evidence.

Orchestrate a multi-artifact product program across experience design, commerce, distribution, globalization, SDKs, marketing, support, operations, delivery, and autonomous maintenance. Use when the primary artifact is the cross-domain dependency, handoff, validation, or delivery graph; when a product program spans at least three lifecycle domains; when an ecosystem certification program must compose eligibility, tests, trust signals, renewal, appeals, and operations; or when app/game, global platform release, marketing, and operations must converge on one build-to-scale target. Do not use as primary for whole-app design, whole-game design, a marketing operating system, one campaign/listing/refund, or one product's store-submission readiness.

Design or critically review one complete modern SaaS web platform joining public acquisition surfaces and an authenticated product across value proposition, onboarding, UI/UX, web performance, SEO, PWA disposition, identity, organizations, billing and entitlements, notifications, support, security, privacy, analytics, operations, and global scale. Use when the whole SaaS platform blueprint is the independent artifact; use specialists for one interface, price, payment, refund, notification, identity, marketing, or release job.

Design, prepare, or audit one exact-artifact Software Distribution Contract and Distribution Evidence Pack for command-line tools, apps, games, web, desktop, PC, console, direct downloads, package managers, registries, containers, and stores. Use when an already-designed software product needs channel selection, target packages, signing and provenance, install/update/uninstall behavior, submission or certification, rollout, recovery, publication, or live consumer readback. Do not use for whole-product design, a single library-registry publish with no distribution decision, listing conversion strategy, asset creation, or a cross-domain launch verdict.

Design or audit one channel listing and creative-conversion artifact for App Store, Google Play, Steam, console/PC stores, Microsoft Store, browser extensions, or direct download: positioning, title/subtitle/description, screenshots, capsule/icon/key art, trailer, proof, pricing/disclosures, privacy/compatibility claims, localization, accessibility, experiments, review/reputation context, and exact asset QA. Use for listing conversion; use Distribution Readiness for submission/certification and Marketing Automation for the full channel portfolio.

Apply binding engineering constraints when implementing, fixing, debugging, designing, reviewing, refactoring, or migrating durable product code, APIs, handlers, workers, architecture, capabilities, DDD/Clean/Hexagonal boundaries, functional cores, contracts, storage, concurrency, security, tests, observability, or delivery-critical runtime paths. Use when code or runtime behavior is the artifact; use a specialist procedure when a whole observability, security, migration, or product contract is primary.

Design or audit a falsifiable, exact-candidate runtime auto-injection and behavior evaluation for one Agent Skill or a complete catalog: positive, near-neighbour, abstention, compound injection, hidden tasks, controls, independent model families, deterministic artifact and safety checks, provenance, uncertainty, replay, and regressions. Use when proving incremental behavior, not when authoring a skill or building a router.

Semantically curate an Agent Skills portfolio: audit native name/description triggers, false negatives and collisions, recurring jobs and artifacts, package boundaries, progressive-disclosure thickness, ownership, consolidation, recovery, and retirement. Use when creating, cleaning, splitting, merging, or reviewing a complete skills repository. Do not use to author one skill from one source, evaluate runtime behavior experimentally, or build a router or marketplace.

Design or audit one complete in-product advertising system for apps, games, web, and content products: rewarded ads, interstitials, banners/native placements, offerwalls, mediation, payer suppression, reward authority, consent, age/territory modes, frequency and fatigue budgets, IAP/IAA cannibalization, fraud, experiments, and shutdown. Use when deciding ad formats, placements, rewards, provider portfolio, or ad economics; combine with an App or Game Blueprint only when whole-product coherence is also unresolved.

No-human parallel development packets, change attribution, collision scopes, and machine-verifiable acceptance. Use when defining or running multi-agent software delivery without a human review dependency. Do not use for a small local edit or live Work Graph operations.

Apply agent-native product constraints for queryable typed state, schema-derived tools, recoverable workflows, delegation, durable context, and model/tool/agent-run traces with protected operator diagnostics. Use when designing a product, API, or workflow that agents must operate directly and recoverably. Do not use for ordinary automation, generic service observability, or product analytics without an agent-facing contract.

Autonomous scheduling: critical-path focus, parallelism budgets, delegated outcomes, replanning, and honest evidence layers. Use when a non-trivial task should continue through multiple independent work lanes without repeated user direction. Do not use for a short direct answer or edit.

CI admission tiers, gate-portfolio discipline, affected-test selection, required checks, flake control, and preview policy. Use when designing, adding, removing, consolidating, or auditing checks that decide whether a candidate may merge, including custom lints and architecture tests. Do not use for debugging one unrelated test failure.

Design or diagnose CI runner capacity, queue/pickup latency, execution profiles, merge-queue backpressure, inventory uncertainty, and critical-path isolation. Use when CI jobs wait, runners disappear, queues saturate, or capacity policy must change. Do not use for a candidate failure caused by product code.

Pricing, packaging, entitlements, commercial ADRs, and market-positioning evidence. Use when making a durable revenue, packaging, licensing, or route-to-market decision. Do not use for implementing an already-decided checkout or billing contract.

Design or audit a recurring Data Reliability Contract for data products and pipelines—datasets, streams, imports, transformations, warehouses, and search/operational projections—across freshness, completeness, semantic drift, reconciliation, trust state, repair, and consumer impact. Use when ongoing data fitness is the primary artifact. Do not use for one bounded customer/tenant migration, search relevance/ranking quality, a general provenance/custody graph, product analytics metrics, ledger truth, privacy, or active incident response alone.

Select among materially distinct technical, product, commercial, or operating options and record the commitment, trade-offs, reversibility, and decision evidence. Use after credible options are formed and one durable choice is required. Do not use for unknown-cause diagnosis, exact-candidate pass/fail review, trivial reversible edits, or execution of an already selected option.

Documentation scope, minimal sufficient docs, generated references, and freshness without prose drift. Use when deciding what durable documentation to create, update, generate, or retire. Do not use for changing product behavior without documentation ownership questions.

Organization-wide manifests, rulesets, selectors, reconcilers, audits, and status projections. Use when one policy or adoption decision must apply consistently across many repositories. Do not use for a product-local setting with no cross-repository owner.

Versioned enterprise profiles: selectors, current defaults, exceptions, replacement, and migration. Use for static organization-wide selections and their lifecycle; Sylphx Enact owns resolved live state.

Evaluation gates, replay oracles, and canary backstops for nondeterministic systems. Use when deterministic unit and integration tests cannot fully verify AI, probabilistic, distributed, or time-dependent behavior. Use CI Admission for flaky-check attribution or quarantine; do not add frontier mechanisms to an ordinary deterministic code path.

Design or audit one complete game economy artifact for mobile, PC, console, web, casual, premium, or live-service games: currencies, inventory, sources/sinks, progression pacing, rewards, gacha/pity, battle passes, IAP/ads, events, refunds/revocation, inflation, concentration, anti-abuse, newcomer/veteran fairness, simulations, and live tuning. Use for economy ownership and balance; use Game Design for whole-game coherence and Payment Readiness for provider transactions.

Compress or restructure an agent communication into a concise, decision-complete, high-signal artifact. Use when the user explicitly asks to shorten, de-duplicate, hand off, summarize progress, reduce context cost, or repair a verbose/slow-to-understand reply, report, commit, PR, ADR, spec, incident note, or agent record. Do not inject by default for every ordinary reply or document.

Apply the operational incident lifecycle: detection, severity, command state, mitigation, recovery verification, communication, and machine-checkable postmortem. Use when responding to or reviewing an active/recent service incident, or designing that incident lifecycle. Do not use for general proactive observability, resilience design, or an ordinary defect with no incident or customer/service impact.

Evolution of Skills, runtime constitutions, required profiles, and architecture generations with one writable owner, migration, reconciliation, and retirement. Use for durable instruction or profile changes, not live Work Graph operations.

Plan, execute, and audit a substantial software or architecture migration in one or many repositories. Use for Capability-first DDD adoption, language/runtime rewrites, monolith restructuring, drop-in replacements, or required architecture cutovers that need independently verifiable slices. Inventory behaviors/contracts/surfaces, refactor real code, prove exact-candidate semantics, choose lifecycle-appropriate cutover, retire legacy structure, and invalidate stale proof.

Design or audit one cross-channel notification policy across push, email, in-app messages, SMS, browser, and desktop: permission and consent, preferences, taxonomy, trigger semantics, channel routing, frequency and fatigue, privacy, dedupe, deliverability, withdrawal, and observed zero-send. Use when those message-wide controls are the primary artifact. For one win-back, lifecycle-push, offer, event, or promotion campaign's objective, audience, eligibility, economics, fulfillment, and shutdown, use promotion-campaign-review.

Design or audit one offline/local-first synchronization and conflict protocol: local storage, queued mutations, idempotency, causality/order, reconnect, tombstones, optimistic states, multi-device/collaborative merges, attachments, auth expiry, encryption, schema migration, data-loss recovery, UX, sync-domain evidence, and chaos tests. Use when unreliable connectivity or concurrent edits need an independently acceptable sync artifact; use App Design for whole-product workflows.

Design operational observability with protected operator evidence and intentional audience-safe customer/public projections. Use when an end-to-end service operating and diagnostic-access contract—logs, metrics, traces, health/readiness, SLOs, alerts, and actions—is the primary artifact. Do not use for product analytics, one feature instrumentation edit, an active incident, recurring data-product quality, or agent tracing alone.

Parallel agent change integration with compare-and-swap landing, bounded duplicate attempts, verification watermarks, and verified-only promotion. Use when candidate generation can outpace shared verification or deployment capacity. Do not use for ordinary low-contention edits.

Design or audit a Product Analytics Event, Identity, and Metric Contract for decision questions, behavior events, identity, consent, delivery, product metrics, QA, dashboards, and drift. Use when trustworthy product measurement is the independent artifact. Do not use for service logs/traces/health/SLOs/alerts/operator diagnostics, generic data-pipeline reliability, active incidents, product strategy, or payment truth.

Repository identity, lifecycle, capability and component ownership, public boundaries, delivery facts, and adoption gaps through PROJECT.md and the machine project manifest. Use when creating, changing, or validating a repository's durable identity and boundaries.