azure-samples/eshoplite
44 skills
$npx skills add azure-samples/eshopliteSkillInstalls
agent-collaborationStandard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communicationagent-conductShared hard rules enforced across all squad agentsagentic-modernizationReusable session pattern for modernized .NET apps that add observability, grounded search, reporting, MCP tools, and A2A agents.architectural-proposalsHow to write comprehensive architectural proposals that drive alignment before code is writtenaspire-session-packagingPackage an Aspire modernization session with docs, demo flow, and architecture notesci-validation-gatesDefensive CI/CD patterns: semver validation, token checks, retry logic, draft detection — earned from v0.8.22cli-wiringBug class: Commands implemented in packages/squad-cli/src/cli/commands/ but never routed in cli-entry.ts.client-compatibilityPlatform detection and adaptive spawning for CLI vs VS Code vs other surfacescross-machine-coordinationSkill ID: cross-machine-coordination Owner: Ralph (Work Monitor) Squad Integration: All agents Status: Specification (ready for implementation)cross-squadCoordinating work across multiple Squad instancesdistributed-meshHow to coordinate with squads on different machines using git as transportdocs-standardsKeeps scenario README files and session docs aligned with the repo's documentation conventions.economy-modeShifts Layer 3 model selection to cost-optimized alternatives when economy mode is active.error-recoveryStandard recovery patterns for all squad agents. When something fails, adapt — don't just report the failure.external-commsPAO workflow for scanning, drafting, and presenting community responses with human review gategh-auth-isolationSafely manage multiple GitHub identities (EMU + personal) in agent workflowsgit-workflowSquad branching model: dev-first workflow with insiders preview channelgithub-multi-accountDetect and set up account-locked gh aliases for multi-account GitHub.history-hygieneRecord final outcomes to history.md, not intermediate requests or reversed decisionshumanizerTone enforcement patterns for external-facing community responsesinit-modeTeam initialization flow (Phase 1 proposal + Phase 2 creation)iterative-retrievalMax-3-cycle protocol for agent sub-tasks with WHY context and coordinator validation. Use when spawning sub-agents to complete scoped work.model-selectionDetermines which LLM model to use for each agent spawn.napContext hygiene — compress, prune, archive .squad/ statenotification-routingRoute agent notifications to specific channels by type — prevent alert fatigue from single-channel floodingpersonal-squadA personal squad is a user-level collection of AI agents that travel with you across projects.pr-review-responseTeaches agents to reply to PR review comment threads after fixing issues, making resolutions traceablepr-screenshotsCapture Playwright screenshots and embed them in GitHub PR descriptionsproject-conventionsCore conventions and patterns for this codebaseralph-two-pass-scanConfidence: high Domain: work-monitoring Last validated: 2026-03-24reflectLearning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating mistakes.release-processEarned knowledge from the v0.9.0→v0.9.1 incident. Every agent involved in releases MUST read this before starting release work.reskillTeam-wide charter and history optimization through skill extractionretro-enforcementEnsure retrospectives happen on schedule and that their action items are tracked in GitHub Issues — not markdown checklists.reviewer-protocolReviewer rejection workflow and strict lockout semanticsscenario-baseline-cloningClone the closest existing eShopLite scenario baseline before adding a new modernization story.secret-handlingNever read .env files or write secrets to .squad/ committed filessession-recoveryFind and resume interrupted Copilot CLI sessions using session_store queriessquad-conventionsCore conventions and patterns used in the Squad codebasetemplates{what this skill teaches agents}test-disciplineUpdate tests when changing APIs — no exceptionstiered-memoryThree-tier agent memory model (hot/cold/wiki) for 20-55% context reduction per spawnversioning-policySemver versioning rules for Squad SDK and CLI — prevents prerelease version incidentswindows-compatibilityCross-platform path handling and command patterns