Astro development requires consistent routing, configuration, and deployment choices. This skill provides page examples, component patterns, CLI references, and adapter workflows linked to official documentation.

Long Japanese responses consume tokens and hide key actions. Genshijin applies three compression levels while preserving technical accuracy and critical warnings.

Frontend guidance becomes outdated as browser APIs and support levels change. This skill finds focused implementation guides with compatibility and fallback advice.

Finding compatible agents across separate registries is difficult. This skill searches a unified registry and supports authenticated messaging, registration, and skill publishing.

Project coordination spreads updates across calendars, inboxes, files, and trackers. This skill organizes common Google Workspace workflows through the gws command-line tool.

Pipeline configuration can be difficult when sources, transforms, sinks, and deployment modes interact. This skill provides practical YAML guidance and architecture decisions for reliable Goldsky Turbo designs.

Goldsky Turbo pipeline failures can interrupt data delivery and require careful investigation. This skill guides status checks, log analysis, and repair recommendations with confirmation before changes.

Moving from The Graph can require a reliable source identifier, deployment path, and endpoint transition. This skill guides the migration and verifies sync before application cutover.

Historical blockchain reads can increase RPC provider costs. This skill guides Goldsky Boost setup and cache troubleshooting while keeping your existing upstream provider.

Container images can retain unnecessary build tools and rebuild dependencies too often. This skill guides Dockerfile design with separate build stages, efficient caching, and minimal runtime dependencies.

Complex conversations can create too many choices, unclear priorities, and difficult restarts. This skill structures replies around one active task and clear recovery cues.

Local business research requires searching listings and gathering details and reviews. This skill documents paid fetcher.sh requests for these tasks through HTTP and MCP.

Code changes can miss acceptance criteria, repository rules, or security boundaries. This skill performs a read-only review and returns structured, line-anchored findings.

Multi-agent issue delivery can lose state, mix roles, and skip safeguards. This skill coordinates implementation, review, QA, escalation, and pull request creation through agent-flow.

Issue implementation can drift beyond scope or produce incomplete handoffs. This skill applies focused changes, runs project checks, commits once, and reports structured evidence.

Stale context files mislead agents and increase maintenance risk. Gardener verifies documentation against code, repairs references, and keeps risk baselines controlled.

Coding agents lose accuracy when repository guidance is missing or outdated. This skill creates reviewed context files, confidence labels, and risk boundaries with human approval.

Ponytail benchmark gains can be confused with savings measured in your repository. This skill displays a compact scoreboard and keeps those claims separate.

Deferred work becomes difficult to track when its limits and upgrade triggers remain scattered across code comments. This skill collects marked comments into a ledger and flags missing triggers.

Unnecessary abstractions and redundant dependencies make repositories harder to maintain. This skill reviews the whole codebase and ranks deletion, simplification, and replacement opportunities.