菜单
已展示 40 / 56 个已收集 Skill。
This skill should be used when the user says "/ship", "commit and push", "create a PR", "ship it", "commit this", "push and PR", or wants to commit, push to remote, and/or create a GitHub pull request. Handles the full commit-push-PR workflow or any subset.
原文语言：英语
Use when performing git cleanup, staging, committing, branch rewriting, cherry-picking, resetting, cleaning, pushing, force-pushing, or configuring safeguards for destructive git operations.
原文语言：英语
Commit and ship a branch through Polygraph. Use when the user says "ship for poly", "ship for polygraph", or wants to commit, push branch with Polygraph, set git upstream, and create a PR for the Polygraph session.
原文语言：英语
Open Plannotator's annotation UI for a markdown file, HTML file, URL, or folder and then respond to the returned annotations.
原文语言：英语
Open Plannotator on the latest rendered assistant message and use the returned annotations to revise that message or continue.
原文语言：英语
GitHub org cleanup without gh CLI. Use when deleting Polygraph demo org repositories while keeping template repositories.
原文语言：英语
Use when sending handoff context from one OpenCode TUI running in tmux to another OpenCode tmux pane, including cross-session context transfer.
原文语言：英语
Use only when the main agent has completed discovery and a task has genuinely concurrent validation or isolated implementation work that benefits from subagents. Do not use for exploration, research, planning, or review.
原文语言：英语
Use when a task mentions ~/.config/ai, global or personal AI configuration, shared agent instructions, portable skills, harness-specific skills, or AI setup shared across OpenCode, Claude, and Codex. Don't use for normal application code or project-only AI…
原文语言：英语
Use when the user wants to list or search AI Observability conversations, inspect generations, manage evaluators (create, test, delete), set up evaluation rules, check scores, or browse evaluator templates. Trigger on phrases like "list conversations",…
原文语言：英语
Use when the user says 'bro,' asks to restate the last response, or calls wording confusing, jargon-heavy, robotic, incoherent, or too long. Rewrite it in plain, concise language without changing its meaning. Don't use for translating text, summarizing a…
原文语言：英语
Use when designing, reviewing, or refactoring code architecture, module interfaces, seams, adapters, dependency direction, testability, hidden coupling, or AI-navigable codebase structure.
原文语言：英语
Use when the user wants to create a new Grafana dashboard, add panels, variables, or annotations to an existing dashboard, design dashboard panels, variables, queries, or layout, or make a material visual redesign of an existing dashboard. This skill uses gcx…
原文语言：英语
Structured diagnostic workflow for debugging application issues using Grafana observability data. Use when the user reports errors, latency spikes, service degradation, HTTP 500s, or wants to investigate why a service is behaving unexpectedly. Triggers for:…
原文语言：英语
Diagnose Entity Graph problems: missing entities, missing edges, disconnected clusters, or filtering issues. Use when the user reports that Entity Graph doesn't look right, services are missing, edges aren't appearing, or environments can't be filtered.…
原文语言：英语
Discover what datasources, metrics, labels, and log streams are available in a Grafana instance. Use when the user asks what data exists, what metrics are available, what services are being monitored, or needs to find a datasource UID.
原文语言：英语
Use when investigating browser/client error logs from Grafana for polygraph or nx-api containers and proposing likely fixes. Requires Grafana MCP; fails hard when unavailable or disconnected. Don't use for backend-only incidents, local-only debugging, or log…
原文语言：英语
Run a narrated, read-only demo tour of gcx for customer or colleague presentations. Showcases the breadth of gcx across every Grafana Cloud product area — resources, datasources, metrics, logs, traces, SLOs, alerts, synthetic monitoring, IRM, k6, fleet, and…
原文语言：英语
(Experimental) End-to-end observability setup for Grafana Cloud. Covers instrumentation, SLOs, alerting, synthetic monitoring, k6 load testing, IRM on-call, dashboards, cost optimization, and GitOps export.
原文语言：英语
Use gcx CLI to manage Grafana Cloud resources. Trigger when the user wants to inspect, create, update, delete, query, or automate any Grafana resource — dashboards, datasources, alerts, SLOs, synthetic checks, oncall, incidents, fleet, k6, knowledge graph, or…
原文语言：英语
Use when the user explicitly wants typed Go stub files, generated resource skeletons, or grafana-foundation-sdk builder boilerplate for dashboards or alert rules. This is scaffolding only; for designing or creating a usable dashboard with datasource discovery…
原文语言：英语
Use when a complex plan or unfamiliar task needs docs/source-grounded pressure testing, domain-language clarification, material unknown discovery, or blindspot analysis before implementation.
原文语言：英语
Use when summarizing current work for another agent, session, pane, model, or future continuation, including goals, files, decisions, verification, risks, next steps, and suggested skills.
原文语言：英语
Use when the user wants to import existing Grafana dashboards as Go code, convert live dashboards to builder code, migrate dashboards to code, or reverse-engineer a dashboard from a Grafana instance. Triggers on "import dashboard", "convert to code",…
原文语言：英语
Use when surveying a whole React codebase to produce a prioritized audit and self-contained implementation plans without changing source code. Trigger for requests to improve React code, audit an app, find high-leverage robustness or performance work, or…
原文语言：英语
Investigate Grafana alerts to determine why they are firing, their scope, and impact. Use when the user asks about a specific alert, wants to understand alert behavior, or needs to diagnose why an alert is in a firing or pending state.
原文语言：英语
Use when the user asks to capture, map, document, preserve, or add a repo area, codebase flow, subsystem, architecture path, runbook, or work topic into the local AI knowledge base.
原文语言：英语
Use when enriching a raw manual note, pasted note, source clipping, or handwritten/voice note in the local AI knowledge base before wiki refresh.
原文语言：英语
Use when checking, auditing, linting, repairing, or health-checking the local AI knowledge base for metadata, links, privacy, staleness, tags, indexes, logs, or provenance issues.
原文语言：英语
Use when the user asks to check, query, search, pull from, or answer using the local AI knowledge base before responding.
原文语言：英语
Use when compiling new or changed knowledge-base captures, notes, or sources into a wiki under the local AI knowledge base.
原文语言：英语
Use for operational management of existing Grafana dashboards: list, get, search, create or update from an already-authored manifest, delete, inspect and restore versions, pull/push/validate/promote dashboard resource files, manage dashboard folders, or…
原文语言：英语
Use when reviewing a diff, branch, pull request, worktree, or code changes for spec compliance, standards, maintainability, regressions, or review findings without opening Plannotator.
原文语言：英语
Use when writing a blog post, editing a draft, reviewing Nartc blog voice, or making prose sound like Nartc, especially Angular, AI workflow, theory-crafting, or personal engineering experience essays. Don't use for generic marketing copy, formal product…
原文语言：英语
Use when the user is triaging what is actively paging in Grafana OnCall, or asks about active alert groups, acknowledging or silencing or resolving fires, on-call queue, or "what's paging right now". Trigger on phrases like "what's paging", "on-call alerts",…
原文语言：英语
Open Plannotator's annotation UI for a markdown file, HTML file, URL, or folder and then respond to the returned annotations.
原文语言：英语
Analyze a user's Plannotator plan archive to extract denial patterns, feedback taxonomy, evolution over time, and actionable prompt improvements — then produce a polished HTML dashboard report. Falls back to Claude Code ExitPlanMode denial reasons when…
原文语言：英语
Open Plannotator on the latest rendered assistant message and use the returned annotations to revise that message or continue.
原文语言：英语
Turn an idea or objective into a goal package for /goal. Interviews the user, builds a reviewed fact sheet via Plannotator, then explores the codebase to produce an execution plan.
原文语言：英语
Generate self-contained HTML visualizations with Plannotator theming. Use for implementation plans, PR explainers, architecture diagrams, data tables, slide decks, and any visual explanation of technical concepts. Plans and PR explainers follow Plannotator's…
原文语言：英语