upstream-evaluation
Evaluate upstream changes using Navigator's design frameworks to decide what to adopt, skip, or adapt
浏览 outfitter-dev 维护的已发布 AI 技能,比较用途与说明,并通过来源仓库了解安装方式。
已收录技能
62收录技能的仓库 Stars 合计
1,007仓库 Forks
0平均每个技能的仓库 Stars
16同一仓库中的多个技能可能共享 Stars,合计包含重复仓库数据。
Evaluate upstream changes using Navigator's design frameworks to decide what to adopt, skip, or adapt
Safely sync navigator's agent-browser fork with upstream vercel-labs/agent-browser, analyze changes, and generate integration documentation
CLI testing guidance and patterns. Loaded by /ops/test/cli command or subagents for comprehensive testing.
CLI testing guidance and patterns. Loaded by /ops/test/cli command or subagents for comprehensive Navigator CLI testing.
MCP testing guidance and patterns. Loaded by /ops/test/mcp command or subagents for comprehensive Navigator MCP server testing.
Triages PR activity to identify what needs attention. Use when reviewing PR status, prioritizing work, checking for stale reviews, or when the user asks about PR health, what needs review, or what's blocking pr...
Helps respond to PR review comments and resolve threads. Use when addressing review feedback, replying to comments, resolving discussions, or when the user wants to handle PR feedback systematically.
Query GitHub PR activity using the Firewatch CLI (fw). Fetch, cache, filter, and act on PR comments, reviews, commits, and CI status. Outputs JSONL for jq composition. Use when checking PR status, finding revie...
Parallel CLI stress testing using orchestrated subagents. Spawns specialized agents to test different CLI domains simultaneously, aggregating results into structured reports. Supports discovery mode (agents ana...
Configure Claude Code GitHub Actions workflows effectively. Covers automatic mode detection, event routing, subagent coordination, hooks for quality gates, MCP server integration, reusable workflows, performanc...
Run and evaluate the Skillset smoke test (aliases, sets, and skill invocation) and interpret its JSON reports. Use this when validating $skill/$set behavior or checking Claude Code/Codex headless runs.
Project documentation structure and templates — READMEs, API docs, guides, and CLI references. Use when creating documentation, structuring a docs/ directory, writing READMEs, or when "documentation", "README",...
Rigorous quality gate for documentation before merge or publish. Verifies code examples run, links resolve, APIs match implementation, and all sections are complete. Use when auditing docs, reviewing documentat...
Bun-first development patterns for TypeScript projects. Use when auditing Node.js projects for migration opportunities, starting new projects, evaluating npm dependencies, or reducing package.json bloat. Trigge...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。