技能雷达 · GITHUB
值得安装的 Agent Skills。
汇总公开仓库中已验证的 Skills。安装前先看清它能做什么、包内包含什么、热度如何，以及来源是否可靠。
- 目录范围
- 已验证
- Skills
- 10,772
- 仓库
- 1711
- 最近同步
- 2026年9月23日
fagnerlopescloud-weaver-computer-setup
This skill should be used when the user asks to "set up my computer", "install dev tools", "set up my environment", or when the pre-flight check reports NEEDSCOMPUTERSETUP. It detects the OS, tries install methods in order of reliability, and falls back gracefully. Works on Linux, macOS, Windows (native or WSL), and locked-down corporate machines.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月12日
fagnerlopescloud-weaver-monitor
Use this skill after a CloudWeaver v2 recipe has been deployed (via cloud-weaver-repo-setup + GitHub Actions pipeline) to confirm the application is actually up and to help diagnose it when it is not. It polls the app's health endpoint until HTTP 200 with retries and backoff, and on failure collects SSH diagnostics from the VM.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月12日
fagnerlopescloud-weaver-offboard
Use this skill when the participant is returning a borrowed machine at the end of the workshop (or wants to take over from a new machine). It invalidates the three secrets that were left on the event machine without requiring physical access to it: Locaweb API credentials (manual rotation in the panel), SSH private key (rotated via the CloudStack API — stop → reset → start), and local cleanup of the cloud-weaver files.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月12日
fagnerlopescloud-weaver-playbook
The CloudWeaver operating instructions — persona, session-startup procedure, the /start-cloud installation flow, the skill reference, and the standing rules. Invoke this skill at the very start of every session and follow it for the entire session.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月12日
its-a-skill-issuegpt-image
Generate and edit images with OpenAI GPT-Image-2 via inference.sh CLI. Models: GPT-Image-2. Capabilities: text-to-image, image editing, inpainting, mask-based editing, multi-image reference, batch generation. Use for: product mockups, marketing visuals, image editing, concept art, inpainting, photo manipulation. Triggers: gpt image, gpt-image-2, openai image, chatgpt image, dall-e, dalle, openai image generation, gpt image edit, gpt inpainting, openai dall-e, gpt 4o image
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月6日
kmalakoffsense-bases
Translate an Obsidian Bases .base file into sense SQL that returns the same rows. Use when asked to convert, import, or reproduce a .base file (or a Bases view, filter, or formula) with sense, or when a markdown tree contains .base files whose views someone wants queryable outside Obsidian.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月13日
kmalakoffsense-setup
Set up the sense CLI on a markdown tree and make the decisions that shape its index: run sense init, choose sqlite, duckdb, or turso, define presets and search signals, configure embeddings, and design queryable note conventions. Use when creating or restructuring a markdown knowledge base, editing sense.config.json, choosing a store or embedding model, or deciding how agents should write notes for later retrieval.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月13日
mcp-zmcp-z-cli
Use @mcp-z/cli to discover and call MCP tools, prompts, and resources from a terminal using a project's .mcp.json. Load for mcp-z or z commands, CLI-based MCP access, or on-demand capability discovery. Application code using @mcp-z/client belongs to the client skill.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月13日
mcp-zmcp-z-client
Use @mcp-z/client from Node.js code. Load when writing or reviewing a script or application that connects to MCP servers through @mcp-z/client. MCP server implementation belongs to the server SDK instead.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月13日
quantipixelsalaga
Build and verify an accepted coding change or fix. Use directly when the outcome is sufficiently clear, or within an atona initiative; exclude initiative coordination, standalone planning, review, and publication.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月13日
quantipixelsalarina
Guide requested work through completion using relevant installed skills and conditional routes. Use as the operating entrypoint for skill-driven work, to choose the next owner, resume work, resolve adjacent ownership, or request the installed skill inventory.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月13日
quantipixelsamose
Establish, sharpen, or reconcile one project's canonical domain model and its durable records. Use when project-specific terms, conceptual identities, domain/context boundaries, relationships, ownership, invariants, .learnings, .nongoals, or ADRs need to be defined, changed, or maintained.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月13日
quantipixelsarchitect
Design, survey, or review the technical structure of a software system or consequential module at the smallest scale needed to resolve the architecture question. Use for architectural friction, system boundaries, module/interface/seam shape, data/state ownership, integrations, deployment, quality scenarios, trade-offs, migration/recovery, or architecture sufficiency; exclude initiative lifecycle planning, user-decision closure, implementation, workspace infrastructure, and code-review verdicts.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月13日
quantipixelsarojinle
Resolve consequential choices through a relentless, complete decision-tree interview and final user confirmation. Use when the user wants to work through dependent choices together or be grilled until decisions are settled. Explicit invocation selects the interview. Use ro-wo for a bounded critique or stress-test; exclude specialist design/architecture, initiative lifecycle planning, delivery execution, and ordinary fact-finding.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月13日
quantipixelsatona
Carry an idea from exploration through a completed, verified build, maintaining the plan and coordinating the skills needed along the way. Use for an initiative spanning discovery, decisions, planning, and delivery, or to resume or replan one. Honor exploration-only and planning-only requests; use alaga directly for an already-settled coding change that needs no initiative coordination.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月13日
quantipixelsatunwo
Review code changes or existing systems at light or deep depth. Assess correctness, behavior preservation, maintainability, simplification, and proof within the requested scope. Exclude implementation and delivery management.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月13日
quantipixelshtml-artifact
Turn supplied material into a selective, traceable, accessible static or interactive browser information projection. Preserve source meaning, authority, evidence state, and retrieval paths; exclude originating analysis, slide decks, decision prototypes, production/application UI, deployments, and reusable libraries.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月13日
quantipixelsirinse
Select and use companion engineering tools; install, update, reconcile, configure, verify, or remove tools, installed skills, host instructions, and native agent declarations. Use for non-obvious tool capability or environment readiness; exclude skill authoring, engineering verdicts, and implementation.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月13日
quantipixelsiwadi
Investigate one substantial, reusable, audit-worthy, or unusually hard-to-resolve question against the strongest practical claim-appropriate evidence. Persist a sourced research record when the conclusion deserves independent life; for peculiar version-specific technical questions, escalate to exact upstream source/tests only when ordinary research cannot resolve a materially decision-changing claim. Exclude routine facts that can be consumed immediately.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月13日
quantipixelsoptimize
Compare trial variants of a working system or agent workflow and decide whether a measured improvement merits keeping one. Use when comparative experiments are needed for the requested result; exclude diagnosis alone, read-only simplification, experiential prototypes, routine validation, and an already-selected correction.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月13日
quantipixelsoro-fun-eniyan
Write, review, edit, or prune human-facing technical communication and prose. Use for docs, explanations, reports, PR descriptions, handoffs, specifications, procedures, messages, and other text whose primary reader is a person. Own technical reader calibration, concept adequacy, structure, terminology, ambiguity, clarity, and meaning-preserving cleanup. Exclude agent-facing instructions and prompts, factual review, translation, and code style.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月13日
quantipixelsoro-fun-sigidi
Write, review, or evolve text that agents consume to guide behaviour. Use for skills, AGENTS.md/CLAUDE.md, prompts, subagent definitions, workflow contracts, tool descriptions, routing text, or other instructions/docs agents act from. Exclude human-facing prose whose primary job is comprehension rather than agent behaviour.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月13日
quantipixelsoro-ologbon
Compatibility entrypoint for legacy requests explicitly naming oro-ologbon. Delegates by audience to oro-fun-sigidi or oro-fun-eniyan.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月13日
quantipixelspese
Serve one explicitly invoked local file, directory, or local web resource through private Tailscale Serve or an explicitly accepted encrypted Tailcat fallback, and return the exact access target. Use only when directly invoked to make that local resource temporarily reachable through a private transport. Exclude public/anonymous tunnels, permanent hosting, production serving, and artifact creation.
- 安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月13日