diagnose-gateway
Diagnose Gateway, config, secrets, channels, and port failures with read-only one-liners.
diagram-maker
Create SVG/HTML or Excalidraw diagrams for concepts, architecture, flows, and whiteboards.
block-kit
Use proactively for structured or interactive Slack replies, and when asked to author or validate native Slack Block Kit JSON.
node-inspect-debugger
Debug Node.js with node inspect, --inspect, breakpoints, CDP, heap, and CPU profiles.
visualize
Create inline visuals for code and explanations, or author persistent OpenClaw dashboard widgets with show_widget.
taskflow-inbox-triage
Preview synthetic inbox routing with a real TaskFlow approval pause, and identify the adapters needed for live triage.
taskflow
Run resumable approval workflows and coordinated subagent recipes with TaskFlow, Swarm, and optional Workboard claims.
canvas
Present hosted widget documents on a connected macOS panel and control panel visibility or navigation.
agent-transcript
Requested GitHub PR/issue agent transcripts: redact, trim, preview, and insert safely.
discord-clawd
Use to talk to the Discord-backed OpenClaw agent/session; not for archive search.
autoreview
Structured code review when explicitly requested, preferring OpenAI/Codex before Claude.
channel-message-flows
Use when running QA Lab channel message flow evidence.
facetime
Inspect FaceTime internal stages, place an approved call to a configured owner handle, and request hangup through facetime_call.
notcrawl
Notion archive: search, sync freshness, pages/databases, Markdown exports, SQL counts, and Notcrawl repo work.
crabbox
Crabbox and Blacksmith Testbox remote testing: isolation, cross-platform E2E, diagnostics, cleanup.
graincrawl
Granola archive: search, sync freshness, notes, transcripts, panels, SQL counts, and Graincrawl repo work.
obsidian-vault-maintainer
Maintain an Obsidian-friendly memory wiki vault with wikilinks, frontmatter, and official Obsidian CLI awareness.
openclaw-ci-limits
Manage OpenClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push single-flight, shard sizing, hosted-runner offload, queue health, and safe ramp-down/ramp-up changes. Use when tuning `.github/workflows/*`, `docs/ci.md`, CI runner labels, matrix `max-parallel`, ClawSweeper/Blacksmith burst protection, CodeQL runner placement, or investigating slow/queued OpenClaw CI.
control-ui-e2e
Use when designing, testing, fixing, or extending the OpenClaw Control UI GUI, including UI stress-test galleries with feedback inputs, Vitest + Playwright end-to-end checks, mocked Gateway flows, screenshots/videos, or agent-verifiable browser proof.
openclaw-debugging
Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code, including fetching stored sessions, transcripts, and attachments as evidence.
openclaw-changelog-update
Regenerate OpenClaw release changelog sections from git history before beta, stable, or extended-stable releases.
meme-maker
Search meme templates, suggest formats, and generate local or hosted image memes.
openclaw-testing
Choose proportional OpenClaw tests and checks, diagnose failures, and route environment-sensitive or release proof to its owner.
auto-qa
Run OpenClaw-wide autonomous QA and live/stress campaigns across independent subsystem lanes, with verified fixes and a resumable evidence report.
openclaw-update
Route routine updates of an existing local or remote OpenClaw Gateway to its installation owner, with automatic session recovery. Defer to deployment-specific skills when available.
control-ui
Operate and troubleshoot the OpenClaw Control UI: navigate connected clients, organize sessions, build session dashboards, and handle direct or Tailscale-hosted Gateways.
discord-user-post
Post an approved message as the logged-in Discord user through the Discord desktop app. Use for release announcements or other direct user-authored Discord posts; not for OpenClaw channel sends, bots, webhooks, relays, agent sessions, or archive search.
openclaw-test-performance
Benchmark, diagnose, and optimize OpenClaw test and plugin-suite runtime, import hotspots, CPU/RSS, heap growth, and slow coverage paths.
openclaw-refactor-docs
Refactor an existing OpenClaw docs page with source-audited preservation, restructuring, and verification.
deepseek-harness-wiki
DeepSeek Harness 开发文档离线 Wiki，检索导航涵盖的插件开发、工具、配置、生命周期、服务、事件、LLM 适配器和 Cordis 教程。用户询问这些开发主题时使用；不用于日常产品使用、部署运维或完整 API 参考。
five-perspective-analysis
从用户、业务负责人、一线执行者、技术负责人、公司经营者五种角色视角交叉分析问题，识别各方目标、约束、风险和冲突，并综合成有优先级的判断与行动建议。适用于产品决策、技术方案、项目复盘、业务难题、职业判断，以及用户要求“换几个视角看看”“考虑得更全面”“用五种视角分析”时。不用于单纯事实查询、只需单一专业结论或必须由真实利益相关者参与的正式调研。
hermes-ops
运维 Hermes Agent 的实战 skill。适用于用户提到“运维 hermes”“排查 hermes 问题”“gateway 异常”“平台掉线”“cron 不执行”“profile 配置混乱”“skills 或 tools 不生效”“想让其他 agent 帮忙维护 hermes”时使用。基于 hermes-agent 源码和官方命令入口，优先做检查、定位、修复、验证四步，不凭感觉瞎改。
hermes-qq
当用户想在 Hermes Agent 正式版 main 分支上补充 QQ platform 支持，或明确提到“给 hermes main 增加 QQ 渠道”“把 QQ support 作为 skill 安装到 Hermes”“让正式版 Hermes 支持 QQ 和文件发送”时使用。这个技能会把当前仓库补成支持 QQ Bot、QQ 文件发送、QQ 平台配置和工具集接线的版本。
llama-index-wiki
LlamaIndex 官方用户文档离线知识库，用于检索并回答 LlamaIndex Python 框架的安装、RAG、数据加载、索引、检索与查询、Agent、Workflow、模型、Embedding、向量库、评估、可观测性、部署、LlamaCloud 和 LlamaParse 等问题，也可生成有文档依据的示例代码与排障建议。当用户提到 LlamaIndex、llama-index、LlamaParse、VectorStoreIndex、QueryEngine、Retriever、AgentWorkflow 或相关集成用法时使用；纯源码贡献、内部实现审查或与 LlamaIndex 无关的通用 AI 问题不使用。
local-audio-transcriber
本地录音转文字工具。当用户发送已有录音、音频或视频文件，并希望把语音转成 Markdown 文稿和 SRT 字幕时使用。Apple Silicon 优先用 MLX/Apple GPU 和 whisper-large-v3-turbo-q4，本地转写，不生成 txt/json/vtt，不用于现场临时录音，也不默认调用云端语音识别服务。
openclaw-ops
OpenClaw 运维助手。用于用户提到 OpenClaw、小龙虾、gateway、渠道连接、消息发送失败、服务不可达、日志排查、渠道或 Agent 管理时使用。优先执行状态检查与故障分流；涉及重启、修复、更新、配置变更等高影响操作时，先向用户说明再执行。
openclaw-session-cleaner
OpenClaw session 清理助手。用于用户提到清理 OpenClaw sessions、删除旧 cron session、压缩或重建 sessions.json、排查 session 文件膨胀时使用。触发后优先检查 ~/.openclaw/agents/main/sessions/ 下的 session 文件数量和 sessions.json 大小，并按指令执行清理。
opendataloader-pdf
PDF 数据提取工具。当用户提到"PDF 提取"、"PDF 转 Markdown"、"PDF 解析"、"提取 PDF 内容"、"PDF 转 JSON"、"RAG PDF"时使用。OpenDataLoader PDF 是目前基准测试第一的 PDF 解析器，支持本地模式（快速、确定）和混合 AI 模式（复杂表格、扫描件、公式），输出 Markdown、JSON（带边界框）、HTML。适用于需要从 PDF 提取结构化数据用于 RAG/LLM pipeline，或需要批量处理 PDF 文档的场景。
p7-advisor
First-tier tech company P7 capability advisor for evaluating, coaching, and giving career advice against a P7 technical/product/expert profile. Use when the user asks for P7-level assessment, promotion readiness, capability gaps, resume/project review, interview preparation, or concrete growth advice based on first-tier tech company P7 expectations.
p8-advisor
First-tier tech company P8 capability advisor for evaluating, coaching, and giving career advice against a P8 senior expert, architect, or domain-owner profile. Use when the user asks for P8-level assessment, promotion readiness, capability gaps, project or resume review, interview preparation, or growth advice based on first-tier tech company P8 expectations.
p9-advisor
First-tier tech company P9 capability advisor for evaluating, coaching, and giving career advice against a P9 senior expert, director, or business/organization-level leader profile. Use when the user asks for P9-level assessment, promotion readiness, executive capability gaps, strategic project review, resume positioning, interview preparation, or growth advice based on first-tier tech company P9 expectations.
paper-interpreter
论文解读助手。适用于用户发送 arXiv 论文链接，并希望下载论文、解读论文、生成读书笔记、做论文拆解或输出详细报告时使用。会在工作目录创建论文文件夹、下载 PDF 与 TeX Source（如有）、生成中文 Markdown 报告。默认先交付初稿，不自动复查；如果用户明确同意，再安排后续复查。不适用于只要简短推荐语的情况。
photo-privacy-avatar
发布照片前的人脸隐私遮挡。用于用户提供一张或多张照片并指定保留人物后，用内置表情头像遮住其他人的正脸及仍可辨认人物的侧脸，处理后统一复查并补齐遗漏；支持合照打码、活动照片打码和批量头像遮挡。不用于识别人名、换脸、美颜、证件水印或直接发布照片。
photoplus-downloader
PhotoPlus相册批量下载原图工具。当用户需要从 photoplus.cn/live/ 相册批量下载原图时使用此技能。适用于 photoplus.cn 相册链接，支持多线程并发、自动跳过已下载文件。
prompt-optimizer
Prompt 优化助手。适用于用户想优化提示词、改进 AI 指令、为特定任务设计更好的 prompt，或需要选择合适提示框架时使用。会根据任务场景匹配合适框架，必要时先追问关键信息，再输出更清晰、更可执行的提示词版本。
qianwenai-wiki
千问AI平台（Qianwen AI Platform / DashScope）官方文档离线知识库，用于检索并回答模型选择、API Key、OpenAI 兼容接口、DashScope SDK、文本与多模态生成、图像/视频/语音、Realtime API、Embedding、Reranking、Function Calling、MCP、批量调用、计费、Token Plan、API/SDK/CLI 参考和模型更新等问题，也可基于官方文档生成示例代码与排障建议。当用户提到千问AI平台、Qianwen AI Platform、DashScope、通义千问 API、百炼 API、DASHSCOPE_API_KEY 或具体千问/万相模型接入时使用；千问聊天产品的一般使用、模型原理论文解读或无关的阿里云产品问题不使用。
qoder-wiki
Qoder 官方文档知识库，包含产品介绍、用户指南、功能配置、扩展能力、账户定价和故障排查。当用户询问 Qoder 相关问题（如安装、使用、功能、定价、快捷键、MCP、Skills、Quest Mode、Repo Wiki 等）时使用此 skill。
qwenwork-wiki
千问办公（QwenWork）官方文档 Wiki，用于查询网页端和桌面端使用、安装、工作台、技能与连接器、定时任务、IM 频道、企业管理及排障；也用于定位企业管理 API 文档。不用于千问AI平台、百炼或 DashScope 模型 API 接入，也不因普通办公任务而触发。
remove-ai-flavor
去除 AI 味道的文章风格优化技能。用于识别并改写文章、公众号稿、自媒体稿、口播稿、演讲稿、课程稿、产品文案中的 AI 痕迹、模板腔、资料味、翻译腔、内容空心、空洞大词、过度金句、破折号滥用、bullet 堆叠、动不动加粗等问题；当用户说“去 AI 味”“去除 AI 痕迹”“不像 AI 写的”“更像人写的”“更自然”“别太机器味”“去掉模板感”“改得像公众号终稿”时使用。不用于事实核查、从零选题策划、论文转公众号、纯标题生成或追求 AI 检测器通过率。
skill-optimizer
审查和优化已有 Skill。用于检查技能质量、触发边界、冗余指令或重构技能说明；不用于执行该技能的业务任务。
Page 676 of 1647 · 82344 results