发现 Skills

Run a multi-step skill workflow declared in a workflow YAML file. Use when the user asks to "run the workflow at <path>", "execute workflow <name>", "run the <name> workflow", "chain these skills", "compose <skill-a> and <skill-b>", or supplies a path to a `.yaml` workflow definition. Arguments follow a `key=value` grammar: the first positional value is the workflow file path, remaining `key=value` pairs are workflow inputs. The runner executes steps strictly in order, halts on the first non-zero exit, and writes a summary JSON to the workflow directory.

Generate professional SVG charts from pipeline artifacts (FINANCIALS, STRATEGY) and insert them into the final plan.

Manage Ollama instances across the home lab. List, pull, remove, and benchmark models. Check Ollama health, compare models, and coordinate inference across local and remote instances. Use when: "ollama status," "list models," "pull model," "remove model," "benchmark ollama," "check ollama," "model health," "inference speed."

AI tutor that teaches you new skills. Interactive lessons, practice exercises, progress tracking, and personalized learning paths for any subject. Use when: "teach me", "learn", "tutorial", "lesson", "practice", "skill learning", "education", "tutor", "course".

name: inspect-quality description: "Interactive QA session where user reports bugs or issues conversationally, and the agent logs them to specs/BUG-LOG.md with a structured audit schema. Explores the codebase and domain context to inform reports..."

Comprehensive backup, update, and restore workflow with dynamic workspace detection

Execute phases from a plan using group-based processing. Builds phases in parallel within groups, audits each group after completion, and auto-fixes Medium/Low issues while escalating High/Critical to the user.

Phase-level planning workflow for planner agents. Handles reading templates, exploring codebase references, creating plan.md and phase files, self-validation, and checkpoint reporting to the orchestrator. Preloaded into planner agents via skills: field — not user-invocable.

Web search, content extraction, site crawling, and multi-source research via the Tavily MCP server.

CI/CD pipeline expert for GitHub Actions, GitLab CI, Jenkins, and deployment automation

Linear project management expert for issues, cycles, projects, and workflow automation

Create git commits with emoji prefixes and Conventional Commit messages. Use when the user wants to commit changes, push code, or asks to use "just pm" command.

Analyze LLM experiment results. Use when the user says "analyze experiment", "experiment analysis", "evaluate experiment", "check experiment metrics", or provides an experiment ID for analysis. Requires experiment_id as an argument.

Automatically classify and extract information from construction documents using NLP. Categorize RFIs, submittals, change orders, specifications, and contracts.

Extract structured data from construction specifications. Parse CSI sections, requirements, submittals, and product data from spec documents.

Create, configure, and manage VM templates in Proxmox. Build reusable VM images for rapid deployment of standardized environments, including Kubernetes clusters and managed applications.

Manage device adoption and onboarding, maintain device inventory, and monitor device configurations across your UniFi network infrastructure.

Unified DataRobot agent workflow — design (agent_spec.md), optional dress-rehearsal simulation via built-in rehearsal engine, template-based coding, and deployment. Combines agent design guidance with interactive pre-code simulation (DataRobot LLM Gateway, feedback report). Use when the user wants to design, build, code, or deploy an AI agent for DataRobot, run a spec simulation before coding, mentions "agent spec", "datarobot-agent-assist", "dr-assist", "dress rehearsal", or is creating agents on DataRobot's platform.

Analyze weekly marketing campaign performance data across channels. Use when analyzing multi-channel digital marketing data to calculate funnel metrics (CTR, CVR) and compare to benchmarks, compute cost and revenue efficiency metrics (ROAS, CPA, Net Profit), or get budget reallocation recommendations based on performance rules.

Automates git workflow tasks including status checks, branch creation, file staging, conventional commit message generation, and pull request creation with the gh CLI. Use this skill when you need to commit changes, create PRs, check git status, create branches, push code, or generate commit messages. Ensures proper git workflow and commit standards.

Post, reply, like, and engage on Clawk — Twitter for AI agents.

Gemini CLI for one-shot Q&A, summaries, and generation.

飞书 OKR：管理目标与关键结果。查看和编辑 OKR 周期、目标（Objective）、关键结果（Key Result）、对齐关系、量化指标和进展记录。当用户需要查看或创建 OKR、管理目标和关键结果、查看对齐关系时使用。

Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.