发现 Skills

Use when you have PR review comments to address and want to evaluate each comment's validity before deciding to fix, reply, or skip

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

Add and manage evaluation results in Hugging Face model repositories using the new .eval_results/ format. Supports extracting scores from model cards.

Analyzes the structure of a 1C metadata object from an XML export — requisites (attributes), tabular parts, forms, movements, and data types. Use it to study object structure (instead of reading XML files directly) and as a preparatory step when writing queries and code that work with objects.

Stops the Apache HTTP Server. Use when the user asks to stop the web server (Apache) to cease web publishing.

freee API操作支援スキル。GCP Secret Managerで認証情報を管理し、freee APIへアクセス。取引（仕訳）の参照・登録、マスタ管理（取引先・品目・口座）、証憑（レシート）アップロードなどを実行。書き込み操作はユーザー確認必須。

Build, scaffold, and deploy Power Automate cloud flows using the FlowStudio MCP server. Your agent constructs flow definitions, wires connections, deploys, and tests — all via MCP without opening the portal. Load this skill when asked to: create a flow, build a new flow, deploy a flow definition, scaffold a Power Automate workflow, construct a flow JSON, update an existing flow's actions, patch a flow definition, add actions to a flow, wire up connections, or generate a workflow definition from scratch. Requires a FlowStudio MCP subscription — see https://mcp.flowstudio.app

Optimize Databricks cluster and query performance. Use when jobs are running slowly, optimizing Spark configurations, or improving Delta Lake query performance. Trigger with phrases like "databricks performance", "spark tuning", "databricks slow", "optimize databricks", "cluster performance".

Configure FireCrawl across development, staging, and production environments. Use when setting up multi-environment deployments, configuring per-environment secrets, or implementing environment-specific FireCrawl configurations. Trigger with phrases like "firecrawl environments", "firecrawl staging", "firecrawl dev prod", "firecrawl environment setup", "firecrawl config by env".

Execute extended video duration using Kling AI continuation features. Use when creating longer videos from shorter clips or building seamless sequences. Trigger with phrases like 'klingai extend video', 'kling ai video continuation', 'klingai longer video', 'extend klingai clip'.

Implement enterprise role-based access control with Linear. Use when setting up team permissions, implementing SSO, or managing access control for Linear integrations. Trigger with phrases like "linear RBAC", "linear permissions", "linear enterprise access", "linear SSO", "linear role management".

Execute set up OpenRouter API authentication and configure API keys. Use when starting a new OpenRouter integration or troubleshooting auth issues. Trigger with phrases like 'openrouter setup', 'openrouter api key', 'openrouter authentication', 'configure openrouter'.

Execute migrate and upgrade OpenRouter SDK versions safely. Use when updating dependencies or migrating configurations. Trigger with phrases like 'openrouter upgrade', 'openrouter migration', 'update openrouter', 'openrouter breaking changes'.

Create optuna study creator operations. Auto-activating skill for ML Training. Triggers on: optuna study creator, optuna study creator Part of the ML Training skill category. Use when working with optuna study creator functionality. Trigger with phrases like "optuna study creator", "optuna creator", "optuna".

Generate security headers generator operations. Auto-activating skill for Security Fundamentals. Triggers on: security headers generator, security headers generator Part of the Security Fundamentals skill category. Use when working with security headers generator functionality. Trigger with phrases like "security headers generator", "security generator", "security".

Execute this skill should be used when the user asks about "how sprints work", "sprint phases", "iteration workflow", "convergent development", "sprint lifecycle", "when to use sprints", or wants to understand the sprint execution model and its convergent diffusion approach. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

Apply Windsurf security best practices for secrets and access control. Use when securing API keys, implementing least-privilege access, or auditing Windsurf security configuration. Trigger with phrases like "windsurf security", "windsurf secrets", "secure windsurf", "windsurf API key security".

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Frontend-backend API contracts, routes, clients, and type definitions. Handles API endpoint definitions, request/response types, route configuration, and cross-stack integration. Use when working with API endpoints, request/response types, route definitions, or frontend-backend integration, or when user mentions API design, adding endpoints, type mismatches, API contracts, REST endpoints, client integration, "404 Not Found" errors, "Type error" in API calls, or route configuration issues.

Audit a repository against spec/project/project-structure/<canonical_language>.md and scaffold or patch any missing artefacts—README, top-level orientation file, .gitignore, .pre-commit-config.yaml, Renovate config, Taskfile, MkDocs setup, .claude/ directory, and the full .github/ layout (workflows, settings.yml, release-drafter.yml, boring-cyborg.yml, stale.yml) with the portfolio-wide Probot extends pointers. Also verifies that the GitHub Apps backing those configs (the Probot apps `settings`, `boring-cyborg`, `stale` plus the Renovate app for `renovate.json5`) are actually installed on the repository via the GitHub API; for Renovate, additionally points at the Mend Renovate dashboard when the App is installed but no Renovate activity is visible. Invoke when the user asks to audit the project structure, apply the project-structure spec, scaffold missing GitHub configs, add .github/settings.yml, generate release-drafter config, bring this repo in line with project-structure, check that Probot or Renovate apps are installed, diagnose why Renovate isn't producing PRs, or add missing project configs. Also handles equivalent German-language requests.

Evaluates a single rule .md across 3 dimensions (Clarity, Completeness, Goal Alignment). Use when asked to 'review rule' or dispatched by /review-claude-config. Do NOT use for skills or agents — use /review-skill or /review-agent.

Guide for ASP.NET Core configuration with appsettings.json, environment-specific settings, and the options pattern

Guide for Azure DevOps automation using az CLI with azure-devops extension. Covers Azure Pipelines, Azure Repos, Azure Boards, work items, pull requests, artifacts, service connections, variable groups, and DevOps automation. Use when working with ADO, az devops commands, YAML pipelines, or Azure DevOps REST API.

Linter-driven refactoring patterns to reduce complexity and improve code quality. Use when linter fails with complexity issues (cyclomatic, cognitive, maintainability) or when code feels hard to read/maintain. Applies storifying, type extraction, and function extraction patterns.