746 skills · sorted by relevance
Azure OpenAI SDK for .NET. Client library for Azure OpenAI and OpenAI services. Use for chat completions, embeddings, image generation, audio transcription, and assistants. Triggers: "Azure OpenAI", "AzureOpenAIClient", "ChatClient", "chat completions .NET", "GPT-4", "embeddings", "DALL-E", "Whis...
The English summary is being prepared. Showing the original description.
ISTQB/JSTQB のテスト完了（test completion）活動のうち、テスト実行結果の評価と完了基準（exit criteria）判定を支援するスキル。テスト実行ログ（test-execution-log.md）と test-plan の完了基準を突き合わせ、完了とみなせるかを判定した test-summary-report.md を作る。テスト完了時の最終レポートにも、テスト途中の中間評価にも使える。「テスト結果をまとめて」「完了基準を満たしたか判定して」「テストレポートを書いて」「今どこまでテストが進んだか評価して」と依頼されたときに使う。単発のテスト作成依頼（単にユニットテストを書きたいだけ）は対象外。/test-report <テスト対象名> で明示的に呼び出されたときのみ使用する。
The English summary is being prepared. Showing the original description.
Run verification commands and confirm output before claiming success
The English summary is being prepared. Showing the original description.
Verify completion and success claims with fresh evidence. Use before claiming a task is complete, a fix works, tests pass, or a feature is ready for GO.
The English summary is being prepared. Showing the original description.
Build with OpenAI's stateless APIs - Chat Completions (GPT-5, GPT-4o), Embeddings, Images (DALL-E 3), Audio (Whisper + TTS), and Moderation. Includes Node.js SDK and fetch-based approaches for Cloudflare Workers. Use when: implementing chat completions with GPT-5/GPT-4o, streaming responses with SSE, using function calling/tools, creating structured outputs with JSON schemas, generating embeddings for RAG (text-embedding-3-small/large), generating images with DALL-E 3, editing images with GPT-Image-1, transcribing audio with Whisper, synthesizing speech with TTS (11 voices), moderating content (11 safety categories), or troubleshooting rate limits (429), invalid API keys (401), function calling failures, streaming parse errors, embeddings dimension mismatches, or token limit exceeded.
The English summary is being prepared. Showing the original description.
Coordinate updates to an operator-configured Team server through its designated Night Watch owner. Use the existing deployment controller’s validation, recovery, and acceptance records to follow the requested update through completion.
Manage preparation, publication, recovery, and verification of OpenClaw beta, stable, and extended-stable releases. Track approved fixes carried into older release branches, required validation evidence, publication scope, and follow-up work through completion.
Manage GitHub issues and pull requests, proposed code changes, using the gh command-line tool. Create and inspect discussions, check automated test results, investigate failed logs, rerun jobs, and track authorized merges through to their verified status.
Delegate feature development, large code refactors, and pull request reviews to Codex, Claude Code, or OpenCode as background workers. Use isolated project checkouts, monitor progress, and arrange completion or failure notifications.
Guides feature development and bug fixes by writing tests before implementation. It confirms each test fails for the expected reason, adds only enough code to pass, and checks the full test suite before completion.
Create rules that detect command patterns, file edits, prompts, or completion events and issue warnings or block matching actions. Configure checks for dangerous commands, sensitive files, and debug code using text patterns or multiple conditions.
Turn unclear feature requests or high-impact changes into acceptance criteria: observable conditions for judging completion. Define scope, assumptions, risks, and verification methods, or review an existing specification so another agent or team can implement it with clearer requirements.
Turn a large engineering objective into a written plan with steps sized for individual pull requests, or proposed code changes. Each step includes context, dependencies, checks, and completion criteria so another agent can continue the work.
Compare coding agents on tasks from your own codebase. Define success checks, run agents in separate Git working directories, and report pass rates, available API costs, completion time, and consistency across repeated trials.
Organize engineering work carried out by AI agents with clear completion criteria, small verifiable tasks, and evaluations before and after implementation. Match model choice to task complexity and track tokens, retries, time, and outcomes to manage cost.
Create Hookify rules that warn Claude or block operations when commands or file edits match specified conditions. The skill explains rule files, text matching patterns, multiple conditions, and how to test and refine the rules.
Build Claude Code hooks, automated checks triggered by events such as tool use or session start. The guidance covers prompt-based decisions, command scripts, configuration, testing, and debugging for validation and workflow automation.
Verify that existing work meets its acceptance conditions using the smallest sufficient set of checks. Reuse results that still match the repository state, report outcomes precisely, and stop once the evidence is complete without adding unrelated work.
Turn clear requirements into small implementation tasks with acceptance criteria, verification steps, dependencies, and estimated scope. Produce a written plan and ordered task list, with checkpoints and opportunities for parallel work identified before coding begins.
Turn an unclear feature idea into a structured specification with goals, boundaries, and testable success criteria. Split broader requests into independent modules when needed, then move through planning, task breakdown, and implementation with human review.
Guide a first task in Paperclip by clarifying goals, constraints, and completion criteria. Prepare a plan or one task proposal, then wait for approval before creating execution tasks or carrying out the agreed work.
Apply a code rewrite plan one step at a time through small, reviewable edits. Keep changes within assigned files, check risk restrictions, and record each step’s files, change summary, rationale, and completion status.
Create a one-page HTML onboarding plan for a new employee. Bring together first-day and first-week schedules, manager and buddy details, 30/60/90-day milestones, useful resources, and a checklist of outcomes that show readiness.
Organize software development from requirements and architecture through testing, review, and deployment. Use specialized agent roles, shared memory, and test-driven development, where tests are written before code, to coordinate work across the project.