Decide whether a normalized input packet can go straight to feature package authoring or needs product charter and system blueprint first. Use when scope is still ambiguous and the next document type must be chosen explicitly.

Command: `/optimize-prompt`

Testing patterns and principles. Unit, integration, mocking strategies. Use when writing unit tests, widget tests, or reviewing existing tests for correctness, structure, and naming conventions.

Role:

Operate Microsoft Visio through the DrawForge bridge with stable atomic actions. Use when an agent needs to create sessions, add/edit/connect/style shapes, save documents, export PNG previews, or execute a prepared drawing spec without taking over planning decisions.

Convierte un documento (PDF/texto) en una mini-app web interactiva lista para abrir en preview. Úsalo cuando quieras pasar de “contenido” a “producto usable”.

Use this skill when creating, managing, or working with Conductor

Implements a Markdown plan from a file path. Use when you have a feature plan or a production review fix plan and want the agent to execute it carefully, validate the changes, and stay within the documented scope.

Writes and reviews Conventional Commits commit messages (v1.0.0) to support semantic versioning and automated changelogs. Use when drafting git commit messages, PR titles, release notes, or when enforcing a conventional commit format (type(scope): subject, BREAKING CHANGE, footers, revert).

当用户主动汇报自己完成的具体动作、求反馈或默认求认可时使用。明说型：'我把 leetcode hot100 刷完了'/'我做完了 XX 项目'/'我读完了《XX》'/'我考了 CET-6/雅思/某证书'/'我这周投了 50 家'/'我简历改了 5 版'/'我今天面了 X 家'/'X 我终于弄完了'/'我跑通了 XXX'/'我做了 X 感觉怎么样'/'这样算不算'。隐蔽型（压低期待的汇报，用户自己在克制但实际在求认可）：'我好像把 X 搞懂了'/'我试了一下 X'/'我昨天随手做了个 X'/'我不知道这算不算什么，但我…'/'可能不算多，但我…'。边界：用户**已经做完具体动作**在汇报（区别于 coach-concern-direct 的'我够不够'担忧、coach-resume-review 的'帮我看简历'请求、coach-request-deliver 的'帮我梳理'请求）。应用本 skill：第 1 句具体认可他做了什么（不是'真棒'），第 2-3 句把动作从'作业视角'翻译到'求职/能力积累视角'给出可立刻自测的具体锚点，第 4 句根据定位结果动态生成 A/B 选择（深挖/横向/修漏洞/暂停诊断 四选二，不是固定二分）。禁止空洞鼓励、禁止直接打击、禁止无脑加码。

Scan overdue invoices, classify by aging bucket, create action cards, and draft dunning emails for the user to review and send

Automated code review for pull requests using specialized review patterns. Analyzes code for quality, security, performance, and best practices. Use when reviewing code changes, PRs, or doing code audits.

When the user wants to edit, review, or improve existing marketing copy. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' or 'copy sweep.' This skill provides a systematic approach to editing marketing copy through multiple focused passes.

Enforce non-functional engineering requirements: clippy cleanliness, test rigor, performance limits, safety defaults, and deterministic behavior.

Code review guidelines covering code quality, security, and best practices.

Send a terminal INPUT_REQUIRED callback when external information is missing and the orchestrator must block the workflow and comment on the ticket

End-to-end source code repository deep dive and review. Use when you need to understand a repo’s architecture, core abstractions, entrypoints and execution flow, extension points, and operational/developer setup; and when you must deliver a structured report (Markdown + standalone HTML) with diagrams (Mermaid), actionable recommendations, and a scored evaluation.

Draft and post single tweets or multi-tweet threads to X/Twitter — always user-approved before posting. Uses post_to_x.py.

How to carry on execution of workstreams after a plan.

review-rubric

security-audit

Provides Bitbucket API integration for interacting with repositories, pull requests, comments, and tasks. Use when working with Bitbucket PRs, reviewing code, or automating PR workflows.

You are a PR optimization expert specializing in creating high-quality pull requests that facilitate efficient code reviews. Generate comprehensive PR descriptions, automate review processes, and ensure PRs follow best practices for clarity, size, and reviewability.

benchmark-models

devex-review

Use during verification phase when conducting thorough code reviews and providing constructive feedback based on universal software quality principles.

ABAP performance best practices for ECC / traditional database systems (Oracle, DB2,MSSQL, MaxDB). Use when writing or reviewing ABAP code on NON-HANA systems.IMPORTANT: First use the SAP system info tool to check the system type — if the system is S/4HANA or runs on HANA DB, load the abap-performance-hana skill instead. Covers database access, buffering, internal table optimization, and ECC-specific patterns.

ABAP performance best practices for S/4HANA and HANA database systems.Use when writing or reviewing ABAP code on HANA-based systems.IMPORTANT: First use the SAP system info tool to check the system type — if the system is ECC or runs on a traditional database (Oracle, DB2, MSSQL), load the abap-performance-ecc skill instead. Covers code pushdown, CDS views, AMDP, advanced SQL, and HANA-optimized patterns.

**Never use Python, Pillow, ImageMagick, HTML/CSS rendering, or any other tool to generate credentials, certificates, diplomas, or badges.** Even if the user says they "just want a PNG" or "just want

Record the updated Codex PR review loop skill with preflight and post-merge learning.

retro

This tutorial demonstrates how to use Azure Machine Learning to build and deploy a custom skill for Azure Cognitive Search's AI enrichment pipeline.

this file is the canonical, reviewable skill instructions (no dynamic loading).

Use `skill` to load specialized skills that provide domain-specific instructions and workflows.

Guide the process of reviewing a business requirements document to identify potential issues and generate clarifying questions

- Manual via `/history` command

Test and validate an existing codebase. Analyzes code structure, performs automated code review with auto-fix, runs API endpoint tests and UI tests via Chrome browser automation, generates documentation. Phase 4 (code generation) is skipped since code already exists. Use when user asks to test existing code, run quality assurance, perform code review, or validate a system.

CLI design guidelines — arguments, flags, subcommands, help, output, errors, interactivity, config precedence. Apply when designing new commands or reviewing CLI UX.

Validate tests and docs, then create a GitHub PR with conventional commit formatting

github-api

自动化 GitHub 操作。当用户需要推送代码到 GitHub、管理仓库、创建 PR、处理 Issue、git push 失败时使用此技能。优先使用 mcporter call github.push_files 而不是 git push。

GitHub API integration with managed OAuth. Access repositories, issues, pull requests, commits, branches, and users.\n Use this skill when users want to interact with GitHub repositories, manage issues and PRs, search code, or automate workflows.\n For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).

MUST load this skill when use `gh` command. GitHub CLI (gh) comprehensive reference for repositories, issues, pull requests, Actions, projects, releases, gists, codespaces, organizations, extensions, and all GitHub operations from the command line.

receiving-code-review

Use when work is ready to push and open a pull request, or when asked to create/submit a PR.

Here’s the updated AGENTS.md with a Doc Sync note so contributors know to check all public-facing docs together when changes happen:

You are the Design & Accessibility Auditor.

Integrate the Kodus CLI with AI coding agents for autonomous review-fix loops.

- `src/` — TypeScript sources for the composite action (`dependency-review.ts`, `check-ossf.ts`, `check-guarddog.ts`, `frozen-install.ts`).