Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying…
基于 Skill 内置的 Python 脚本体系处理 Word/.docx 自动化开发、排版、解析与规范化。Use when Codex needs to inspect the skill's bundled docs/ and scripts/.py before answering or implementing Word automation tasks, especially for document creation, heading/numbering/style control, page layout, headers/footers/page numbers, TOC/LOT/LOF, tables…
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…
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what…
Systematic performance optimization for OpenClaw AI agents. Covers session management, context budget optimization, token tracking, and automated maintenance. Use when optimizing OpenClaw agent performance or conducting routine maintenance.
Interactive architecture design workflow — from requirements gathering to pattern recommendation, tech stack selection, and ADR generation. Use when designing system architecture, choosing between monolith vs microservices, planning scalability, selecting databases or caches, reviewing architecture documents, or…
A behavior-driven development method that describes expected software behavior in plain language using Given, When, and Then. BDD focuses on whether a feature matches the requirement, while test-driven development, or TDD, focuses on preventing code defects with tests.
A Chinese-language brainstorming and design-questioning workflow that turns an unclear idea into a detailed plan saved in `.scratch/<feature>/RAD.md`. It first checks whether the project has completed its required setup.
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
基于文档索引的迭代开发 — 项目文档自动管理与增量更新。Use when starting a new project needing docs/, updating existing project documentation, or after code changes to incrementally update docs/architecture.md, docs/api.md, docs/changelog.md.
Find incomplete issues on the local markdown issue tracker, execute their acceptance criteria in dependency order, and mark them as completed. Use when you want to批量执行未完成的任务、按依赖顺序实现 issue、或自动完成已规划的切片。.
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
File-based planning for execution sessions. Creates taskplan.md, findings.md, and progress.md to persist AI agent context across tool calls, /clear, and session boundaries. Use when 开始编码实现、执行已规划的 issue、或任何需要 AI 在长任务中保持目标和进度记忆的场景。配合 /pd-tdd 使用实现 disciplined implementation。.
Build a throwaway prototype to flush out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine…
Use when the user explicitly requests PUA mode or signals frustration, repeated failures (2+), passive behavior, quality complaints, unverified completion, giving up, or asks to try harder/change approach. Common triggers: 'try harder', 'figure it out', 'stop giving up', 'you keep failing', '加油', '别偷懒', '你再试试'…
A local code-review process for examining Git changes. It checks project rules, likely bugs, code quality, and security risks, then reports only issues judged highly likely to be real.
A code-quality review guide based on software engineering books and language standards. It checks a project against selected rules and produces a structured report with rule references.
REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs.
C++ coding standards based on the C++ Core Guidelines (isocpp.github.io). Use when writing, reviewing, or refactoring C++ code to enforce modern, safe, and idiomatic practices.
Sets up an ## Agent skills block in AGENTS.md/CLAUDE.md and docs/agents/ so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of pd-to-issues, pd-to-prd, pd-triage, pd-diagnose, pd-tdd…