disciplined-quality-evaluation
Skills(SKILL.md)は、AIエージェント(Claude Code、Cursor、Codexなど)に特定の能力を追加するための設定ファイルです。
詳しく見る →disciplined-quality-evaluation
disciplined-research
disciplined-specification
disciplined-validation
disciplined-verification
Specialized skill for building production-ready Discord bots. Covers Discord.js (JavaScript) and Pycord (Python), gateway intents, slash commands, interactive components, rate limiting, and sharding.
List all channels in a Discord guild/server via the Discord API. Use this skill when the user wants to see all channels, find specific channels, or audit server structure.
Use after solution concepts exist to surface and prioritize assumptions behind outcomes, opportunities, or solution ideas and design experiments to test them.
When given a project codebase, this skill observes the important functions in the codebase for future action.
Conduct discovery interviews to gather requirements, clarify vague ideas, and create detailed specifications. Use when gathering requirements or clarifying vague ideas. Not for execution or simple partial updates.
Use when validating product assumptions before building, discovering unmet user needs, understanding customer problems and workflows, testing concepts or positioning, researching target markets, identifying jobs-to-be-done and hiring triggers, uncovering pain points and workarounds, or when users mention user research, customer interviews, surveys, discovery interviews, validation studies, or voice of customer.
Structured project discovery using proven methodologies (JTBD, Amazon PR/FAQ, ADR, Lean Startup, DDD). Transforms ambiguous ideas into clear, validated specifications ready for spec-kit handoff.
View and manage code-to-spec discrepancies. Detects API changes, function signature mismatches, and documentation gaps. Supports brownfield analysis and code-spec comparison.
Use when encountering bugs, test failures, unexpected behavior, errors, or performance problems - dispatches systematic-debugging-agent that enforces 4-phase process (root cause investigation, pattern analysis, hypothesis testing, implementation) to prevent quick-fix attempts and ensure proper debugging
django-cloud-sql-postgres
Expert Django developer specializing in Async Views, Django Ninja (FastAPI-like), and HTMX patterns for modern full-stack apps.
Expert Django developer mastering Django 4+ with modern Python practices. Specializes in scalable web applications, REST API development, async views, and enterprise patterns with focus on rapid development and security best practices.
Django framework workflow guidelines. Activate when working with Django projects, manage.py, django-admin, or Django-specific patterns.
Expert on Intel 8237A DMA Controller for ES-1841. Provides guidance on DMA transfers, floppy/HDD data transfer, DRAM refresh, page registers, and channel configuration.
Captures Dmitrii's distinctive writing voice and preferences for all written outputs. Use when creating case studies, blog posts, articles, documents, emails, proposals, PRDs, specifications, messages, or any written content on Dmitrii's behalf. MUST be invoked for any mid-to-long form content creation.
This skill provides guidance on finding and using D&D 5e rules for campaign content creation.
A comprehensive DnD campaign and adventure creation skill for game masters and creative content creators. Helps design complete campaigns, adventures, NPCs, encounters, maps, and storylines tailored for tabletop play. Use this when designing D&D content, creating campaign worlds, developing adventure hooks, designing encounters, or building narrative structures for player tables.
DNV Standards Specialist
Execute increment implementation following spec and plan - hooks run after EVERY task
Layer 4 artifact for Behavior-Driven Development test scenarios using Gherkin Given-When-Then format
引导用户通过结构化工作流程进行文档协作。当用户想要编写文档、提案、技术规范、决策文档或类似结构化内容时使用。此工作流程帮助用户高效传递上下文、通过迭代精炼内容,并验证文档对读者有效。触发词:writing docs、creating proposals、drafting specs 或类似文档任务。
Create Data Contracts (CTR) - Optional Layer 9 artifact using dual-file format (.md + .yaml) for API/data contracts
Deep expertise for documentation lifecycle orchestration. Quality assessment frameworks, workflow patterns, delegation protocols, and release checklists. Auto-loads for doc-expert agent.
Fetch library and framework documentation via context7-mcp and fetch-mcp
Format documentation with emojis, status bars, and versioning matrix. Use when creating or updating README files, documentation, specs, or any markdown files.
Reference for The Fold's typed comments and doc forms system. Use when adding type annotations, documentation, todos, or other metadata to Scheme code. Covers (doc ...) syntax, standard tags, search commands, and type checker integration.
Generate comprehensive, accurate API documentation from source code. Use when creating or updating API documentation, generating OpenAPI specs, or when users mention API docs, endpoints, or documentation.
This skill enables systematic, parallelized analysis of documentation using multiple specialized agents. It maximizes throughput by running independent sections in parallel while respecting dependenci
Lists and filters documentation files by type, status, tags, and date range with frontmatter parsing
Locate and retrieve specific documentation sections from DiPeO's docs/ by heading anchors or keywords. Returns minimal, targeted excerpts instead of full files. Use when you need precise documentation context without loading entire guides.
Documentation lifecycle management skill. Activates when user mentions documentation, docs, sync, quality, validation, releases, or setup. Routes to appropriate agent (doc-expert for orchestration, doc-writer for content) and provides gentle reminders about documentation health.
Efficiently navigate codebase documentation during Research phase. Use instead of Grep/Glob for finding architectural decisions, feature specs, and technical docs. Maps topics to doc locations for fast context retrieval. If codebase lacks documentation structure, provides patterns to establish one.
Apply Progressive Disclosure principles to organize large documentation projects. Restructure docs into hierarchical structure, reduce token usage by 95%+, and create README files for navigation.
Create Atomic Requirements (REQ) - Layer 7 artifact using REQ v3.0 format with 12 sections, SPEC-readiness scoring, and IMPL-readiness scoring
Token-efficient documentation search using Serena Document Index. 90%+ token savings vs reading full files. Use BEFORE reading README.md or docs/ files. Triggers on architecture questions, pattern lookups, and project-specific documentation needs.
Create Technical Specifications (SPEC) - Layer 10 artifact using YAML format for implementation-ready specifications
Create Task Breakdown (TASKS) - Layer 11 artifact decomposing SPEC into AI-structured TODO tasks
Meta-skill for converting external documentation into Claude Agent Skills with proper YAML frontmatter and structured instructions following the official specification.
Updates documentation after code changes to keep docs in sync with code reality. Use AFTER implementation is complete. Covers feature docs, workflow docs, and index files.
Use when user asks about 'documentation workflow', 'how to document', 'doc system', 'what is llmdoc', 'how does llmdoc work', or needs guidance on the documentation system.
Generates and improves documentation
DocETL is a system for creating LLM-powered data processing pipelines. This skill helps you build end-to-end pipelines: from data preparation to execution and optimization.
SOTA Docker/Compose architecture, implementation, refactor, and security hardening. Use when working on containerization tasks such as creating or rewriting Dockerfiles, docker-compose files, buildx/bake configs, .dockerignore, and CI pipelines for build/test/scan/publish; auditing existing container setups for security, correctness, size/perf, and best practices (least privilege, non-root, minimal images, pinned base images, BuildKit secrets, healthchecks); debugging Docker build/run issues; or designing dev vs prod compose workflows across services (DB/cache/queues) with correct networking, volumes, secrets, and resource limits.