Plugins

现实范围评估与规格转任务分解专家

GitHub Project V2 management — auto-discovery, opinionated board setup, and issue hygiene hooks

Initializes and maintains an Obsidian vault inside the project directory that serves as a living knowledge base of the project's structure, features, tools, and dependencies.

Reads a project's plan.md and builds/updates a tasks.md split into Milestones and sub-tasks with descriptions and a status tracking table. Auto-triggers at project/session start so the planning convention never needs re-explaining.

Tools and guidance for software project planning, feature breakdown, epic management, implementation planning, and task organization for development teams.

Discover, catalog, and rank everything you've built or sketched on a machine via a two-pass parallel read-only sweep: a clustered project catalog plus blind-spot agents (transcripts, other agent CLIs, running services, research artifacts, beyond-home), synthesized into a tiered novelty/leverage ranking with idea/live/dormant tags and evidence-anchored rationale.

Project quality assurance: review configuration and documentation files for consistency, completeness, and correctness

Project quality assurance: review configuration and documentation files for consistency, completeness, and correctness

Generate a high-level weekly status report for a Basecamp project. Activity-first via the basecamp CLI; outputs a lean 3-section markdown report (TL;DR, blockers, gaps).

Claude Code project infrastructure scaffolding with hooks, agents, settings, and CLAUDE.md templates (project-type-specific plus generic/DM-standard starters)

Client intake, workstream-based scoping estimates, risk registers, brand-styled Excel scope packages, and Sayer brand guidelines (scoping-only; delivery skills not yet bundled).

Create new project repositories of various types

One-time project scaffolding and environment setup: onboard, scaffold, e2e-skill-scaffolding.

from ccplugins/awesome-claude-code-plugins

Four meta-skills: pressure-test decisions, grill your plans, multiply your options, and establish shared language.

AgentsMD authoring standards, workspace management, and skills/tools registry lookup

Universal Claude Code workflow with specialized agents, skills, hooks, and output styles for any software project. Includes orchestrator, code-reviewer, debugger, docs-writer, security-auditor, refactorer, and test-architect agents.

Generate and maintain an interactive HTML status page (project_status.html) summarizing a project's main parts, what shipped, and what's pending. Restyled with the ivory/clay/olive palette from thariqs.github.io/html-effectiveness.

47 skills for project workflows — planning, specs, auditing, debugging, code review, shipping, and more

from hhopkins95/ai-systems

A multi-agent meta-skill for Codex, Claude Code, and other coding agents: turn each project, machine, device, API, and MCP server into a lightweight, self-improving skill; auto-log key events; reflect logs into lean lessons.

DevOps 자동화 스킬 모음 - 코드 분석, 설계, 구현, 테스트, 리뷰, 리팩토링, 문서화, 트러블슈팅 등 23+ 스킬

Long-running, goal-oriented project management for Obsidian. Stateful workspaces, Kanban boards, journal bridge.

AI-native project management workflow. Skills for task management, design reviews, health checks, and more — integrated with ProjSight MCP Server.

from mikekelly/opencode-promode

Prompsit Translation API: CLI setup, text/document translation, quality evaluation (BLEU, chrF, MetricX), parallel corpus scoring (Bicleaner), and monolingual data annotation (Monotextor).

Editorial localization pipeline (agent workflow). Tier-based strategy (witness/body/UI), glossary lock, back-translation gate, diff-aware re-runs. Wraps `prompsit translate` plus an LLM editor pass.

Refines a rough prompt idea into a polished, Claude-optimized prompt through a structured clarification loop.

Iterative prompt engineering assistant — pick a framework, draft, critique, and deliver a finished artefact with test cases.

Prompt engineering: system prompt anatomy, personas, tone, templates, few-shot examples, reasoning, and output constraints.