By poorants
General-purpose, cross-cutting tools usable in any project or context. Currently bundles engram — a networked PARA document brain (PARA management + knowledge-graph linking, MOC hubs, and integrity lint). Carries engram's capture-loop hooks.
Manage and enforce project code conventions. Extract conventions from existing code, check compliance, and evolve rules over the project lifecycle. Use when user says /code-convention, 'check conventions', 'code style', 'naming rules', 'add convention', 'convention check', 'extract conventions', or asks about coding standards. Triggers include 코드 컨벤션, 코딩 규칙, 네이밍 규칙, 코드 스타일, 컨벤션 검사, 컨벤션 추출, 코딩 표준, 컨벤션 추가.
UI 컴포넌트/레이아웃을 글이 아니라 "보고 골라서" 정하는 시각적 프로토타이핑 토너먼트. 화면에 무언가를 어떻게 표현할지(카드, 목록 행, 패널, 컨트롤, 빈 상태 등) 정해야 할 때, 프로젝트의 실제 테마 토큰 (팔레트·폰트·radii)을 재사용한 단일 오프라인 HTML로 20–30개의 서로 다른 시안을 생성하고 — 브라우저에서 체크박스로 투표 → 당선작을 잠긴 탭으로 이월 → 빈 슬롯을 새 시안으로 재생성하며 N라운드 반복해 최종안으로 수렴시킨 뒤 실제 코드에 반영한다. UI 옵션을 탐색/비교하거나, 컴포넌트를 프로토타이핑하거나, 레이아웃이 어색(너무 길다/비었다/복잡)해서 커밋 전에 대안을 보고 싶을 때 사용. 언어 무관 — 예: "컴포넌트 POC", "시안 만들어", "프로토타입", "디자인 시안", "카드 타입", "여러 개 만들어서 고르자", "투표해서 고르자", "시안 비교", "component POC", "design bake-off", "compare layouts", "show me options".
Networked PARA document brain — manages docs by PARA (Projects, Areas, Resources, Archives) AND weaves them into one connected knowledge graph via bi-directional links, MOC hubs, and integrity linting: a logical link layer over physical folders, so the vault grows like an interconnected brain, not isolated folders. Also upgrades a legacy folders-only PARA vault (`para/`) into a networked `brain/`. Use when the user wants to manage/organize/search docs, save meeting notes, archive or migrate a project, review doc status, OR connect notes, find orphan documents, fix broken links, update MOCs, raise neural density, build a knowledge graph, or review what the brain gained this session. Matches intent in any language — e.g. "문서 정리", "회의록 저장", "문서 아카이브", "para→brain 마이그레이션", "노트 연결", "링크 점검", "고아 문서", "MOC 업데이트", "브레인 리뷰", "organize docs", "connect notes", "check links", "find orphans", "para to brain".
Adopt and operate a structure-based MAJOR.MINOR.PATCH versioning scheme computed locally from the git commit graph at build time — no tags, CI, or tokens. MINOR = merge (MR/PR) count, PATCH = direct main commits since the last merge, MAJOR = a human-chosen milestone. Suited to internal/in-house products that need a monotonically increasing version to identify which build is which (for public libraries, prefer standard SemVer). Covers installing version.sh + version.conf, build-system wiring (Make/Go/Node/Python), MAJOR bumps, and tagging vX.Y.Z at actual release. Use when user says /git-versioning, 'set up versioning', 'version scheme', 'how is the version computed', 'bump major', 'tag a release', 'version 붙이기'. 트리거: 버전 관리, 버전 체계, 버전 매기기, 버전 계산, 버전 도입, 메이저 올리기, 릴리스 태그, 버전 스킬.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Claude Code skills marketplace by poorants.
Skills are organized into two kits, split by audience:
ant-common-kit — general-purpose, cross-cutting tools usable in any project or context.ant-dev-kit — software-development tooling.Windows:
iex (irm https://raw.githubusercontent.com/poorants/ant-skills/main/bootstrap/init-claude-project.ps1)
macOS / Linux:
bash <(curl -sL https://raw.githubusercontent.com/poorants/ant-skills/main/bootstrap/init-claude-project.sh)
This unified auto-installer registers the marketplaces, installs both kits (plus
Anthropic's example-skills), sets permissions, and initializes the PARA document
structure / code conventions based on the repo type. Re-running refreshes everything
to the latest. See bootstrap/README.md for the mode-aware details.
claude plugin marketplace add poorants/ant-skills
claude plugin install ant-common-kit@ant-agent-skills --scope user
claude plugin install ant-dev-kit@ant-agent-skills --scope user
User scope installs once globally (no per-repo duplication); engram's hooks self-gate to brain repos, so a single user-scope install is safe everywhere.
Tools usable in any project or context. Carries engram's capture-loop hooks
(hooks/hooks.json). Grows as more general-purpose tools are added.
| Skill | Description |
|---|---|
| engram | Networked PARA document brain — PARA management (Projects/Areas/Resources/Archives) + knowledge-graph linking, MOC hubs, and integrity lint |
claude plugin install ant-common-kit@ant-agent-skills --scope user
Dev-focused tooling. Grows as more development skills are added.
| Skill | Description |
|---|---|
| code-convention | Extract, enforce, and evolve project code conventions |
| component-prototype | UI variant prototyping tournament — generate many native-looking variants, vote, iterate to a final design |
claude plugin install ant-dev-kit@ant-agent-skills --scope user
ant-skills/
├── .claude-plugin/
│ └── marketplace.json # Plugin registry (ant-common-kit, ant-dev-kit)
├── bootstrap/ # One-liner setup scripts (the unified auto-installer)
│ ├── init-claude-project.ps1
│ ├── init-claude-project.sh
│ └── README.md
├── hooks/
│ └── hooks.json # engram capture-loop hooks (owned by ant-common-kit)
├── skills/
│ └── <skill-name>/
│ ├── SKILL.md # Skill definition (required)
│ ├── scripts/ # Helper scripts (optional)
│ ├── references/ # Reference docs (optional)
│ └── assets/ # Static assets (optional)
├── scripts/validate.py # Local skill validation
└── template/SKILL.md # Template for new skills
npx claudepluginhub poorants/ant-skills --plugin ant-common-kitCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
Intelligent prompt optimization: injects the right context at the right moment so Claude lands a better first output. Clarifies vague prompts with research-based questions, plus targeted nudges for approach selection, plan readability, workflow routing, background execution, subagent routing, output readability, user-decision questions, and plan-mode assessment