anton-abyzov

47 mods in 8 plugins, 3 repositories, 277 stars between them.

sw

01

anton-abyzov/specweave

Plugin Claude Code

Bundles 11 skills, 1 agent, 2 hooks · 516 tokens together

Portable intent and verified progress across coding tools. Eleven focused workflow skills, two default lifecycle hooks, and a deterministic CLI and live local dashboard.

not rated 165 +1 changed yesterday A tokens not measured original MIT

debug

02

anton-abyzov/specweave

Skill Claude Code

Systematic 4-phase debugging with escalation protocol. Use when saying "debug", "investigate bug", "find root cause", "why is this failing", or "fix this bug".

not rated 165 +1 yesterday A SkillSpector: warn 38 tokens original MIT

diagrams

03

anton-abyzov/specweave

Skill Claude CodeCodex

Mermaid diagrams following the C4 model: context, container, component, sequence, ER and deployment. Use when saying "diagram", "visualize", or "architecture diagram".

not rated 165 +1 changed 24d ago A SkillSpector: pass 0 tokens original MIT

e2e

04

anton-abyzov/specweave

Skill Claude Code

Generate and run Playwright E2E tests traced to spec.md acceptance criteria, with an optional accessibility audit. Use when saying "e2e tests" or "a11y audit".

not rated 165 +1 yesterday A SkillSpector: warn 38 tokens original MIT

release-expert

05

anton-abyzov/specweave

Skill Claude CodeCodex

Multi-repo release coordination: version alignment, RC lifecycle, release waves, rollback planning. Use when saying "release", "version alignment", or "cut an RC".

not rated 165 +1 yesterday A SkillSpector: pass 0 tokens original MIT

tdd-cycle

06

anton-abyzov/specweave

Skill Claude Code

Execute full TDD red-green-refactor cycle with validation gates. Use when saying "TDD cycle", "test-driven development", or "full TDD workflow".

not rated 165 +1 changed 24d ago A SkillSpector: pass 33 tokens original MIT

sw-do

07

anton-abyzov/specweave

Skill Claude Code

Work a SpecWeave increment task by task - claim, implement inside the task's Files, test, commit, done with evidence - then verify and close. Use for "implement", "continue", "keep going".

not rated 165 +1 changed 4d ago A SkillSpector: pass 44 tokens original MIT

sw-handoff

08

anton-abyzov/specweave

Skill Claude Code

Hand work to another tool, account or machine and pick it up there, in two words. Use when the user says "hand off", "hand off all", "out of tokens", "switching accounts", "pick up" or "continue".

not rated 165 +1 changed 5d ago A SkillSpector: pass 51 tokens original MIT

sw-increment

09

anton-abyzov/specweave

Skill Claude Code

Plan work as a SpecWeave increment - one spec.md with Problem, Scope, numbered ACs, Approach and Tasks - before writing code. Use for "plan a feature", "new increment", "let's build X".

not rated 165 +1 changed 4d ago A SkillSpector: pass 46 tokens original MIT

sw-review

10

anton-abyzov/specweave

Skill Claude Code

Adversarial fresh-context review and risk check of an increment before it ships; every finding cites path:line and is re-verified. Use for "review", "qa", "quality check", "critique this".

not rated 165 +1 changed 4d ago A SkillSpector: pass 45 tokens original MIT

sw-jev

11

anton-abyzov/specweave

Skill Claude Code

Use Jev or optional OpenAI Decisions for bounded routing, shell-command risk, text screening and failure triage. Use for "jev", "system one", or "classify this".

not rated 165 +1 changed 7d ago C 38 tokens original MIT

sw-auto

12

anton-abyzov/specweave

Skill Claude Code

Run a SpecWeave increment unattended until every task is done, then verify and close. Use for "auto mode", "run until done", "ship this while I sleep".

not rated 165 +1 yesterday A 36 tokens original MIT

sw-brainstorm

13

anton-abyzov/specweave

Skill Claude Code

Widen the options before committing - framed options compared on stated criteria, ending in a pick that becomes an increment. Use for "brainstorm", "ideate", "what are our options".

not rated 165 +1 yesterday A 39 tokens original MIT

sw-done

14

anton-abyzov/specweave

Skill Claude Code

Close a SpecWeave increment - every task done or skipped, specweave verify green, a fresh-context review, then specweave complete. Use for "close it", "we are done", "finish up".

not rated 165 +1 yesterday A 45 tokens original MIT

sw-project

15

anton-abyzov/specweave

Skill Claude Code

Keep a project's goal, decisions, work items, artifacts and briefs portable across AI tools and accounts. Use for project coordination, "project brief", "what is this project about".

not rated 165 +1 yesterday A 36 tokens original MIT

sw-sync

16

anton-abyzov/specweave

Skill Claude Code

Sync SpecWeave increments with GitHub, Jira or Azure DevOps - push progress, pull or import issues, check token and health, run setup. Use for "sync", "push to GitHub", "import issues".

not rated 165 +1 yesterday A 46 tokens original MIT

sw-team

17

anton-abyzov/specweave

Skill Claude Code needs its repo

Run one SpecWeave increment with several agents in parallel - any tool or account, a worktree each, claims through the ledger, one close. Use for "team", "parallel agents", 3+ disjoint lanes.

not rated 165 +1 yesterday A 46 tokens original MIT

codex-bridge

18

anton-abyzov/vskill

Plugin Claude Code

Bundles 1 skill · 98 tokens together

Cross-runtime plugin demonstrator — ships one strict-mode SKILL.md (agents-md-author) installable in both Anthropic Claude Code and OpenAI Codex CLI from the same source. Reference implementation for the dual-manifest authoring pattern (.claude-plugin/ + .codex-plugin/).

not rated 47 +1 3d ago A tokens not measured original MIT

easychamp

19

anton-abyzov/vskill

Plugin Claude Code

Bundles 1 skill · 188 tokens together

EasyChamp tournament management — create sports leagues and tournaments, build brackets, schedule matches with venues, and record results. Backed by the EasyChamp MCP server.

not rated 47 +1 3d ago A tokens not measured original MIT

frontend

20

anton-abyzov/vskill

Plugin Claude Code

Bundles 4 skills · 590 tokens together

Frontend development skills — visual design with browser verification, Figma-to-code workflows, Code Connect publishing, design token extraction, and design system integration across React, Vue, SwiftUI, and Compose.

not rated 47 +1 changed 20d ago A tokens not measured original MIT

marketing

21

anton-abyzov/vskill

Plugin Claude Code

Bundles 2 skills · 356 tokens together

Marketing automation skills — social media content creation, posting, engagement, content distribution, audience growth across 11 platforms, Blotato batch scheduling via REST API + MCP, and Slack messaging with context-aware session management.

not rated 47 +1 changed 20d ago A tokens not measured original MIT

personal

22

anton-abyzov/vskill

Plugin Claude Code

Bundles 2 skills · 237 tokens together

Personal knowledge and finance automation — autonomous Obsidian vault management (PARA + LLM Wiki) and end-to-end corporate/personal tax preparation from Xero, bank statements, and Google Drive.

not rated 47 +1 3d ago A tokens not measured original MIT

productivity

23

anton-abyzov/vskill

Plugin Claude Code

Bundles 1 skill · 141 tokens together

Personal productivity automation skills — expert network survey completion, time-saving automation for professional consultations and paid expertise sharing.

not rated 47 +1 3d ago A tokens not measured original MIT

skills

24

anton-abyzov/vskill

Plugin Claude Code

Bundles 1 skill · 50 tokens together

Skill discovery, installation, and authoring — find skills with scout, create new universal skills with skill-builder.

not rated 47 +1 3d ago A tokens not measured original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: