rust-learning-lab
claudecodexLearn and review Rust through syntax, rationale, practice, and debugging.
1 skill
Every plugin for Claude Code we can find on GitHub, read straight from each repo's .claude-plugin manifests. Install one with claude plugin marketplace add owner/repo and claude plugin install name@marketplace — each page has the exact lines. Looking for Codex? See Codex plugins.
Learn and review Rust through syntax, rationale, practice, and debugging.
1 skill
Research a topic (company, service, website, product) and render a short promo video as an MP4, drawn entirely in code. Give it a design (hand-drawn with 8-bit minis, motion graphics, sand art, lyric music video, beat-synced footage, UI morph, hero comic, toon, scrapbook, torn-paper collage, particles, split-flap, neon, arcade, terminal, thermal receipt, transit map, blueprint, the design language of Apple, Samsung, Ferrari, Nike, or Spotify, any site's DESIGN.md, or any free style you describe), the topic, and the format; the story is written from the research, with code-generated music.
1 skill
DEPRECATED — SpecSwarm commands have moved to the `ss` plugin. Install `ss@specswarm-marketplace` and uninstall this plugin. Slated for full removal in v8.0.0.
A rail of your session's prompts beside the transcript or above the prompt; hover to read one, click to jump to it.
Oxy, SageOx's mascot, in Claude Code's thinking line, reacting to what Claude is doing. /oxy shows, hides, and sizes him.
What SageOx gave this session, in a scrollable pane beside the chat: each ox call, the context ox put in front of the model, and what was read, plus a one-line lane under each ox call showing what moved between SageOx and the session. /ox-session-report opens, refreshes, and closes it; /ox-session-report flow on|off|still sets the lanes.
Complete mobile development toolkit for Android, iOS, and Kotlin Multiplatform.
46 skills · 35 commands · 27 agents · 3 MCP servers · hooks
Correctness workflow for structured development. 33 skills with configurable intensity levels: spec-before-code, skeptical review, enforced TDD, formal modeling, adversarial review, verification, documentation, and metrics. Intensity gates let you choose standard, high, or critical rigor per project.
33 skills · 16 agents
Best-of-breed general Flutter engineering skills — architecture, Riverpod 3.x state, testing, persistence, i18n/RTL, accessibility, performance, plus codegen/CI/migration runbooks — usable in any Flutter app.
40 skills
MyWorkflow — 2.2(归并版):协作语义修正 + 等待与阻塞纪律 + 技能精简 15 技能 + 每轮任务纪律 hook(长会话反漂移)+ 续接与恢复协议 + 9 月内容 + DSH 原生。技能直接按描述触发;开发类任务全程按阶段调 skill(root-cause/real-world-verify/github-collab 等)。
21 skills · hooks
Ten battle-tested SDLC skills: sdlc-intent (PRD digest + seven-layer audit + A/B/C risk tiering), sdlc-design (technical design: alternatives, tiered interface contracts, shared assets, C/H decisions, slicing constraints), sdlc-test (cases/dev/static/exec/spec/report with human checkpoints), sdlc-gate (risk-tiered adversarial review gate: 4/2 fresh-context subagents or self-check, plus guard_dev), sdlc-doubt (adversarial re-check of non-trivial decisions), sdlc-ui-visual (design-to-code visual restoration via screenshots: DOM geometry + pixel heatmap + tiered fix rounds), sdlc-release-check (pre-release audit: config keys, job/MQ registrations, DDL/DML grading, runbook), sdlc-guardrails (write-time red-line engine: PostToolUse hook + pre-commit + baseline scan), sdlc-sync (artifact sync bridge between local markdown and the team-facing platform), sdlc-handoff (cross-agent session handoff: self-contained card, drift check, direct takeover).
10 skills
Public social media data from TikTok, Instagram, YouTube, X, Facebook and 28 more platforms.
8 skills · 1 MCP server
Persistent memory across conversations. Remember preferences, decisions, and project context with AutoMem.
1 skill · 3 commands · 1 MCP server · hooks
AI skills for building embedded Linux distributions with yoe: create, update, and audit units, diagnose build failures, and pull packages from Alpine.
6 skills
Standalone kairos skills: orchestration + cdd-* family + CDD engine.
6 skills
YouTube tools — search, transcripts, video info, channel browsing, playlists
2 skills · 1 agent · 1 MCP server · hooks
Ray Amjad's agent skills: turn an idea into a spec (idea-to-spec), ship it as a reviewed and verified PR (task-lifecycle), and make your coding agent prove its work (Prove It).
5 skills
Multi-agent orchestration for coding agents: run external agent CLIs (Codex, Claude Code, OpenCode, Grok Build, Gemini, Devin CLI, Antigravity CLI) as independent reviewers, stateful repository researchers, steerable single-agent implementers, or media workers (audio/video transcription, image generation and editing) via the `porch` CLI. Also ships coordinator-mode (a long-lived coordinating role that delegates implementation and keeps a journal across compaction) and remote-agents: dedicated remote Linux/Windows agent hosts (SSH-over-SSM, headless desktop, work bridge).
3 skills
Connect your agent to Dataiku: inspect projects, datasets, recipes, ML, and agents with typed MCP tools, and drive Dataiku Cobuild to build project-level assets.
2 skills · 1 MCP server
Skills for writing idiomatic gsx (JSX-like Go templates)
2 skills
Observability hooks, protocol enforcement, and the thoughtbox CLI
1 MCP server · hooks
Local-first AI memory palace for AI assistants
2 skills
Boundary design, eight boundary rules, violation detection, remediation. Pairs with micro-frontend-canvas skill. Module Federation v1/v2, Native Federation, Single SPA.
2 skills
AI humanizer skill: removes AI slop and the signs of AI writing from prose, then measures the rewrite against human baselines.
2 skills
六爻起卦、排盘核对与两套断卦方法
2 skills
Regular Expression Linter — write your own linting rules using regular expressions. Skills for running relint and authoring new rules.
2 skills
Draft-first PRD generator — probe the real problem, draft 4 design documents immediately, confirm assumptions in one batch
1 skill · 1 command
Author, validate, review and release LinkML schemas with the ohi CLI (ohi linkml). Covers schema authoring, bootstrapping from RDFS/OWL/SHACL/JSON Schema/XSD or sample data, modelling-quality review, instance-data validation, and GitHub Actions setup. Auto-load for any task involving a LinkML schema.
2 skills
Build, run, diagnose, deploy, and monetize BNB Chain seller agents with bag.
1 skill
Detect merge conflicts across git worktrees before they happen. Warns before writing to files that would cause merge conflicts when running multiple AI agents in parallel.
hooks