Claude Code plugins

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.

Code quality subset: one-pass review and A-F ship verdict with TypeScript, React, Next.js, OWASP, and database checklists, plus findings-only and grade-only modes (suede-code), and CI branch protection that gates the merge (suede-ci-gate).

67 skills

JasonColapietro/suede-creator-skills 124

Suede AI marketing and growth subset: SEO and AI search, paid acquisition and outbound, monetization (pricing, offers, paywalls), lifecycle and retention, and the measurement and operations layer. License notices for adapted material are in NOTICE.md.

67 skills

JasonColapietro/suede-creator-skills 124

code

claudecodex

Code and planning framework plugin

13 skills · 6 commands · 24 agents · hooks

closedloop-ai/claude-plugins 124

vibe

claudecodex

Vibe sessions, handoff, seed refresh, and ClosedLoop ticket workflows

17 skills · 17 agents

closedloop-ai/claude-plugins 124

Collection of 22 focused skills for building, optimizing, evaluating, and deploying DSPy applications.

24 skills

OmidZamani/dspy-skills 124

Decision and analysis frameworks including OODA, SWOT, Cynefin, Red Team, Pre-mortem, WRAP, 5 Whys, and Post-mortem

23 skills

neurofoo/agent-skills 124

Prioritization frameworks including Eisenhower Matrix, RICE Scoring, and MoSCoW

23 skills

neurofoo/agent-skills 124

Creative and ideation frameworks including SCAMPER, Six Thinking Hats, and Design Thinking

23 skills

neurofoo/agent-skills 124

closedloop-core

claudecodex

Shared ClosedLoop planning, intelligence, review, QA, measurement, and PR monitoring

12 skills

closedloop-ai/claude-plugins 124

gosqlx

claude

Validate, format, lint, analyze and security-scan SQL with GoSQLX (MCP tools, skills, slash commands, a SQL reviewer agent and a .sql validation hook).

5 skills · 4 commands · 1 agent · 1 MCP server · hooks

ajitpratap0/GoSQLX 124

Get the most out of your MemoryLane data. See how work really gets done and find what to automate.

6 skills · 1 MCP server

deusXmachina-dev/memorylane 124

tma1

claude

Local-first LLM agent observability. Track tokens, cost, and conversations on your machine.

4 skills · 2 commands

tma1-ai/tma1 124

crawlie

claudecodex

Turn your agent into an SEO team: crawl any site, catch broken links, redirect chains, missing metadata, thin content, and AI-search (GEO) gaps — then get a prioritized fix list and diff crawls to prove the fixes landed. Runs on Crawlie Cloud: sign in and go, nothing to install.

4 skills · 1 MCP server

spronta/crawlie 124

aldine

claude

Claude writes, typesets and reviews LaTeX in your Aldine: repair loop, section drafting and bibliography skills over the Aldine MCP connector.

3 skills · 1 MCP server

trahloff/Aldine 124

Learn anything, beautifully. AI research pipeline + interactive local learning boards, powered by your Claude Code subscription.

1 skill · 1 command · 1 agent

raiyanyahya/Superlearn 124

Watch a tutorial/lecture video and produce structured study notes

1 skill · 1 command · hooks

devinilabs/claude-watch 124

synthteam

claudecodex

Consult distilled personas of colleagues — build them from Slack history (distill-slack-persona), get a single colleague's take (ask-colleague), or convene a deliberating panel (ask-team).

3 skills

nickwinder/synthteam 124

Local LLMs on your own GPUs through LlamaForge: what fits, download, load, Auto-Forge the fastest setup, hand grunt work to a local model.

2 skills

dadwritestech/LlamaForge 124

view-browser-tab

claudecodex

Screenshot open browser tabs for visual debugging.

1 skill

puffinsoft/peek-cli 124

Turn a brief, script or MP4 into a reviewed, verified vertical explainer video, with review receipts before publishing.

1 skill

runesleo/claude-video-kit 124

The AI Literacy framework's complete development workflow — harness engineering, agent orchestration, literate programming, CUPID code review, compound learning, and the three enforcement loops

41 skills · 32 commands · 20 agents · hooks

Habitat-Thinking/ai-literacy-superpowers 123

ultraship

claude

Full lifecycle plugin: plan, build, test, review, ship, deploy, verify, reflect. Currency Guard keeps Claude on current docs. 41 tools, 45 skills, 13 agents.

45 skills · 16 commands · 13 agents · 2 MCP servers · hooks

Houseofmvps/ultraship 123

ax

claude

ax - the agent experience layer. Local graph of every Claude Code + Codex session, skill invocation, edit, and commit. Surfaces what to use, what to ground on, and which experiments to package next.

12 skills · 1 agent

Necmttn/ax 123

llm-wiki

claude

Build a shared Markdown wiki with local hybrid search, cited evidence and a compiled graph. Capture task experience and evaluate skill improvements with explicit apply/rollback. Optional hosted wiki on Cloudflare with MCP access for every agent. Includes the llm-wiki skill and ten /wiki:* commands.

1 skill · 10 commands

praneybehl/llm-wiki-plugin 123

Skills, knowledge, and scripts for developing plugins for IDA Pro in Python, using idiomatic patterns, lessons, and tricks.

3 skills

HexRaysSA/claude-marketplace 123

(Unsafe) Skills, knowledge, and scripts for reverse engineering with IDA Pro. Autonomously writes and executes IDA Domain scripts to analyze binaries, extract functions, decompile code, and automate any reverse engineering task.

1 skill · 1 command · 1 agent

HexRaysSA/claude-marketplace 123

Researches and authors Mitchell-extended model cards from a model name.

1 skill · 1 command · 1 agent

Habitat-Thinking/ai-literacy-superpowers 123

Agents accountable for helping to maintain human understanding. Ships the `diagnostic-legibility` agent — builds and self-challenges two models of a codebase scope (architectural moving parts and domain concepts) via a five-question retained-challenge cycle, then cross-checks the two collections against each other via a five-question per-direction cycle. The `/diagnose` command surfaces the mutually-corrected models on demand as a readable report. The `ConceptualPipelineMap` template adds a standalone, presentation-agnostic flow-perspective data model; the agent's `scope-resolution` mode answers 'what does my task touch?' (a bounded, disclosed scope from a work task); and its `pipeline` mode traces control flow within that bound into a ConceptualPipelineMap alongside the architectural/domain collections, then cross-checks all three against each other (the maximal six directed pairs) for mutual correction. The `/pipeline-map "<task>"` command renders the task-scoped map as a self-contained HTML flowchart (pinned, SHA-verified Mermaid inlined; no CDN) with a scope-resolution panel, node-detail table, and no-JS fallback; `--predict-change` adds an opt-in change-site prediction (which stages the task will modify and where it will insert new ones) disclosed as a prediction, never a directive.

2 commands · 1 agent

Habitat-Thinking/ai-literacy-superpowers 123

spex

claudecodex

Specification-Driven Development with Process Discipline for Claude Code

2 skills

rhuss/cc-spex 123

ida-mcp

claudecodex

Official Hex-Rays IDA MCP Server.

1 MCP server · hooks

HexRaysSA/claude-marketplace 123