All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 415,052 of them, each with its token cost per session, a security scan with the line that triggered it, and whether it is the original or one of the copies.
WILLOSCAR/research-units-pipeline-skills
Skill Codex
Write output/DRAFT.md (or output/SNAPSHOT.md) from an approved outline and evidence packs, using only verified citation keys from citations/ref.bib.
Agent Claude Code
Read-only adversarial reviewer. Pre-PR it returns a verdict for the arbiter; on an open PR it posts true line-anchored INLINE comments via the git-host API, written in the PR's own language. Scores risk and checks cross-service compatibility. Never edits code.
slowmist/slowmist-agent-security
Skill Claude CodeCodex
Comprehensive security review framework for AI agents. Covers skill/MCP installation, GitHub repos, URLs/documents, on-chain addresses, products/services, and social shares. Built from real-world attack patterns and incident response experience.
Skill Claude Code
Use this skill when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial analysis, industry research, competitive intelligence, investment due diligence, or any consulting-grade analytical report. This…
Skill Claude Code
Precision-first adversarial bug hunting for runtime, logic, data, concurrency, and security defects. Uses deterministic risk triage, evidence-bounded retrieval, Hunter/Skeptic/Referee review, optional hybrid verification, and explicit immutable Fixer scope. Scan-only and single-pass by default; complete-coverage…
Agent Claude Code
Google Scholar Research Assistant - helps with academic literature search, citation tracking, and Zotero export via Google Scholar. Use proactively when the user needs to search Google Scholar, find papers, track citations, or manage references.
zenstory-ai/video-recap-skills
Plugin Claude Code
Bundles 6 skills · 772 tokens together
Independent stages plus a thin orchestrator for Chinese-narration recaps from supported video files: local Python/ffmpeg; remote Xiaomi MiMo ASR, VLM, and default TTS; optional Fish Audio TTS with a separate API key; final playback review required.
Skill Claude CodeCodex
Comprehensive Rust coding guidelines with 265 rules across 26 categories. Use when writing, reviewing, or refactoring Rust code. Covers ownership, error handling, async patterns, concurrency, unsafe code, API design, memory optimization, performance, numeric safety, conversions, serde, pattern matching, macros…
Plugin Claude Code
Bundles 34 skills · 3,095 tokens together
The PIV loop (plan, implement, validate, review, commit, PR) plus priming, planning, worktrees, and the meta-skills for building your own AI Layer.
Command Claude Code
Look up library documentation using Context7 MCP tools for a specific task.
Skill Claude CodeCodex
Discover, verify, security-screen, and maintain Solana wallet products using the canonical local registry in packages/ecosystem-data and current web research. Use when asked to refresh wallet data, find new Solana wallets, add or remove wallets, check wallets for scam or security concerns, audit wallet features or…
iusztinpaul/designing-real-world-ai-agents-workshop
Agent Claude Code
Tester role definition for /implement-universal. Loaded by the orchestrator at the start of the Tester phase, on logic tickets only. Trusts the SWE phase's happy-path e2e excerpt (does NOT re-run the Make target), runs at most 1 adversarial break path, walks every Acceptance Criterion with concrete evidence, and emits…
Skill Claude CodeCodex
Use vibe watch to run a managed Harness waiter that returns to the same conversation later. Best for reviews, CI, files, logs, and other wait-now-continue-later workflows.
Skill Claude CodeCodex
A Chinese-language course-building and study-feedback guide that turns provided lessons and related materials into a complete learning package. It can organize concepts, examples, diagrams, exercises, progress, and learner feedback into a structured course.
Skill Claude Code
Author Templatical email templates and integrate the Templatical email editor SDK. Use whenever the user wants to create, design, draft, mock up or edit a marketing, transactional or newsletter email — for example "make a product-launch email", "design a welcome email", "build an event invite", "draft an…
MCP server Claude CodeCodexCursor +2
One of 4 in .mcp.json
MCP server "ai-dial-ui-kit" as configured in epam/ai-dial-chat. Runs ./node_modules/@epam/ai-dial-ui-kit/dist/mcp-server.cjs with node.
buzhangsan/skills-manager-client
Skill Claude CodeCodex
An example skill from a skills-management project. A skill is a packaged set of instructions that teaches an agent how to handle a particular kind of task.
Skill Claude CodeCodex
Use Go AST-aware analysis to enumerate symbols, extract signatures, and propose mechanically safe refactors (read-only by default).
skydoves/compose-performance-skills
Skill Claude CodeCodex
Use this skill to run an end-to-end Jetpack Compose performance audit when the symptom is broad ("the app feels sluggish", "scroll is rough everywhere", "we're starting a perf sprint", "what should we fix first?"). Orchestrates the four-phase Measure → Diagnose → Fix → Verify loop by sequencing the 25 focused skills…
waybarrios/opencode-power-pack
Plugin Claude Code
Bundles 54 skills · 3,045 tokens together
Fifty-four software-development workflows for Claude Code, Codex, OpenCode, and Pi.
Skill Claude CodeCodex
Extract structured insight briefs from community research transcripts or notes. Produces pain points, stakeholder needs, opportunity maps, risks, and follow-up questions. Requires human review before publication.
Skill Claude CodeCodex
A skill that applies a project's DESIGN.md file as visual and brand guidance for interface work. It covers components, colors, fonts, layout, copy, motion, and visual assets.
MCP server Claude CodeCodexCursor +2
Metacognitive AI agent oversight: adaptive CPI interrupts for alignment, reflection and safety. Runs locally from the @pv-bhat/vibe-check-mcp npm package. Needs 1 environment variable to run.
Skill Claude CodeCodex needs its repo
Onboard an external repo via a structured handover assessment + harnessability scoring across 5 codebase dimensions.
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: