NeVibeCode · 916 items
Agent setup: memory, context, orchestration: skills, plugins, subagents, slash commands and mcp servers
Agent setup: memory, context, orchestration for Claude Code, Codex and Cursor: skills, plugins, subagents, slash commands and mcp servers, from popular to niche.
isms-audit-expert skill Skill for ISO 27001 compliance verification, security control assessment, and certification support. Documents audit findings, classifies nonconformities, and manages corrective actions.
Claude Code
791installs
skill-security-auditor skill Scans AI agent skills for malicious code before install: detects eval(), os.system(), data exfiltration, prompt injection, and vulnerable dependencies.
Claude Code
785installs
codebase-onboarding skill Turns an unfamiliar repo into onboarding docs: stack, config files, layout, local setup. Useful when someone new joins the team or after a large refactor.
Claude Code
698installs
agent-designer skill Turns written requirements into a multi-agent architecture, validated tool schemas and a read on your run logs. Worth running before you wire agents to a design you picked by gut.
Claude Code
682installs
agent-workflow-designer skill Picks a multi-agent workflow pattern and scaffolds the config before you write code, with handoff contracts and retry gates spelled out.
Claude Code
658installs
mcp-server-builder skill Turns an OpenAPI spec into an MCP server: tool manifest plus starter code in Python or TypeScript, with a validator to check it.
Claude Code
644installs
threat-detection skill Supports proactive threat hunting with hypotheses, IOC sweeps and telemetry anomaly checks. Use it to investigate activity that automated alerts may miss.
Claude Code
637installs
executive-mentor skill This skill challenges plans, hard decisions and failure reviews. Use it before a board meeting, an irreversible move or a post-mortem.
Claude Code
606installs
security-hardening command This command runs a staged security review: vulnerability scanning, threat modeling, and architecture checks. Use it when a project needs a documented hardening pass.
Claude Code CX Codex Cursor
437installs
dotnet-mcp-builder
official skill Build MCP servers and basic clients in C#/.NET with ModelContextProtocol 2.x. Use the skill when an agent needs to add MCP support to a .NET project.
GitHub Copilot
152installs
agent-installer subagent Subagent for discovering, browsing, and installing Claude Code agents from the awesome-claude-code-subagents repository. Simplifies finding and integrating new tools into your workflow.
Claude Code
363installs
status command Shows Conductor project status, active tracks, and next actions. Use it to inspect task progress and spot blockers.
Claude Code CX Codex Cursor
348installs
embedded-systems subagent A subagent for microcontroller firmware work with memory, power, and real-time constraints in mind. Use it for RTOS tasks, drivers, and peripheral integration.
Claude Code
279installs
vendor-management skill A skill for recurring vendor reviews: a 0–100 score across five weighted dimensions, SLA compliance tracking and a risk matrix for the portfolio.
Claude Code
297installs
build-evidence-map
official skill Builds an auditable evidence map for a disputed decision while retaining support, counterevidence and gaps. Use it when a prose summary would hide disagreement.
GitHub Copilot
70installs
gh-attach
official skill Uploads local files to GitHub attachments, embeds them in PRs, issues, and comments, and downloads existing attachments.
GitHub Copilot
64installs
gitmoji
official skill Turns a diff or a one-line description into a gitmoji commit message: one emoji for the intent, then a short imperative line. Useful where the repo history already runs on emoji.
GitHub Copilot
46installs
setup-my-iq
official skill An interview-driven skill that writes six markdown files about you: how you work, who is on your team, and how your tools are configured. Useful when the agent lacks that context.
GitHub Copilot
35installs
vardoger-analyze
official skill Reads your GitHub Copilot CLI conversation history and writes a fenced block of personalization rules into the instructions file Copilot already loads.
GitHub Copilot
33installs
steno-mode
official skill Compresses agent replies into disciplined shorthand, cutting roughly 40% of response tokens while code, commands, paths and API names stay exact.
GitHub Copilot
32installs
bench-read
official skill Reads shared bench artifacts and summarizes their state for the operator. Use it when desks exchange findings through workspace files.
GitHub Copilot
28installs
desk-journal
official skill Keeps a desk journal across sessions by recording completed work, current state, and the next step. Use it when work needs to resume with its context intact.
GitHub Copilot
25installs
desk-open
official skill Opens a new desk in the workshop: a folder, a first journal entry and a signals directory, so the next Copilot session finds the trail.
GitHub Copilot
23installs
arquiteto-de-empresa skill Interviews a founder across 12 business phases and turns the answers into a linked markdown bundle that both people and AI agents can read.
Claude Code
51installs
figma-design-to-code
official skill Guides an agent through implementing a Figma node in a project’s existing stack. Use it before calling get_design_context.
CX Codex GP ChatGPT
30installs
agents-sdk
official skill Builds, runs, and tests OpenAI Agents SDK apps from Codex. Turns a prompt, repo, or session into a working agent with tools and eval tests.
CX Codex GP ChatGPT
22installs
google-docs
official skill This skill creates, edits, adapts, and checks Google Docs while preserving templates, structure, and styling. Use it for documents with tabs, tables, and controlled fields.
CX Codex GP ChatGPT
22installs
research-router-skill
official skill This skill routes broad life-sciences questions to the right skills, normalizes key entities, and produces a concise evidence-backed synthesis. Use it when one lookup is not enough.
CX Codex GP ChatGPT
16installs
continual-learning skill A skill that teaches AI agents to remember mistakes, tool patterns, and project conventions between sessions. Without it, each run starts fresh; with it, agents compound their knowledge and work more accurately.
Claude Code GitHub Copilot
79installs
rnacentral-skill
official skill This skill queries RNAcentral to search RNA entries, inspect a single record, and retrieve cross-references. Use it when an agent needs concise RNAcentral summaries.
CX Codex GP ChatGPT
13installs
ideate
official skill This skill turns a Product Design brief into three visual directions. Use it to explore interface variants, remixes, and new product concepts.
CX Codex GP ChatGPT
5installs
figma-use-motion
official skill Adds use_figma context for Figma node animation, covering keyframes, easing, animation styles, and timeline duration.
CX Codex GP ChatGPT
5installs
figma-use-figjam
official skill This skill gives Codex FigJam-specific context for Figma’s MCP tools. Use it when an agent must inspect or edit a FigJam board.
CX Codex GP ChatGPT
5installs
build-report
official skill Builds analytical reports with findings, tables, and visuals for executives, product teams, or technical audiences.
CX Codex GP ChatGPT
4installs
Prompt Engineer
official subagent Treats each message as a prompt draft, reviews its quality, and returns a rewritten instruction for a language model.
GitHub Copilot
★ 40,369repo stars
VSCode Tour Expert
official subagent Subagent that creates .tour files — interactive step-by-step codebase walkthroughs in VSCode CodeTour format.
GitHub Copilot
★ 40,369repo stars
881–916 of 916