Explore skills
5,473 skills found
Category alert
Get new Pesquisa e Web skills every Monday
compliance-os
Compliance OS is a meta-orchestrator enabling compliance teams to configure applicable frameworks, compute control overlap, simulate internal audits, and consolidate evidence across multiple standards. It helps determine which of its 12 supported frameworks, such as ISO, GDPR, and SOC 2, apply based on a company profile.
adversarial-reviewer
This skill provides an adversarial code review to break the self-review monoculture, offering genuinely critical feedback on recent changes before merging a PR. It forces perspective shifts through hostile reviewer personas to catch blind spots.
llm-wiki
Use for building or maintaining a persistent personal knowledge base (second brain) in Obsidian, where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current.
senior-architect
This skill assists with system architecture design, evaluation, and review, covering topics like microservices, databases, scalability, and technical decisions. It's useful for architecture decision records (ADRs), tech stack evaluation, and dependency analysis.
caveman
Ultra-compressed communication mode. Reduces token usage by approximately 75% by removing filler, articles, and pleasantries, while maintaining full technical accuracy. Use when the user says caveman mode, talk like caveman, use caveman, less tokens, be brief, or invokes /caveman.
board
Read, write, and browse the AgentHub message board for agent coordination.
merge
Merge the winning agent's branch into base, archive losers, and clean up worktrees.
demo-video
Use when the user asks to create a demo video, product walkthrough, feature showcase, animated presentation, marketing video, or GIF from screenshots or scene descriptions. Orchestrates playwright, ffmpeg, and edge-tts MCPs to produce polished video content.
eval
Evaluate and rank agent results by metric or LLM judge for an AgentHub session.
status
Show DAG state, agent progress, and branch status for an AgentHub session.
code-tour
Use this when the user requests to create a CodeTour .tour file, which provides persona-targeted, step-by-step walkthroughs linking to real files and line numbers. This is triggered by requests such as creating an onboarding, architecture, or PR review tour, explaining code, or any structured code walkthrough.
dependency-auditor
Audits and manages dependencies across multi-language projects, identifying vulnerabilities, license conflicts, transitive dependency risks, and safe-upgrade paths. Use when auditing third-party packages before release, investigating a CVE, planning a major version bump, or running a license-compliance review.