Dependency and package security toolkit with three skills: audit a system/OS or globally-installed package before installing it (system-package-audit), triage reported vulnerabilities in a project's dependencies (vulnerability-report-triage), and vet a new dependency before adopting it (dependency-adoption-review).
Plugin security-check from marketplace infinum-ai in infinum/ai. Commands read from the repo's manifest — today.
dependency-adoption-reviewDue-diligence review of a new third-party dependency before you add it to a project — answers "should we take this dependency at all?". Checks necessity vs. native/existing alternatives, license (and relicensing risk), maintenance health, governance and bus factor, security track record, adoption si
system-package-auditSupply-chain security audit of a system/OS package or globally-installed CLI tool (Homebrew, apt, and global npm/pip/cargo/gem installs) before you install or upgrade it — checks known CVEs, maintainer/ownership changes, install scripts, source-vs-registry integrity, the version diff, and typosquatt
vulnerability-report-triageTriage reported vulnerabilities in a project's dependencies (Dependabot, GitHub Advisory, or an in-house weekly security report) for SOC2/compliance deadlines. Detects the tech stack, classifies each item by production-vs-development impact and direct-vs-transitive placement, judges whether it actua
Act as an Infinum Purpose Driven Design (PDD) practitioner — drawing on the PDD philosophy, principles, 6-phase process, and full toolkit. Skills: discovery workshops, interview guides, archetypes, rainbow & competitive analysis.
12 skills
Make Figma design systems and screen files AI-readable so MCP/Code-Connect code generation produces correct, on-brand code. Platform-neutral structure and naming for the component library (ai-ready-design-system) and the assembled screens/flows (ai-ready-screens). Pair with a platform binding from design-conventions.
2 skills
Local repo housekeeping for the feature you're working on: save a disposable per-feature progress note for session handoff (under ~/.claude/progress/, never committed), and clean up after a PR merges by pruning the merged branch and worktree. All local.
2 skills
Generate a Product Requirements Document (PRD) in Markdown. Guided flow with clarifying questions, structured output, and iterative refinement.
1 skill
Platform-binding conventions for ai-ready-figma design systems — the framework-specific casing, naming, state vocabulary, and token-to-theme mapping that AI code generation needs. Ships flutter-m3-conventions (Flutter Material 3) today; add a skill per platform as more are needed.
1 skill
Download Figma frame screenshots to disk as PNG files. Works via local MCP server or Figma REST API.
1 skill
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.
hooks
Design fluency for frontend development. 1 skill with 24 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
1 skill · 4 agents · hooks
Cross-installation agent federation with zero-trust security, PII-gated data flow, and compliance-grade audit trails
3 skills · 1 command · 1 agent
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Install the "AAS Security Engineer" workflow plugin from Agentic Awesome Skills.
12 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.