smartworldar afath · Agent Skills
242 Skills with substantive, source-verified documentation. Open a card to read the original instructions and review package and installation details.
investor-outreach
Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
lightpanda
Headless browser built from scratch for AI agents and automation workflows. 16x lighter and 9x faster than Chromium — 123MB peak memory vs 2GB, 5s vs 46s for 100 pages. Written in Zig, not a Chromium fork or WebKit patch. Use when integrating headless browser automation into AI agent pipelines, web scraping at scale, or any automation needing a lightweight, fast alternative to Puppeteer/Playwright with Chromium. Supports CDP (Chrome DevTools Protocol) for drop-in compatibility.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
market-research
Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries. Use when the user wants market sizing, competitor comparisons, fund research, technology scans, or research that informs business decisions.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
mcp-dependency-review
Statically review MCP configuration for mutable package references before approval or CI, without executing discovered MCP servers. Use when reviewing .mcp.json, Cursor, VS Code, Claude, Windsurf, or other repo-scoped MCP config.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
mcp-server-patterns
Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API. Use when building or debugging an MCP server — tools, resources, prompts, validation, or transport choice.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
mle-workflow
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
module-governance
Establish or maintain a business module's local agent instructions, domain-context links, and interface ownership when implementing a new module or changing its responsibilities. Reuse project-level rules and existing ECC workflows; ordinary bug fixes, styling, and read-only design discussions do not start module documentation setup.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
module-regression
Govern cross-module regression in large repositories with a REGRESSION.md ledger that records each module's downstream consumers and executable acceptance command. After a change, run the changed module and every affected downstream command, and use observed exit codes as regression evidence under the project's delivery policy. Use for module regression, regression ledgers, impact audits, downstream verification, and changes where modifying A may break B.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
nextjs-turbopack
Next.js 16+ and Turbopack — incremental bundling, FS caching, dev speed, and when to use Turbopack vs webpack.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
offensive-active-directory
Active Directory security assessment and hardening methodology covering Kerberoasting/AS-REP Roasting exposure, BloodHound ACL path auditing, ADCS certificate template misconfigurations (ESC1-ESC15), delegation controls (unconstrained/constrained/RBCD), and tiered administration architecture.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
offensive-advanced-redteam
Authorized Purple Team and adversary emulation methodology mapped to MITRE ATT&CK, validating that EDR, SIEM, and network telemetry accurately detect and alert on multi-stage intrusion scenarios.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
offensive-ai-security
AI and LLM application security assessment aligned with OWASP Top 10 for LLM Applications covering direct and indirect prompt injection, agent tool-call authorization gates, RAG document ACL enforcement, structured output validation, and system prompt isolation.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
offensive-anti-forensics
Digital forensics readiness and log integrity engineering covering centralized immutable SIEM forwarding, Windows Event Log / Linux auditd tamper detection, filesystem timestamp consistency (MFT $SI vs $FN), and chain-of-custody preservation.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
offensive-api-abuse
API business logic and automated abuse resilience assessment covering bulk enumeration prevention, cursor pagination bounds, idempotency key enforcement on state-changing endpoints, and cost-based rate limiting.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
offensive-api-security
Comprehensive OWASP API Security Top 10 auditing across REST, GraphQL, gRPC, and WebSocket APIs covering object/function-level authorization, mass assignment, OpenAPI schema validation, and token-bucket rate limiting.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
offensive-basic-exploitation
Source and binary auditing for classic memory safety flaws including unbounded stack copies (gets, strcpy, sprintf), format string specifiers (printf(userbuf)), and -fstack-protector-strong / -Wformat-security enforcement.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
offensive-bluetooth-ble
Bluetooth Low Energy (BLE) security assessment covering GATT profile enumeration, characteristic read/write authentication requirements, LE Legacy vs LE Secure Connections (ECDH) pairing, and application-layer encryption.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
offensive-bluetooth-classic
Bluetooth Classic (BR/EDR) security assessment covering SDP service discovery, link key negotiation minimum entropy (KNOB/BIAS remediation), HID profile restrictions, and discoverability controls.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
offensive-bug-identification
Systematic vulnerability discovery through static code auditing, CodeQL and Semgrep taint-tracking queries, security patch diffing, and sink-to-source reachability verification.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
offensive-business-logic
Application business logic vulnerability assessment covering multi-step workflow state machine enforcement, numeric boundary/negative value manipulation, privilege/subscription tier validation, currency rounding discrepancies, and invariant verification. Use when auditing checkout, billing, and multi-stage workflows.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
offensive-c2-frameworks
Network threat hunting and detection engineering for command-and-control (C2) channels covering JA3/JA4 TLS fingerprinting, periodic beacon jitter statistical analysis, DNS tunneling entropy detection, and egress proxy inspection.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
offensive-cicd-pipeline
CI/CD workflow security assessment for GitHub Actions, GitLab CI, and Jenkins covering pullrequesttarget untrusted code execution, ${{ }} script injection, third-party action SHA pinning, ephemeral runners, and GITHUBTOKEN permissions.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
offensive-cicd-secrets
CI/CD secret hygiene and architecture audit covering replacement of long-lived cloud keys with OIDC workload identity federation, environment approval gates, log redaction, and pre-commit secret scanning.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8
offensive-cloud
AWS, Azure, and GCP cloud security assessment covering IAM privilege escalation paths (iam:PassRole, policy versioning, Azure RBAC/Entra roles, GCP service account impersonation), storage bucket public exposure, IMDSv2 enforcement, and VPC endpoints.
- 1h installs
- 2
- GitHub stars
- 5
- Updated
- Nov 8