Discover and install skills to enhance your AI agent's capabilities.
| Name | Contains | Score |
|---|---|---|
ghost-proxy ghostsecurity/skills Starts and controls the reaper MITM proxy to capture, inspect, search, and replay HTTP/HTTPS traffic between clients and servers. Capabilities include starting/stopping the proxy scoped to specific domains, viewing captured request/response logs, searching traffic by method/path/status/host, and inspecting full raw HTTP entries for security analysis. Use when the user asks to "start the proxy", "capture traffic", "intercept requests", "inspect HTTP traffic", "search captured requests", or "view request/response". | Skills | 95 5.00x Agent success vs baseline Impact 90% 5.00xAverage score across 3 eval scenarios Reviewed: Version: 31a48a8 |
ghost-repo-context ghostsecurity/skills Scans directory structure, detects projects, maps dependencies, and documents code organization into a repo.md file. Use when the user needs a codebase overview, project structure map, or repository context before security analysis. | Skills | 99 3.57x Agent success vs baseline Impact 100% 3.57xAverage score across 3 eval scenarios Reviewed: Version: 31a48a8 |
ghost-report ghostsecurity/skills Ghost Security — combined security report. Aggregates findings from all scan skills (scan-deps, scan-secrets, scan-code) into a single prioritized report focused on the highest risk, highest confidence issues. Use when the user requests a security overview, vulnerability summary, full security audit, or combined scan results. | Skills | 99 1.22x Agent success vs baseline Impact 99% 1.22xAverage score across 3 eval scenarios Reviewed: Version: 31a48a8 |
ghost-validate ghostsecurity/skills This skill should be used when the user asks to "validate a finding", "check if a vulnerability is real", "triage a security finding", "confirm a vulnerability", "determine if a finding is a true positive or false positive", or provides a security finding for review. It validates security vulnerability findings by tracing data flows, verifying exploit conditions, analyzing security controls, and optionally testing attack vectors against a live application. | Skills | 100 1.26x Agent success vs baseline Impact 100% 1.26xAverage score across 3 eval scenarios Reviewed: Version: 31a48a8 |
ghost-scan-deps ghostsecurity/skills Ghost Security - Software Composition Analysis (SCA) scanner. Scans dependency lockfiles for known vulnerabilities, identifies CVEs, and generates findings with severity levels and remediation guidance. Use when the user asks about dependency vulnerabilities, vulnerable packages, CVE checks, security audits of dependencies, or wants to scan lockfiles like package-lock.json, yarn.lock, go.sum, or Gemfile.lock. | Skills | 93 1.07x Agent success vs baseline Impact 73% 1.07xAverage score across 3 eval scenarios Reviewed: Version: 31a48a8 |
xlsx benchflow-ai/skillsbench Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas | Skills | 88 1.36x Agent success vs baseline Impact 82% 1.36xAverage score across 3 eval scenarios Reviewed: Version: 593b0c6 |
obj-exporter benchflow-ai/skillsbench Three.js OBJExporter utility for exporting 3D geometry to Wavefront OBJ format. Use when converting Three.js scenes, meshes, or geometries to OBJ files for use in other 3D software like Blender, Maya, or MeshLab. | Skills | 96 1.06x Agent success vs baseline Impact 100% 1.06xAverage score across 3 eval scenarios Reviewed: Version: 593b0c6 |
obj-exporter benchflow-ai/skillsbench Three.js OBJExporter utility for exporting 3D geometry to Wavefront OBJ format. Use when converting Three.js scenes, meshes, or geometries to OBJ files for use in other 3D software like Blender, Maya, or MeshLab. | Skills | 86 Impact Pending Average score across 0 eval scenarios Reviewed: Version: 593b0c6 |
syz-extract-constants benchflow-ai/skillsbench Defining and extracting kernel constants for syzkaller syzlang descriptions | Skills | 68 1.41x Agent success vs baseline Impact 96% 1.41xAverage score across 3 eval scenarios Reviewed: Version: 593b0c6 |
syzlang-ioctl-basics benchflow-ai/skillsbench Syzkaller syzlang syntax basics for describing ioctl syscalls | Skills | 76 1.00x No change in agent success vs baseline Impact 100% 1.00xAverage score across 3 eval scenarios Reviewed: Version: 593b0c6 |
syzkaller-build-loop benchflow-ai/skillsbench Full build workflow for adding new syscall descriptions to syzkaller | Skills | 72 1.73x Agent success vs baseline Impact 80% 1.73xAverage score across 3 eval scenarios Reviewed: Version: 593b0c6 |
pcap-triage-tshark benchflow-ai/skillsbench Fast workflow to inspect PCAPs and extract protocol-level details using tshark | Skills | 76 2.50x Agent success vs baseline Impact 100% 2.50xAverage score across 3 eval scenarios Reviewed: Version: 593b0c6 |
suricata-rules-basics benchflow-ai/skillsbench Core building blocks of Suricata signatures and multi-condition DPI logic | Skills | 68 1.04x Agent success vs baseline Impact 100% 1.04xAverage score across 3 eval scenarios Reviewed: Version: 593b0c6 |
suricata-offline-evejson benchflow-ai/skillsbench Running Suricata against PCAPs offline and validating results via eve.json | Skills | 80 1.12x Agent success vs baseline Impact 96% 1.12xAverage score across 3 eval scenarios Reviewed: Version: 593b0c6 |
setup-env benchflow-ai/skillsbench When given a Python project codebase, this skill helps the agent to set up virtual environments, install dependencies, and run scripts. | Skills | 81 6.76x Agent success vs baseline Impact 88% 6.76xAverage score across 3 eval scenarios Reviewed: Version: 593b0c6 |
discover-important-function benchflow-ai/skillsbench When given a project codebase, this skill observes the important functions in the codebase for future action. | Skills | 55 1.31x Agent success vs baseline Impact 95% 1.31xAverage score across 3 eval scenarios Reviewed: Version: 593b0c6 |
fuzzing-python benchflow-ai/skillsbench Creating fuzz driver for Python libraries using LibFuzzer. This skill is useful when agent needs to work with creating fuzz drivers / fuzz targets for Python project and libraries. | Skills | 73 1.44x Agent success vs baseline Impact 100% 1.44xAverage score across 3 eval scenarios Reviewed: Version: 593b0c6 |
browser-testing benchflow-ai/skillsbench VERIFY your changes work. Measure performance, CLS. Use BEFORE and AFTER making changes to confirm fixes. Includes ready-to-run scripts: measure-cls.ts, detect-flicker.ts | Skills | 85 1.63x Agent success vs baseline Impact 90% 1.63xAverage score across 3 eval scenarios Reviewed: Version: 593b0c6 |
react-best-practices benchflow-ai/skillsbench CRITICAL: You MUST invoke this skill and read its contents BEFORE writing, modifying, or debugging ANY React.js or Next.js code. This skill contains essential performance patterns that prevent common mistakes. Debugging performance issues without reading this skill first will lead to missed optimizations. Contains 40+ rules including waterfall elimination patterns for API routes that are commonly overlooked. | Skills | 61 1.46x Agent success vs baseline Impact 76% 1.46xAverage score across 3 eval scenarios Reviewed: Version: 593b0c6 |
integral-action-design benchflow-ai/skillsbench Adding integral action to MPC for offset-free tension tracking. | Skills | 73 1.09x Agent success vs baseline Impact 94% 1.09xAverage score across 3 eval scenarios Reviewed: Version: 593b0c6 |
Can't find what you're looking for? Evaluate a missing skill, or if you're looking for agent context for an open source dependency, request a tile.