Skill Claude CodeCodex
Use when you need to interact with Google services from Clawdbot, including Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
18 2mo ago A 31 tokens
vercel
02Skill Claude CodeCodex
Use when you need to deploy projects to the Vercel hosting platform in the cloud, such as Next.js applications, static sites, and serverless functions.
18 2mo ago B 35 tokens
clawhub
03Skill Claude CodeCodexGemini CLI
Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.ai with advanced caching and compression. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with optimized performance.
18 2mo ago C 64 tokens
Skill Claude CodeCodexGemini CLI
Scans installed OpenClaw skills for malicious patterns including prompt injection, credential theft, data exfiltration, obfuscated payloads, and backdoors. Use when installing new skills, after skill updates, or for periodic security scans. Runs deterministic pattern matching — fast, offline, no API cost.
18 2mo ago A 64 tokens
Skill Claude CodeCodexGemini CLI
A handful of commands available for code security, dependency security and other security audits using Snyk.
18 2mo ago B 32 tokens
Skill Claude CodeCodexGemini CLI
Use this skill when you are writing tests, refactoring test, or asked to run tests. This skill provides you with guidelines for testing the project.
18 2mo ago A 34 tokens
Skill Claude CodeCodex
Run diff, commit, push and other git related commands.
18 2mo ago A 20 tokens
Skill Claude CodeCodex
Adds a new eval category to the Coding Agent Security Benchmark so tasks can be grouped and filtered independently via --category. Updates the EVALCATEGORIES registry, scoring dispatch, task JSON files, documentation, and verifies end-to-end with a dry-run. Use when the user says "add a new category", "create a…
2 7d ago A 147 tokens
Skill Claude CodeCodex
Adds a complete vulnerable-code fixture to the Coding Agent Security Benchmark (snyk-vulnbench): fixture.json project metadata, ground-truth JSON, eval tasks, Snyk Code SARIF capture, mapRuleId updates, optional new VulnTypes, and verification. Use when adding or onboarding a new directory under fixtures/, wiring…
2 7d ago A 0 tokens
Skill Claude CodeCodex
Generates benchmark chart artifacts from JSONL result files: a self-contained HTML report, one PDF export per rendered chart, a compact chart manifest, and an article-ready visuals guide with placeholders, PDF paths, and captions. Use when the user says "generate charts", "make an HTML report", "visualize the…
2 7d ago B 181 tokens
Skill Claude CodeCodex
Produces a Markdown statistics report for the benchmark's fixture projects by combining each fixture's fixture.json metadata with cloc source-code counts. Use when the user asks for fixture statistics, project size, lines of code, fixture inventory, language breakdowns, or a comparison of benchmark projects. Use it…
2 7d ago A 96 tokens
Skill Claude CodeCodex
Convert benchmark reports, evaluation writeups, or results-driven markdown articles into arXiv-ready LaTeX projects. Use when Codex needs to turn markdown plus benchmark data, tables, citations, HTML/SVG charts, and figures into a self-contained article directory containing main.tex, references.bib, arXiv-compatible…
2 7d ago B 89 tokens
Skill Claude CodeCodex
Produces publishable markdown benchmark reports from eval results, modeled on the structure and tone of frontier AI lab reports (Anthropic, Cursor, FrontierSWE, BaxBench). Use when the user wants to write up benchmark findings, turn eval results into a blog post or technical report, publish a model/agent comparison…
2 7d ago A 184 tokens
Skill Claude CodeCodex
Runs security benchmark evaluations from natural language. Translates requests like "run find vulns for js 1 to 3 with opus and snyk" into the correct tsx src/index.ts CLI invocation with --task, --config, and --category flags. Use when the user says "run benchmark", "benchmark js find vulns", "evaluate with sonnet"…
2 7d ago A 182 tokens
blog-writer
15Skill Claude CodeCodex
Instructions for AI coding agents producing technical blog posts in this style.
2 7d ago A 0 tokens
cloc
16Skill Claude CodeCodex
Estimates source-code size with cloc using the repository's standard exclusions. Use when the user asks to count lines of code, compare project sizes, measure a fixture, or run cloc on a directory. Accept either a filesystem directory or a fixture name such as "app-project-keystonebank". Do NOT use for vulnerability…
2 7d ago A 80 tokens
Skill Claude CodeCodex
Creates high-quality agent skills by running the official Claude skill creator plugin and then applying a structured set of enhancement phases covering use-case design, frontmatter completeness, body structure, writing quality, and progressive disclosure architecture. Use this skill when the user wants to create a new…
2 7d ago A 126 tokens
Instructions file CodexOpenCode
AGENTS.md instructions for snyk-labs/snyk-vulnbench, covering coding agent security benchmark, project purpose, primary eval categories, tech stack and architecture.
2 7d ago A 2,518 tokens
Instructions file
Claude Code instructions for snyk-labs/snyk-vulnbench.
2 7d ago A 3 tokens
Skill Claude CodeCodex
Prefer defaulting and naked switches over if/else chains for shallow branching logic in Go. Use when writing or refactoring conditional logic with 1-3 branches.
2 7d ago A 39 tokens
Skill Claude CodeCodex
Use when adding a cross-cutting concern (OTEL tracing, logging, metrics, caching, auth) to a business domain, creating files under business/domain//extensions/, or adding the extension seam (ExtBusiness/Extension) to a bus package.
2 7d ago A 58 tokens
Skill Claude CodeCodex
Enforce primitive-at-edges / strong-types-in-Business layering and the toBus/fromBusResponse/toDB converter pattern. Use when writing, editing, or auditing Go files under app/, business/domain/, or .../stores/db.
2 7d ago A 56 tokens
review-pr
23Skill Claude CodeCodex
Service Diffguard: read-only PR review lenses for correctness, error visibility, comment truthfulness, test coverage, type/contract boundaries, and simplification across every language in this repo (Go, Vue/JS/SCSS, Rego, protobuf, SQL, Helm/YAML, shell). Use for PR review, pre-commit review, unstaged-diff review, or…
2 7d ago A 88 tokens
Skill Claude CodeCodex
Apply modern Go syntax guidelines based on the project's Go version. Use whenever writing, editing, or reviewing Go (.go) code — not only when explicitly asked for guidelines.
2 7d ago A 38 tokens