Skills real projects publish on GitHub, most starred first. Each one says what it will make an agent do before you copy it.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
awarexonePipes a download into a shellSkillawarexone/AXguard/axguard-preship/SKILL.md
Pre-ship security review checklist for the current repository. Use for focused release reviews covering auth, SQL/injection/SSTI, path, SSRF, XSS, uploads, GraphQL, crypto, secrets, cloud, supply chain, debug, and agent risks when a full /axguard-audit is not requested.
awarexonePipes a download into a shellSkillawarexone/AXguard/axguard-remediate/SKILL.md
Apply concrete defensive fixes for confirmed AXguard findings and re-audit. Use with /axguard-fix after triage. Prefer minimal patches, critical first, then verify with axguard audit/scan.
awarexoneSkillawarexone/AXguard/axguard-report/SKILL.md
Produce or polish AXguard Markdown and HTML audit reports from verified evidence. Use with /axguard-report. Prefer regenerating via axguard audit; tighten narrative only with confirmed findings.
awarexoneSkillawarexone/AXguard/axguard-security/SKILL.md
Analyze code for security vulnerabilities, investigate findings, verify fixes, and assess security risk before deployment. Use when reviewing security-sensitive changes, before ship/deploy, or when an agent should call AXGuard MCP instead of inventing its own scanner.
awarexonePipes a download into a shellSkillawarexone/AXguard/axguard-triage/SKILL.md
Triage AXguard scanner output — false-positive filter, severity promotion, and keep/drop gates per vuln class. Use after an audit when the user wants signal, not volume, or runs /axguard-triage.
awarexoneSkillawarexone/AXguard/cloud-security/SKILL.md
Review cloud and CORS misconfiguration in app code and IaC-adjacent configs — metadata URLs, public buckets, wildcard origins (CWE-918 / CWE-942 / A05:2021 / A10:2021).
awarexoneSkillawarexone/AXguard/command-injection/SKILL.md
Analyze OS command and shell injection in application code — use when reviewing subprocess, exec, system, shell=True, or user-influenced shell strings (CWE-78 / CWE-77 / A03:2021).
awarexoneReads credentialsSkillawarexone/AXguard/configuration-security/SKILL.md
Find security misconfiguration before ship — debug flags, verbose errors, exposed actuators/admin, weak defaults (CWE-489 / CWE-209 / A05:2021).
awarexoneSkillawarexone/AXguard/deserialization-security/SKILL.md
Analyze unsafe deserialization and object-decode sinks — use when reviewing pickle, YAML load, Java ObjectInputStream, PHP unserialize, or untrusted serialized blobs (CWE-502 / A08:2021).
awarexoneSkillawarexone/AXguard/file-upload-security/SKILL.md
Analyze unsafe file upload handling — use when reviewing multipart uploads, extension/MIME checks, stored filenames, image processors, or user-supplied archives (CWE-434 / A04:2021).
awarexoneSkillawarexone/AXguard/graphql-security/SKILL.md
Analyze GraphQL API security — use when reviewing schemas, resolvers, introspection, batching, authorization per field, or CSRF on cookie-authenticated GraphQL endpoints (API1/API5/API8:2023).
awarexoneSkillawarexone/AXguard/jwt-security/SKILL.md
Analyze JWT implementation flaws — use when reviewing alg confusion, none algorithm, missing verify, weak secrets, or claim validation gaps (A07:2021 / API2:2023 / auth.jwt rules).
awarexonePipes a download into a shellSkillawarexone/AXguard/mcp-security/SKILL.md
Review Model Context Protocol servers/clients and tool bridges for trust, supply-chain, and over-privileged tool exposure before ship.
awarexoneSkillawarexone/AXguard/oauth-security/SKILL.md
Analyze OAuth/OIDC integration security — use when reviewing redirect URIs, state/nonce, token handling, PKCE, or confused-deputy risks in authorization code flows (CWE-601 / A07:2021 / API2:2023).
awarexoneReads credentialsSkillawarexone/AXguard/path-traversal/SKILL.md
Analyze path traversal and unsafe file access — use when user input influences file paths, downloads, includes, zip extraction, or static file send APIs (CWE-22 / A01:2021).
awarexoneSkillawarexone/AXguard/prompt-injection/SKILL.md
Assess direct and indirect prompt-injection risks in LLM/AI features — use for chatbots, RAG, agents, and tool-calling apps.
awarexoneSkillawarexone/AXguard/prototype-pollution/SKILL.md
Analyze JavaScript prototype pollution risks — use when reviewing deep merges, recursive object assigns, query-to-object parsers, or untrusted JSON key merges (CWE-1321 / A03:2021).
awarexoneReads credentialsSkillawarexone/AXguard/secrets-detection/SKILL.md
Find and triage hard-coded secrets, tokens, and credentials in source and build artifacts before ship (CWE-798 / A07:2021 adjacent).
awarexoneSkillawarexone/AXguard/security-architecture-review/SKILL.md
Review security architecture and trust boundaries — use for design-level control gaps across authZ, secrets, egress, multi-tenant isolation, and insecure-by-design features (A04:2021) before or with /axguard-audit.
awarexonePipes a download into a shellSkillawarexone/AXguard/security-remediation/SKILL.md
Apply minimal defensive patches for confirmed findings and verify with re-audit — post-triage only.
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Open a skill to see its discussion. Reports from people and their agents are coming.
