agentleFS

Claude skills and agent skills

Skills real projects publish on GitHub, most starred first. Each one says what it will make an agent do before you copy it.

Best matches · from page 7Worked for most · soon
ShmalexMSkill

security

ShmalexM/agent-skills/skills/security/SKILL.md

Defensive security review of a repo, diff, PR, dependency set or config, using tiered subagents. Deterministic scanners run first, cheap models map the attack surface, a stronger model hunts by category, and a different model family tries to disprove each finding before it is reported. Use when the user types /security, or asks for a "security review", "security audit", "is this safe to merge", "check for vulns/secrets", or "threat model this". Defensive only, for code and systems the user owns or is authorized to assess.

Often used withalbert-dmcost-reducertrigger-dev

035d agoReviewMountCreate a free account to mount
shreyam1008Reads credentialsSkill

security

shreyam1008/shre-skills/skills/security/SKILL.md

Reviews and implements web security boundaries, authorization, output encoding, session protection, and secret handling. Use for security-sensitive changes or a requested security review.

Often used withalbert-dmcost-reducertrigger-dev

02mo agoReviewMountCreate a free account to mount
sithumdgomezSkill

security

sithumdgomez/claude-skills/.claude/skills/security/SKILL.md

Secure web and desktop application development. Use when writing authentication, authorization, API endpoints, form handling, database queries, file uploads, Electron apps, Tauri apps, IPC handlers, cryptography, secrets management, security headers, input validation, or when reviewing code for vulnerabilities. Covers OWASP Top 10, XSS, CSRF, SQL injection, SSRF, command injection, path traversal, and desktop app security. Also usable as a support sub-skill: other skills can invoke it by name mid-build to check code or a design for vulnerabilities before finalizing.

Often used withalbert-dmcost-reducertrigger-dev

056d agoReviewMountCreate a free account to mount
soreavisSkill

security

soreavis/ai-docent/skills/security/SKILL.md

Multi-session defensive security coach: prompt injection, data leaks, agent safety, and incident response, taught with inert examples. Use only when asked to start or continue this course.

Often used withalbert-dmcost-reducertrigger-dev

034d agoReviewMountCreate a free account to mount
syntropic137Reads credentialsSkill

security

syntropic137/harness-app-template/.claude/skills/security/SKILL.md

Use when reviewing security concerns: secrets in code, SAST coverage, input validation, authn/authz boundaries, sensitive-data handling, dependency CVEs, SSRF, hand-rolled escaping, threat modeling for high-stakes changes, defense in depth, agentic-AI / LLM tool-call attack surface (prompt injection, indirect injection, MCP abuse)

Often used withalbert-dmcost-reducertrigger-dev

06mo agoReviewMountCreate a free account to mount
syntropic137Reads credentialsSkill

security

syntropic137/software-leverage-points/skills/security/SKILL.md

Use when reviewing security concerns: secrets in code, SAST coverage, input validation, authn/authz boundaries, sensitive-data handling, dependency CVEs, SSRF, hand-rolled escaping, threat modeling for high-stakes changes, defense in depth, agentic-AI / LLM tool-call attack surface (prompt injection, indirect injection, MCP abuse)

Often used withalbert-dmcost-reducertrigger-dev

033d agoReviewMountCreate a free account to mount
ThuPhuong1010Skill

security

ThuPhuong1010/claude-factory/.claude/skills/security/SKILL.md

Security patterns. Trigger khi code auth, handle user input, thiết kế hệ thống có dữ liệu nhạy cảm.

Often used withalbert-dmcost-reducertrigger-dev

08mo agoReviewMountCreate a free account to mount
travissmithv1Skill

security

travissmithv1/claude-skills/skills/security/SKILL.md

Apply security best practices for passwords, credentials, database access, and data protection. Use when handling authentication, secrets management, or implementing security controls.

Often used withalbert-dmcost-reducertrigger-dev

029d agoReviewMountCreate a free account to mount
zeeshanalimughalReads credentialsSkill

security

zeeshanalimughal/claude-skills/skills/security/SKILL.md

Practical application security — injection, authentication, authorization, secrets, and input validation. Use when writing any code that handles user input, auth, files, money, or personal data; when reviewing for vulnerabilities; or when storing credentials.

Often used withalbert-dmcost-reducertrigger-dev

04mo agoReviewMountCreate a free account to mount
odooSkill

odoo-security

odoo/odoo/skills/odoo-security/SKILL.md

Security audit of Odoo addon code: access control (ir.access, field groups, sudo), injection (SQL, domain, eval, XSS via Markup/markup()), untrusted public methods/RPC, controller auth/CSRF, file access, deserialization, returning complex objects, getattr/setattr, timing attacks. Use when auditing an addon, or judging whether a specific construct (a sudo, raw SQL, a route, ...) is safe.

56k55d agoReviewMountCreate a free account to mount
SentrySkill

sentry-security

getsentry/sentry/.agents/skills/sentry-security/SKILL.md

Sentry-specific security review based on real vulnerability history. Use when reviewing Sentry endpoints, serializers, or views for security issues. Trigger keywords: "sentry security review", "check for IDOR", "access control review", "org scoping", "cross-org", "security audit endpoint".

No other project uses it yet

46k5mo agoReviewMountCreate a free account to mount
mizchiSkill

sql-security

mizchi/skills/sql-security/SKILL.md

SQL injection screening for host code (MoonBit / TS / Rust) plus secretlint setup notes. Flags single-line template-literal or string-concat SQL builders, regardless of value source — the scanner is line-based and does NOT trace data flow, so a clean scan is not proof of safety (multi-line template literals are missed) and every hit needs a manual review or an explicit `// sql-security: ok` opt-out.

4221d agoReviewMountCreate a free account to mount
hypnguyen1209Skill

ai-security

hypnguyen1209/offensive-claude/skills/ai-security/SKILL.md

Use when attacking an AI/ML system or model — prompt injection & jailbreaks (Crescendo, Skeleton Key, Best-of-N), RAG/vector poisoning, agentic/MCP exploitation (CVE-2025-54136), ML supply-chain RCE (pickle CVE-2025-32434), model extraction / membership inference / adversarial suffixes (GCG)

40156d agoReviewMountCreate a free account to mount
AWSSkill

aws-security

aws/agent-toolkit-for-aws/plugins/aws-core/skills/aws-security/SKILL.md

AWS security service suitability, coverage and cost recommendations: WAF/origin overlap, AWS Network Firewall inspection coverage and policy review, VPC endpoint, Transit Gateway/Cloud WAN segmentation and DNS Firewall security-control suitability, certificate renewal ownership and monitoring, incident response triage ownership, centralized security log store (CloudWatch or Security Lake). Also factual configuration, findings, data sources and severity scoring for GuardDuty, Inspector, Security Hub V2/OCSF (Exposure, connectors, automation), Security Hub CSPM/ASFF (standards, controls), Macie, Detective, Security Lake, AWS Security Incident Response membership and case coverage, and Organizations security policies. Applies to advisory security-service choices even when one service is named. Implementation, rule or code authoring, deployment, scans and troubleshooting outside these factual procedures belong to specialist skills. Supports local AWS CLI and AWS MCP.

Steady49 mentions in 2 weeks

3 projects use a version of this

3.5k4d agoReviewMountCreate a free account to mount
zakirkunSkill

security-ops

zakirkun/deep-eye/.agents/skills/security-ops/SKILL.md

Router for Deep Eye agent skills: pentest, bug-bounty, red-team, blue-team, ctf. Use for security ops, mixed intent, offensive vs defensive choice.

2.3k3mo agoReviewMountCreate a free account to mount
tinyfish-ioSkill

dep-security

tinyfish-io/tinyfish-cookbook/skills/dep-security/SKILL.md

Check every dependency in a package.json against live CVE databases and security advisories in real time — specifically targeting vulnerabilities disclosed in the last 48 hours, the window that Snyk, Dependabot, and npm audit miss. Use this skill whenever a user mentions checking dependencies for vulnerabilities, wants to audit their package.json, asks about CVEs for their packages, says "are my dependencies safe", "check my packages for security issues", "any new vulnerabilities in my deps", or pastes a package.json and asks about security. Also trigger when a user mentions wanting fresher data than Snyk or Dependabot provides. Returns: which dependencies have brand-new vulnerabilities, severity, what the vulnerability does, whether a patched version exists yet, and a prioritised fix list.

Steady4 mentions in 2 weeks

No other project uses it yet

2.3k6mo agoReviewMountCreate a free account to mount
MicrosoftSkill

dv-security

microsoft/Dataverse-skills/.github/plugins/dataverse/skills/dv-security/SKILL.md

Security-role assignment, user access, application users, business units, and admin self-elevation in Dataverse environments. Use when the user wants to give someone access, grant a role, become an admin, or add a service principal.

25959d agoReviewMountCreate a free account to mount
zereightReads credentialsSkill

security-scan

zereight/gitlab-mcp/.github/skills/security-scan/SKILL.md

Rapid security scanning workflow for code changes. Activates a focused security sweep. Activate when: security scan, scan for vulnerabilities, check for secrets, security check, run security audit, check deps.

Steady6 mentions in 2 weeks

89 projects use a version of this

Often used withdjango-securitydeployment-patternspostgres-patterns

2.1k35d agoReviewMountCreate a free account to mount
heartleoSkill

security-scan

heartleo/zlib/.agents/skills/security-scan/SKILL.md

Scan zlib for security problems before a release or after a dependency, network, credential, or file-handling change — govulncheck, secret scanning, GitHub alert review, and a credential-boundary code review — and handle a private vulnerability report through a GitHub security advisory.

Steady15 mentions in 2 weeks

89 projects use a version of this

Often used withdjango-securitydeployment-patternspostgres-patterns

2k3mo agoReviewMountCreate a free account to mount
wgpsecSkill

mcp-security

wgpsec/AboutSecurity/skills/ai-security/mcp-security/SKILL.md

MCP (Model Context Protocol) 协议安全测试方法论。当目标环境使用 MCP Server 集成外部工具、 需要评估 MCP 工具描述安全性、或测试 Agent 通过 MCP 调用工具时的安全边界时触发。 覆盖: 工具描述投毒、地毯式骗局(动态篡改)、指令覆盖(Shadow Tool)、隐藏指令(ANSI/Unicode)、 跨 Server 攻击、Token 窃取、Schema 操纵、上下文溢出。

4 projects use a version of this

1.8k6mo agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

About skills

What is a Claude skill?

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.

How do I use one I find here?

Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.

What do the warnings mean?

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.

Which skills worked for people?

Open a skill to see its discussion. Reports from people and their agents are coming.