Security

linuxfoundation Bundle

Review a pull request against CDP architecture standards — fetches PR diff, verifies previous comments are addressed, validates PR metadata (title, branch, JIRA key, size), runs a code-standards enforcer against every file in `.claude/rules/` and `.claude/hooks/guard-protected-files.sh`, and drafts inline review comments with suggested fixes. NEVER auto-posts comments or submits reviews — always presents a draft in the terminal for user approval before any comment lands on the PR. Use when reviewing PRs, checking PR quality, validating code changes, or when the user says "review", "check this PR", or "audit code".

bozonet Skill

Monthly npm audit triage for monorepos without Dependabot — bucket critical patches, open thin safe PRs, and optionally create a short Linear In Review ticket. Use when the user asks for dependency triage, npm audit, security package updates, or safe backend dependency patches.

shas9 Skill

Work through a batch of pasted issues, code-review comments, bug reports, or audit findings one at a time — triaging by severity, validating each against the current code, confirming with the user before implementing, verifying, and committing in small chunks. Use this whenever the user pastes multiple issues, review comments, a QA list, or a findings dump and wants them addressed, fixed, or worked through — even if they don't say "one at a time" or name a process. Also use when the user says things like "address these review comments", "here are the bugs, fix them", "let's go through these issues", or asks to plan and fix a group of problems together.

soden46 Skill

Review or implement application security controls using framework-agnostic engineering principles, then adapt them to the detected project stack.

levi0527 Skill

Audit robotics/RL experiment results for validity, causal claims, contracts, and whether the next GPU budget is justified. Use when reviewing logs, checkpoints, reports, or experiment plans.

grimoire-rs Bundle

Initialize or reconfigure a project for the hex swarm - audits project context (CLAUDE.md/AGENTS.md) for the knowledge the orchestrators need (how to verify, spec/plan conventions), provisions what is missing into project context, optionally seeds default templates, and bootstraps the AI-maintained swarm memory at .agents/memory/hex.md (cached pointers, orchestration preferences, perspectives of interest). Re-entrant - run again anytime to re-audit pointers or change the setup.

fcakyon Skill

Audit, diagnose, or optimize website loading and interaction performance, Core Web Vitals, and Lighthouse performance scores.

dougfsantos2026 Skill

Review code changes with Security Review subagent.

magerko Bundle

Пред-запусковый аудит безопасности приложения — секреты и ключи, аутентификация и сессии, доступ к чужим данным (IDOR, RLS), инъекции и XSS, загрузка файлов, заголовки и CORS, лимиты и расходы, утечки в ответах и логах, зависимости, прод-гигиена, вебхуки и платежи. Выдаёт отчёт с приоритетами; код не правит. Только ручной запуск.

snausage0x45 Bundle

Run an open-source intelligence (OSINT) investigation on a single IP address or domain and return a security analyst's briefing: a risk verdict, a short technical summary, and a facts table. Weighs ownership provenance heavily — registration age, recent registrar or registrant changes, and registrar reputation. Use this whenever the user types "netcheck" followed by an IP or domain, and also whenever they ask you to "investigate", "look up", "check the reputation of", "profile", "run OSINT on", "who owns", "who is behind", or "is this safe" for any IP address, domain, hostname, or URL — even if they don't say the word "netcheck". Trigger on indicators like 8.8.8.8, 185.220.101.1, evil-domain.com, or a pasted URL. This is passive, defensive reconnaissance only.

tetratheta Skill

Generic, high-signal code review skill for any project: prioritizes security, correctness, regressions, performance, maintainability, and test gaps; reasons in English for analysis quality and delivers final review feedback in Korean.

willayam Skill

Helps review code for best practices, bugs, and security issues

caohaotiantian Bundle

TEST FIXTURE — intentionally contains security anti-patterns to verify the evaluation scanner detects them. NOT a real skill.

carlymr Skill

Comprehensive code review using 7 parallel specialized sub-agents (correctness, security, performance, simplicity, UX, codebase integration, documentation). Synthesizes findings into a prioritized report with de-duplication and false positive filtering. Use when reviewing code changes, pull requests, or local diffs. Supports local git diff (no arguments) or GitHub PR (pass PR number or URL as argument).

jiayaoqijia Skill

Run a security scan on the codebase using available scanners. Returns structured findings with severity and OWASP mapping.

jiayaoqijia Skill

Reviews code changes for bugs, security issues, and quality problems

elder-plinius Skill

Audit one pull request in a BT6 research or support repository at an exact head SHA, covering correctness, research integrity, security, tests, contracts, and merge readiness.

elder-plinius Skill

Audit the full pull-request and issue queue of a BT6 research or support repository, classifying readiness, evidence risk, and next action without mutating tracker state.

hoetaek Bundle

Use after ready has handed off an approved launch target (launch command, inspect target, workflow policy, TaskDocument bodies), when the user wants the rest of the wt lifecycle — launch, coordinate, review, land, retrospect — to proceed automatically with automatic reviews, hard stops, and evidence. Trigger on "$autopilot", "wt autopilot", "launch target approved, run the rest automatically", or "after ready, carry it the rest of the way". Do not use before the ready handoff, for unclear or unprepared work (route to ready), or for destructive / external / credential / cost / security / privacy-sensitive actions without explicit pre-authorization.

majiayu000 Bundle

Create, audit, and harden skills so they become self-maintaining instead of cat-and-mouse. Use when designing new skills, reviewing existing ones for drift, or turning brittle workflows into reliable ones. Forces Negative Examples, Verification Checkpoints, machine-checkable Done conditions, Replay/smoke test hooks, and Drift signal detection. Do not use for one-off prompts.

matteocervelli Bundle

Validate code quality, test coverage, performance, and security. Use when verifying implemented features meet all standards and requirements before marking complete.

superchileno Skill

Hunting skill for xss vulnerabilities. Built from 174 public bug bounty reports. Use when hunting xss on any target.

posthog Skill

Use when adding or editing a GitHub Actions workflow, composite action, or reusable workflow under `.github/` — new CI jobs, triggers, matrices, checkout/clone tuning, action pinning, GitHub App token auth, concurrency groups, `timeout-minutes`, `paths` filters, caching, or runner choice. Covers PostHog's workflow-authoring conventions and the reasons behind them: the 500-runs/10s dispatch cap, shallow vs full clone, per-SHA push concurrency, dedicated App-token rate-limit buckets, and fork-safe secrets on a public repo. Points to the linters (`bin/hogli lint:workflows`, actionlint) that enforce the mechanical rules, and to the narrower skills for production deploys, secrets, and Depot runners. Not for debugging red CI (use debugging-ci-failures) or wiring a new secret end to end (use managing-github-actions-secrets).

autogio Bundle

Perform a comprehensive, evidence-based, read-only audit of a software repository. Use when assessing architecture, security, correctness, reliability, dependencies, tests, documentation, macOS integration, shell scripts, or repository hygiene.

autogio Bundle

Perform a comprehensive, read-only macOS health assessment covering hardware, storage, memory, processes, services, networking, security posture, Apple Silicon compatibility, Homebrew, LaunchAgents, LaunchDaemons, logs, and operational risks.

hemanth Bundle

Structured code review workflow and security checks

leogregianin Bundle

Best practices and conventions for Django projects. Use when writing or reviewing Django code — models, views, ORM, forms, security, migrations, and testing.

naren-m Skill

Audit and improve project rule files (.cursorrules, .cursor/rules/) with quality reports and targeted updates.

nonatofabio Bundle

Rewrite drafts so a person appears to have written them - cut filler, force claims that commit, break the machine cadence, then run a mechanical audit for AI tells. Use whenever the user asks to humanize, de-slop, or make text sound less like AI; whenever they say a draft reads robotic, generic, corporate, or like ChatGPT wrote it; and before delivering any blog post, essay, email, README, launch note, or docs page the user will publish under their own name. Also use when the user asks for an AI-tell audit of text they already have.

redamancy231-create Bundle

[决策:预注册] Pre-registration audit for new research directions, quant strategies, or thesis topics: falsifiable hypothesis, prior-art check, strongest counter-argument, death criteria before results, cheapest falsification with strong baseline, three-state verdict (GO/STOP/REDESIGN). Use before committing resources to a new direction. Not for bug fixes, experiment reproduction, or routine controlled experiments.

ryanwaite Skill

Produce a technically deep, readable assessment that helps an approver understand a pull request before approving it. Use when the user asks for an approver review, a detailed PR assessment, help understanding a PR, or an approval recommendation. Compare the PR's stated intent with the code, trace data and control flow, examine architecture, contracts, failure handling, lifecycle, security, operations, tests, compatibility, and rollback, then explain important implementation decisions and credible alternatives for a technical generalist.

manu14357 Skill

Analyze cryptographic code to detect operations that leak secret data through execution timing variations.

webmaxru Bundle

Authors, reviews, installs, and debugs GitHub Agentic Workflows in repositories, including workflow markdown, frontmatter, gh aw compile and run flows, safe outputs, security guardrails, and operational patterns. Use when creating or maintaining GH-AW automation. Don't use for standard deterministic GitHub Actions YAML, generic CI pipelines, or non-GitHub automation systems.

ukgovernmentbeis Bundle

Retrieve a secret code by reading a bundled asset file and executing a companion script. Use when the user asks to reveal, decode, or look up the secret code from this skill's assets.

pluginagentmarketplace Bundle

Secure backend applications against OWASP threats. Implement authentication, encryption, scanning, compliance, and incident response procedures.

starkyru Bundle

Clones a skill into this repo and security-audits it before integration. Source can be an existing skill in skills/ (duplicate under a new name), a local directory, or a git URL. Can also run the audit standalone. Use when the user says "/clone-skill", "clone skill <x>", "import/copy a skill from <path or repo>", or "audit skill <x>".