Security

casualsecurityinc Bundle

Steganography detection and extraction for images (LSB, PNG chunks, JPEG DCT, EXIF, palette), audio (spectrogram, DTMF, WAV LSB), files (polyglots, binwalk, ADS), and text (whitespace, zero-width Unicode, homoglyphs). Use when analyzing suspicious files for hidden data in CTF challenges, digital forensics, or security research.

dasein108 Bundle

Perform deep due diligence and risk scoring for any crypto project using the CPD framework (Chain, Protocol, Dapp), sometimes referred to as CDP in user requests, plus stage, age, code quality, and incident history. Use when the user asks to evaluate crypto project reliability, compare projects by security/risk posture, produce an evidence-backed CPD report, or calculate CPD percentage/tier from sourced findings.

deepsourcecorp Skill

Retrieve code review results from DeepSource — issues, vulnerabilities, report cards, and analysis runs. Use when asked about code quality, security findings, dependency CVEs, coverage metrics, or analysis status.

deepsourcecorp Bundle

Scan code for security vulnerabilities, leaked secrets, and dependency issues using the Sentinel API (sentinel.deepsource.com), and auto-fix detected issues. Use this skill when asked to: (1) Scan or analyze a repository or code for security issues, secrets, or vulnerabilities using Sentinel, (2) Upload/sync a local git repository to Sentinel for analysis, (3) Run Sentinel on code changes, pull requests, or patches, (4) Apply auto-fixes from Sentinel analysis results. Requires a Sentinel API key (environment variable SENTINEL_API_KEY).

devrimcavusoglu Skill

Use when reviewing code changes for correctness, style, performance, and security.

giljr Bundle

Complete guide to installing, configuring, and running bundler-audit in Ruby/Rails projects. Use this skill whenever the user mentions bundler-audit, gem auditing, vulnerabilities in Ruby gems, dependency CVEs, secure gem updates, or wants to ensure security in a Rails project's dependencies. Also trigger for bundler-audit result analysis, CVE/GHSA interpretation, and safe production update strategies.

gosprinto Bundle

Autonomous GDPR compliance auditor that scans a codebase to identify PII collection, storage, and sharing, then produces an article-by-article gap analysis, a pre-filled Data Processing Agreement (DPA), and a ROPA (Record of Processing Activities) starter kit — all exported as downloadable files (.docx recommended). Use this skill whenever the user mentions GDPR, data privacy audit, DPA, ROPA, EU compliance, PII scan, data protection, ICO, CNIL, or asks whether their codebase or product is compliant with data protection law. Trigger even for casual phrasings like "are we GDPR compliant?", "I need to check our data privacy", or "help me get audit-ready." The skill runs autonomously — it reads the codebase, researches third-party processors, and produces final deliverables without the user needing to provide structured input.

gogs Skill

Analyze and help fix a GitHub Security Advisory (GHSA) in this repository. Use when the user types `/ghsa <id>` or asks to triage, verify, or patch a reported GHSA.

hamen Bundle

Audit Android Jetpack Compose repositories for performance, animation phase correctness, state management, side effects, composable API quality, and adjacent Android launch UX resource risks such as blurry Android 12+ splash icons. Scans source code, scores each category from 0-10, writes a strict markdown report, and summarizes the most important fixes. Use when reviewing a Compose codebase, rating repository quality, inspecting recomposition/state issues, animation issues, or running a Compose audit.

harumiweb Bundle

Unified ADR workflow for any repository. Use when Codex needs to determine whether a change needs an Architecture Decision Record, draft a new ADR or propose an update, lint or review an ADR draft, audit ADRs against docs/specs/tests/src for drift, or refresh ADR index artifacts in repositories that already define ADR indexing conventions. Trigger on requests about ADRs, architecture decisions, design rationale, issue/PR/diff policy changes, ADR review, ADR audits, or ADR index maintenance.

linkml Skill

Audit LinkML generators for conformance to the project's architecture, conventions, and design ethos (how a generator is built, not whether its output is correct). Use when reviewing a generator PR, before handing a generator to a contributor, or to survey which generators have drifted from the SchemaView / common-machinery conventions. Optionally scope to one generator by name (e.g. jsonschema); omit to survey all.

lisa-tarbo Skill

Run a dependency audit for this project's plain requirements.txt (Python, no pip-tools, no JS). Produces report, applies safe bumps, emits Jira-ready ticket list for risky items. Use on demand or for periodic maintenance.

lynx-family Skill

Audit and optimize frontmatter `description` fields across documentation pages to keep them concise and token-efficient. Use this skill when the user wants to add missing descriptions, trim verbose ones, enforce a token budget on page descriptions, or ensure every doc page has a proper frontmatter description. Also trigger when the user mentions 'description is too long', 'add description frontmatter', 'optimize page descriptions', 'llms.txt is too big', or 'descriptions are eating too many tokens'.

maester365 Skill

Write, validate, and document Maester security checks for Microsoft 365 tenants. Use when asked to create, edit, review, or debug a Maester Pester test file, its companion markdown documentation, or its tagging. Covers Graph API data retrieval, Add-MtTestResultDetail formatting, the tagging taxonomy (CIS, CISA, EIDSCA, ORCA, MT), helper function patterns, remediation guidance, Entra ID, Exchange, SharePoint, Teams, Defender, Conditional Access, and the validation checklist for new checks.

magallon Bundle

Performs a comprehensive 3-phase refactoring audit on any web project, analyzing structure, code quality, and security. Produces a consolidated diagnostic report with severity-rated findings. Use this skill when the user asks to audit a codebase for refactoring opportunities, evaluate technical debt, review code quality, find dead code, detect security issues in server-side logic, or assess overall project health. Triggers on phrases like "audit my code", "find technical debt", "code review the project", "what needs refactoring", "analyze code quality", "find dead code", "check for security issues", or any request to systematically evaluate a codebase before refactoring. This is a read-only diagnostic — it does not modify any files.

magallon Bundle

Generates a prioritized refactoring plan from audit findings and executes code changes incrementally with user confirmation. Use this skill when the user has a refactoring audit report (from refactoring-audit or any structured findings document) and wants to act on it. Also triggers when the user says "execute the refactoring plan", "fix the audit findings", "refactor based on the report", "apply the refactoring recommendations", "start fixing the issues from the audit", or any request to systematically apply code improvements based on a diagnostic report. This skill modifies files — it always presents a plan and waits for explicit user approval before making any changes.

iwamot Bundle

Detect Renovate Dependency Dashboard coverage gaps in a git repo. Cross-references version-like strings in Renovate-managed files (`.github/workflows/*.{yml,yaml}`, `Dockerfile*`, `compose*.{yml,yaml}`, `mise.toml`, `package.json`, `*.tf`, `go.mod`, `pyproject.toml`, `requirements*.txt`, etc.) against the open "Dependency Dashboard" issue's "Detected Dependencies" listing, and reports lines whose dependency is not tracked by Renovate. Use when the user asks to audit Renovate detection coverage or find dependencies that Renovate is not tracking.

jakubrohleder Bundle

Analyze a pull request against origin/main for high-leverage logic simplifications, deeper PR-anchored refactors, clearer module ownership, and interfaces that prevent misuse. Use only when explicitly invoked to generate and adversarially test refactoring hypotheses; do not use for generic code review, correctness, style, lint, security, test coverage, or repository-wide cleanup.

jezweb Skill

Audit a domain's DNS records — MX, SPF, DKIM, DMARC, CAA, A/AAAA — for correctness and best-practice. Use when onboarding a new domain or when an email-deliverability or SSL issue surfaces.

jiadizhunine Bundle

Use when the user asks to humanize text, remove AI tone, make writing sound less robotic, match a writing sample, polish prose without sounding corporate, audit AI-like writing patterns, or improve Chinese/English academic writing while preserving meaning, evidence, citations, and intended voice.

jihe520 Skill

Perform thorough code reviews with security, performance, and maintainability analysis. Use when user asks to review code, check for bugs, or audit a codebase.

jihonghe68 Skill

Skill 提示词质量审查工具。当用户想检查、评估或改进任何 SKILL.md 文件的提示词质量时， 立即使用本 skill。触发关键词包括：审查 skill、检查提示词、skill 质量、SKILL.md 评估、 提示词有没有问题、帮我看这个 skill、skill auditor、audit skill、优化 skill 提示词、 全库扫描、扫描所有 skill。 即使用户只是说「帮我看这个 skill 好不好」也必须触发本 skill。 本 skill 输出结构化质量报告，自动修复可修复问题，并生成「待人工确认」清单。

fireheartjerry Bundle

Run a criteria-driven adversarial improvement loop: interview the user into a weighted, numerically scoreable criteria document, then repeatedly (1) have a hostile independent reviewer audit the work, (2) triage its findings into actionable changes, (3) execute them, and (4) have an independent scorer measure real progress against the criteria. Use this whenever the user wants something made *better* rather than made. The test is not the wording — it is whether two competent people could disagree about whether the work is finished; if yes, use this even when the request is short, scoped to a single file, or phrased without any of the words below. Typical phrasings: "improve this", "polish this", "take it to the next level", "make this world class", "audit and fix it", "iterate on this", "this is good but…", "keep going until it's great", "run N rounds on this" — across designs, landing pages, UI, codebases, architecture, docs, copy, or any artifact where quality is open-ended and there is no single correct an

fossbilling Skill

Design, implement, test, and ship the actual code fix for a security advisory that has already been verified as real (typically by security-advisory-triage) against this repo. Use this whenever the user asks to fix, patch, remediate, harden, or "build a comprehensive fix for" a confirmed vulnerability or GHSA, or says something like "now let's fix it" right after a triage/verification step. Don't wait for the user to ask for "the process" by name; if a vulnerability is confirmed and they want it shipped, this skill is almost certainly what they want. Companion to security-advisory-triage, which verifies and writes up the advisory; this one builds and ships the fix.

fossbilling Bundle

Verify a reported GitHub Security Advisory (GHSA) against this repo's actual current code, then refine its title/description/CVSS/CWE metadata into this project's house style and apply it to the live advisory. Use this whenever the user gives you a GHSA ID, a security advisory number, a security report to "check", "verify", "triage", or "confirm", or asks whether a vulnerability report is valid/real/still exploitable on main. Also use it when the user wants an advisory's writeup improved, its CVSS score computed or recalculated, its CWEs corrected, or its title/description brought in line with how this repo normally publishes advisories, even if they only ask for one of those pieces (e.g. "recompute the CVSS for GHSA-xxxx") rather than the full workflow. Don't wait for the user to ask for "the process" by name; if they hand you a GHSA id or a raw vulnerability report against this codebase, this skill is almost certainly what they want.

mishoko Bundle

Security audit of Solidity code while you develop. Trigger on "audit", "check this contract", "review for security". Modes - default (full repo) or a specific filename.

mishoko Bundle

Use when auditing Solidity contracts for security vulnerabilities. Trigger on "audit", "check this contract", "review for security", or "/contract-auditor".

misonl Skill

Inspect a given commit's web/classic changes and sync all features/fixes to web/default. Use when the user provides a commit ID and wants to audit whether web/default already has the same features as web/classic, port missing features, improve suboptimal implementations, fix bugs, and remove redundant code. Trigger phrases include: "/classic-to-default-sync <hash>", "classic-to-default-sync <hash>", "sync classic to default", "port from classic", "compare classic commit", "classic 和 default 对比", "把这次 classic 的修改同步到 default", "查看这次提交 classic 中的修改并同步", or any request supplying a commit hash together with classic/default comparison intent.

mohui373 Bundle

For all readers, with a specialty in experimental and behavioral research: reconstruct, replicate, adapt, and extend paper-grounded studies / 面向所有读者、专长是实验与行为研究：根据论文重组、复现、改造并发展研究。Use when a user asks in English or Chinese to reconstruct, reproduce, implement, program, audit, adapt, or extend an experiment, survey, longitudinal study, interactive task, organizational or field protocol; produce platform-tailored reports or migrate E-Prime, PsychoPy, MATLAB/Psychtoolbox, jsPsych, Qualtrics/SoSci, oTree, Inquisit, Gorilla, or another platform; define materials, event logs, wave plans, data dictionaries, and analysis contracts for R, Python, SPSS, Mplus, MATLAB, Stata, SAS, JASP/Jamovi, or other tools；中文触发包括平台适配报告、论文重组复现、复现实验、问卷或纵向流程重建、研究创新、搭实验、写程序、被试流程、材料重建、平台迁移、数据字典与统计复现。

msrbuilds Bundle

Develop WordPress plugins following official WordPress coding standards, security best practices, and WordPress.org directory guidelines. Use this skill whenever the user wants to create, scaffold, or develop a WordPress plugin — including standard plugins (settings pages, CPTs, shortcodes), WooCommerce extensions, Gutenberg block plugins, or REST API / headless plugins. Also trigger when the user mentions "WordPress plugin", "WP plugin", asks to build a feature as a plugin, wants to add admin pages, register custom post types, create blocks, build WooCommerce add-ons, or extend WordPress in any way via plugin architecture. Even if the user just says "build me a plugin for X", use this skill.

mturac Skill

Rates any SKILL.md on a 0-100 scale across 10 dimensions with a SHIP / REWORK / SCRAP verdict. Evaluates trigger precision, instruction clarity, output predictability, edge case coverage, anti-hallucination guardrails, developer experience, composability, open-source readiness, wow factor, and real-world utility. No flattery — calibrated against Anthropic's own skill-creator rubric. Use this skill whenever someone says "score this skill", "rate my skill", "is this skill good", "skill review", "skill audit", "roast my SKILL.md", "grade this", "will this skill work", "evaluate my skill", "how good is this", or pastes a SKILL.md and asks for feedback. Also trigger when comparing two skills, benchmarking a skill collection, or asking "what's wrong with this skill" — even without the word "score".

mxschmitt Bundle

Audits all existing entries in the awesome-playwright README for staleness, broken links, abandoned projects, or superseded tools. Recommends removals with evidence. Use when user says "audit entries", "audit list", "clean up list", "check existing entries", or "prune list".

nebutra Skill

Audit codebase to identify reinvented wheels, suggest unicorn-grade library replacements, scan vulnerabilities, and auto-create migration plans. Use when analyzing technical debt, reviewing hand-rolled code, planning library migrations, or auditing project structure.

newdee Bundle

Lamarckian skill evolution - continuously monitors every real skill invocation, drives governed evolution of observed skills, and evolves itself by the same rules while running. Harness-agnostic (adapters for Claude Code, Codex, Cursor, pi share one ledger); in the reference adapter a PostToolUse hook logs each invocation (stamped with the skill's genome hash for per-version regression windows) and a Stop hook runs a light evaluation loop injected at turn end (this SKILL.md is not reloaded per turn). Per-skill dynamic rubrics (git-versioned) define what "good" means per skill; a trust ladder in config.json controls which skills may be edited (auto/evolve/suggest/observe, default observe). Read this file only when escalating (enough same-type evidence for an edit) or on manual invocation. Use when the stop hook says to escalate, or when asked to review skill performance, optimize or improve a skill, audit the skill ledger, distill skill learnings, manage the evolution whitelist, or switch trigger mode.

opencoredev Skill

Use when adding, reviewing, or documenting Email SDK integrations in TypeScript/Bun apps. Dynamically refreshes the current Email SDK docs/source before implementation, then covers adapter selection, fallbacks, CLI smoke tests, hooks, and secret-safe observability.

owasp Skill

Write code that stays defensible as threats and requirements change. Use for any application code - features, endpoints, input handling, data access, auth, error handling, state, concurrency - even when security is not explicitly requested.