Security

vxcozy Skill

Master orchestrator for the 5-step productivity system. Runs the full audit-architect-analyst-refinery-compounder loop or individual steps. Use when: (1) "run the full loop", "start the system", "architect system", (2) "run step N", "run audit", "run architect", (3) "what step am I on?", "system status", "where am I in the loop?", (4) "continue", "resume", "next step". Manages state, sequencing, and skill chaining across all 5 steps.

xclouddev Bundle

Manage xCloud servers — list/inspect servers, monitoring, services, tasks, reboot, snapshots, sudo users, PHP versions, databases & database users, server cron jobs, firewall rules, fail2ban, and provisioning new sites onto a server (WordPress or Git-deployed PHP/Node apps). Use for any server-level infrastructure or server security (firewall/fail2ban) request. NOT site-level config (see xcloud:sites), NOT SSL certs (see xcloud:ssl), NOT WordPress app management (see xcloud:wordpress).

mnemon-dev Bundle

Use persistent memory when prior preferences, decisions, constraints, or project history could affect a task, or when durable non-secret knowledge should be preserved.

gkrtjd99 Skill

Audit a local project for privacy leaks, secrets, personal paths, tokens, API keys, and data that should not be committed. Use when checking whether a repository exposes sensitive information, credentials, private paths, or commit-unsafe data.

haksolot Skill

Audit the decisions in .ank/ against the current code and report what no longer holds. Use when asked whether ADRs, specs, or tasks are still accurate, after a milestone, or when the corpus and the code seem to disagree.

noteflowai Skill

Attach an existing internal audit cache to a public report.

noteflowai Skill

Stage report inputs in an internal audit cache for later review.

noteflowai Skill

Submit an existing report cache to the synthetic audit service.

poteto Bundle

Audit and evolve the brain vault — prune outdated content, discover cross-cutting principles, review skills for structural encoding opportunities. Triggers: "meditate", "audit the brain".

dragoon0x Skill

The small words that shape big experiences. Button labels, tooltips, confirmations, placeholders, and the 3-word strings that determine whether a product feels polished or half-finished. Use during any copy audit pass.

jeremylongworth-source Bundle

Create and maintain executive risk registers and opportunity registers. Use when Codex is asked to identify strategic, operating, financial, customer, product, people, legal, security, delivery, or reputation risks; prioritize risks; define mitigations; or prepare leadership risk review artifacts.

zhaoxuya520 Bundle

供应链安全时使用。适用于依赖漏洞扫描 / 镜像安全 / CI 投毒防护 / SBOM。融合 SLSA + Sigstore + Snyk + Trivy。

tuyv Bundle

Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice profile (casual / professional / technical / warm / blunt), and an iterate-to-convergence pass.

etolucy Bundle

Audit, rename, and polish a GitHub repository across its local checkout and remote settings. Use when Codex needs to synchronize a local and GitHub repository name, set the description, homepage URL, or topics, create repository branding and a GitHub social preview, restructure a README, or prepare and publish a cohesive repository identity. Uses GitHub CLI for supported remote operations and delegates visual identity work to $create-context-aware-logos.

ivanwng97 Skill

Run pixtuoid's review protocol at either scope — the mandatory pre-merge DIFF gate (2+ differentiated-lens agents on the diff) or a whole-codebase AUDIT (subsystem × factor fan-out over the whole tree). Both draw ONE shared factor taxonomy + verify contract + disposition; they differ only in population and orchestration. Use before merging ANY PR, on 'review this PR/branch' / 'is this ready to merge' (diff scope), or on 'whole-codebase review' / pre-release / periodic audit (whole-codebase scope). Encodes the convergence contract (churn budget, two-fix-round cap, HIGH-only blocking), the five hard requirements, the escalation triggers, the adversarial finder→verify fan-out, and the disposition sweep the repo learned the hard way.

jwhiteux Bundle

Multi-persona deliberation framework for high-stakes decisions. Five specialized personas independently analyze a dilemma, blind-review each other's reasoning, and a Chairman synthesizes a single verdict. Use this skill whenever the user says 'council this', 'run the council on...', 'pressure-test this', 'war room this', 'stress-test this decision', 'red-team this', or asks for adversarial review of a choice. Also trigger when the user is weighing a high-cost, hard-to-reverse decision — architecture and tech selection, security tradeoffs, business pivots, pricing, hiring, major commitments — and would benefit from deliberately breaking their own assumptions before committing. When in doubt on a consequential or expensive decision, convene the council.

quantclaw Skill

System health audit and diagnostics

wayne2wang Bundle

Audit near-final computer vision and robotics conference papers for mathematical and notation correctness, high-confidence writing and formatting errors, reviewer-facing risks, current venue compliance, and exhaustive bibliography integrity. Use for submission PDFs or LaTeX projects before submission, revision, or rebuttal; do not use to draft a paper from scratch or migrate it to another template.

jmagly Bundle

AUTO-INVOKE when user mentions cryptography, AEAD, KDF, chain of trust, signing key, auth factor, MFA, secret hygiene, supply chain trust, physical threat. Security-engineering quick reference — decision domains for crypto primitives, chain-of-trust, auth factors, degraded modes, supply-chain trust, physical-threat modeling.

managedcode Bundle

Quick pragmatic detection-focused review of .NET test code for anti-patterns that undermine reliability and diagnostic value. Use when asked to audit test quality, investigate flaky or coupled tests, find duplication or magic values, or when tests pass but don't actually verify anything. Best for identifying and prioritizing issues in existing tests with severity-ranked findings and targeted remediation guidance. Catches assertion gaps, swallowed exceptions, always-true assertions, flakiness indicators, test coupling, over-mocking, naming issues, magic values, duplicate tests, and structural problems. Do NOT use for direct MSTest API rewrites or implementation-only fixes (for example swapped Assert.AreEqual argument order or converting `DynamicData` from `IEnumerable<object[]>` to `ValueTuple`) — use writing-mstest-tests instead. For a deep formal audit based on academic test smell taxonomy, use exp-test-smell-detection instead. Works with MSTest, xUnit, NUnit, and TUnit.

florian101010 Skill

Use when performing a quality audit, security review, or robustness check. Covers XSS/innerHTML scanning, rule compliance verification, race condition analysis, config schema validation, and documentation drift detection. Produces a severity-classified report (Critical/High/Medium/Low).

bahayonghang Bundle

Audit and improve the Claude Code context layer — CLAUDE.md guidance files, .claude/rules/ path-scoped rules, and companion code_map.md navigation maps — against Claude 5 context-engineering rules (judgement over rules, progressive disclosure, no cross-layer conflicts). Asks whether to optimize the current repository (default) or the global ~/.claude context. Use when the user asks to check, audit, optimize, rightsize, slim, or restructure CLAUDE.md or Claude context files, mentions nested CLAUDE.md, code_map.md, or context engineering, or says 优化 CLAUDE.md, 审计 CLAUDE.md, 优化上下文, 精简上下文, 生成 code_map (Claude). Not for trivial single-line edits the user has already fully specified.

mehdi-benhariz Skill

Whole-repo audit for over-engineering. Like ponytail-review, but scans the entire codebase instead of a diff: a ranked list of what to delete, simplify, or replace with stdlib/native equivalents. Use when the user says "audit this codebase", "audit for over-engineering", "what can I delete from this repo", "find bloat", "ponytail-audit", or "/ponytail-audit". One-shot report, does not apply fixes.

cyberuni Skill

Fix a PR that is failing due to security or vulnerability issues — npm/pnpm/yarn/bun audit failures, CVE alerts, Dependabot merge conflicts, Snyk failures, or GitHub security advisory blocks. Use when asked to 'fix the security PR', 'resolve the vulnerability failure', or 'unblock the Dependabot PR'.

equinor Bundle

Review dependency PRs with structured research, existing-PR-discussion capture, multi-lens analysis (security, code quality, impact), and a repeatable verdict template. USE FOR: dependency update PRs, Renovate/Dependabot PRs, library upgrade reviews, "review this dependency PR", "should we merge this update". DO NOT USE FOR: feature PRs, application code reviews, dependency automation/bot configuration, or unattended merge without confirmation.

rcarmo Skill

Project conventions with module caching, linting, security checks, and tests via Make

greenpau Bundle

Create, revise, route, validate, or audit tested repo-local skills as a progressive-disclosure engineering handbook. Use when changing AGENTS.md or .codex/skills, adding durable tested contracts, reorganizing routes, synchronizing skill UI metadata, removing placeholders, or checking reachability and routing integrity.

greenpau Bundle

Apply tested repository Go coding standards to implementation and review work. Use when creating or modifying Go packages, APIs, process execution, protocol parsing, result models, coverage logic, renderers, artifact storage, errors, security-sensitive paths, or tests in tested.

greenpau Bundle

Create, review, or revise tested repository commit messages and commit-message files. Use when summarizing a tested change for version control, selecting a subsystem indicator, validating the required subject and Before/After/Tests/More info structure, or creating a message file for a user-reviewed commit.

greenpau Bundle

Design, implement, review, or audit tested across its CLI, child-process runner, event protocol, result aggregation, coverage, reporting, and artifact-publication boundaries. Use when a change crosses packages, alters run or report lifecycle semantics, introduces a new output, or needs routing to the specialized tested implementation skills.

carlsz Skill

Verify a stored critical user journey by replaying it step by step against the running app, and report the exact step that broke as a cuj report in .ux/audits. Use for "verify my CUJs", "do the journeys still work", "journey regression check", "which step broke".

carlsz Bundle

Run an expert heuristic usability evaluation of a host app and write a severity-scored report to .ux/audits. Use for "usability audit", "heuristic evaluation", "UX audit", or "usability review".

dream-zjk Skill

Use when reviewing a pull request, a diff, or uncommitted changes for bugs, security issues, and style regressions.

frankhildebrandt Skill

Fetches open Dependabot security alerts for any GitHub repository (user-specified or from workspace remote), filters Critical and High (optionally Moderate) alerts with an available patch version, and builds a Plan-mode plan with one todo per actionable fix. Use when the user asks for a Dependabot security fix plan, vulnerability remediation plan, or points at /security/dependabot (e.g. github.com/{owner}/{repo}/security/dependabot).

itallstartedwithaidea Skill

Structured Google Ads account audit across 7 dimensions. Activate when the user asks to "audit my account", "check for problems", "find issues", "review my campaigns", or requests a comprehensive account health assessment. Delivers findings with severity ratings and prioritized action items.

jinshenganyuci Bundle

Build, migrate, audit, test, and package the `A.xiongda-onekey-start` KernelSU module and derived Android kernel-plus-driver variants. Use when Codex must create or update 熊大一键启动 or a minimal Action-plus-manual-driver module, preserve a chosen base release, implement manual or game auto-start, embed a byte-exact driver, stream root-operation logs through KernelSU WebUI, prevent post-install 0644 permission failures, diagnose a module that did not execute, or deliver a reproducible validated release.