Security

borghei Bundle

Aufbau und Prüfung des Schwachstellenmanagements nach Anhang I Teil II VO (EU) 2024/2847 – Politik zur koordinierten Schwachstellenoffenlegung (CVD-Policy), Kontaktstelle und Eingangskanäle für Meldungen, Triage und Bewertung, Behebung durch Sicherheitsupdates, sichere Update-Verteilung mit Signatur, öffentliche Offenlegung behobener Schwachstellen und Security Advisories, Koordinierung mit CSIRT, BSI und CVE-Vergabe sowie die Schnittstellen zur Meldepflicht nach Art. 14 CRA, zu NIS2 und zur reformierten Produkthaftung ab dem 09.12.2026. Use when ein Hersteller eine CVD-Policy einführen, seinen Schwachstellenprozess CRA-fest machen oder eine eingehende Schwachstellenmeldung eines Sicherheitsforschers rechtlich und prozessual behandeln muss.

okhp3 Skill

Designs how a system knows who someone is and what they may do — login, sessions, tokens, roles, and permission checks. Use this whenever the user is building login or signup, adding roles or permissions, choosing between sessions and JWTs, integrating OAuth or SSO, or asking how to protect an endpoint. For finding authorization bugs in code that exists, use security-analysis.

okhp3 Skill

Reviews a change — a diff, a PR, a branch, or uncommitted work — for correctness, risk, and maintainability, and reports findings ranked by severity. Use this whenever the user asks you to review, check over, or give feedback on code they or someone else wrote, mentions a pull request, or says a change is "ready", even if they only ask "does this look ok?". For examining a whole codebase rather than a change, use code-analysis; for vulnerabilities specifically, use security-analysis.

okhp3 Skill

Works out what could go wrong in a system's design before it is built — who would attack it, how, and which defences are worth having. Use this whenever the user is designing a system that handles sensitive data, money, or authentication, asks what the security risks are, mentions threat modeling or STRIDE, or is starting a feature with a meaningful attack surface. This is design-time and systematic; for finding vulnerabilities in code that exists, use security-analysis.

okhp3 Skill

Assesses what a project depends on — known vulnerabilities, licence obligations, abandoned packages, and supply chain risk. Use this whenever the user asks what their dependencies look like, mentions a CVE or security advisory, needs a licence review, is evaluating whether to adopt a library, or has a dependency tree nobody has looked at in years. For performing the upgrades this identifies, use dependency-upgrade.

okhp3 Skill

Reviews code or a change for exploitable vulnerabilities — injection, auth and access-control gaps, secret exposure, unsafe deserialization, SSRF, path traversal, and reports them with the concrete attack path. Use this whenever the user asks about security, vulnerabilities, hardening, or a security review, and also proactively when a change touches authentication, authorization, user input handling, file paths, subprocess calls, deserialization, or credentials. For general correctness review, use code-review.

okhp3 Bundle

OverKill Hill P³ daily oracle workflow. Use when building or reviewing a stable reading that combines a tarot card, optional zodiac horoscope, and an AI message. Also activate for daily insight, affirmation, card-draw, or consistent word-of-the-day features in a client-only app. Preserve the repo's ISO cache key, deterministic fallback, graceful degradation, and direct-browser security warning; do not add a backend or proxy to this repository.

okhp3 Skill

Handles credentials safely through their whole life — where they live, how code gets them, how they rotate, and what to do when one leaks. Use this whenever the user is adding an API key, database password, token, or certificate, mentions a secrets manager or vault, asks how to store credentials, or has committed a secret to git. For finding exposed secrets during a code review, use security-analysis.

okhp3 Bundle

Produce evidence-led technical documentation for an undocumented application, including architecture, operations, code tours, data dictionaries, and security findings. Expose uncertainty instead of smoothing it over.

okhp3 Bundle

Conduct an authorized, evidence-led security review of an undocumented web application for an assessor or remediation baseline. Keep security review distinct from penetration testing.

marielynneblock Bundle

Use when investigating Dynatrace incidents, validating releases, writing DQL, triaging security findings, or operating Dynatrace with dtctl.

event4u-app Skill

Use to audit a past architectural decision — did the chosen option hold up, what assumptions drifted, should the ADR be superseded? Backward review only; does not lock new choices.

event4u-app Bundle

Use when adding auth, webhooks, uploads, queues, secrets, tenant boundaries, or public endpoints — produces trust boundaries + abuse cases mapped to files, BEFORE implementation.

event4u-app Skill

Single-pass tech-stack detection with an agents/evidence/analysis/ write-up; explicit request only. Deep multi-pass audit → universal-project-analysis. Raw primitives → project-analysis-core.

event4u-app Bundle

Use when hardening a Linux host you operate — SSH posture, a default-deny firewall baseline, and unattended security upgrades, each verified on the box rather than assumed from a config file.

event4u-app Skill

Writes Symfony PHP — DI container, bundles, Doctrine, Messenger, Security voters, console commands. For Laravel / Eloquent / Artisan use `laravel`. For framework-free PHP use `php-coder`.

event4u-app Bundle

Use BEFORE writing or editing any non-trivial UI — inventories components, design tokens, shadcn primitives, and reusable patterns into state.ui_audit. Hard gate for fe-design.

event4u-app Skill

Use when designing customer onboarding — time-to-first-value, milestone design, friction audit, drop-off diagnosis. Triggers on 'fix onboarding', 'why do new accounts churn fast'.

event4u-app Skill

Use when polishing a skill/rule/command/guideline frontmatter description — pushier phrasing, trigger coverage, undertrigger audit — even if the user just says 'make this pushier'.

event4u-app Skill

Use when shaping an engineering hiring loop — stages, take-home vs live, calibration, bar-raiser, signal-vs-noise audit. Triggers on 'design our interview loop', 'audit our hiring bar'.

event4u-app Skill

Performance audit — bottleneck profiling, N+1 query detection, hot-path analysis; explicit request only, not part of regular feature work.

event4u-app Skill

Use when a diff may introduce security risk — authZ, injection, secrets, unsafe deserialization, SSRF, XSS, mass assignment — dispatched by /review-changes, /do-and-judge, /judge.

event4u-app Bundle

Run the offline (jscpd) and online (scanoss-py) similarity scanners on demand against a diff or path — the ONLY home of this repo's detection capability; no CI gate exists or ever ran it automatically

event4u-app Skill

Use for deep Symfony project analysis: kernel/bootstrap, container wiring, routing/request flow, Doctrine, security, Messenger, and Symfony-specific failure patterns.

event4u-app Skill

Deep multi-pass codebase audit — orchestrates project-analysis-core plus the framework-specific project-analysis-*; explicit request only. Single-pass scan → project-analyzer.

xjli360 Bundle

Audit Amazon Sponsored Products structure by objective, targeting, search-term evidence, placement, and unit economics. Use when an account has tangled campaigns, unclear keyword migration, rising ACoS, or no defensible optimization order.

xjli360 Bundle

Audit Amazon product images against current marketplace and category requirements, submission status, mobile readability, and factual accuracy. Use when images are rejected, replaced, suppressed, or due for a pre-publication compliance review.

xjli360 Bundle

Audit and migrate Amazon parent-child variation themes against the current product template without breaking valid families. Use when a theme is deprecated, an update returns an invalid-value error, or catalog maintenance may split a family.

xjli360 Bundle

Run an eight-gate Amazon product selection audit covering discoverability, operating difficulty, economics, differentiation, timing, seasonality, compliance, and inventory. Use when a candidate needs a complete pre-purchase decision review.

xjli360 Bundle

Audit Amazon environmental and sustainability claims against product-level certificates, scope, validity, current program eligibility, listing content, packaging, and ads. Use before claiming eco benefits or seeking a sustainability badge.

xjli360 Bundle

Audit an Amazon AI-generated product summary or audio highlight against verified listing fields, specifications, reviews, and buyer questions. Use to find missing or misleading facts without claiming control over ranking or generation.

swan-gtm Skill

Use this skill when an AI-visibility score needs to be trusted, explained, or challenged — "why did our AEO score drop," "prove this visibility number to the client," "this scan result looks wrong." Traces any aggregate visibility or sentiment score down to the individual scans behind it, and from there to the raw AI answer text — an audit trail from headline number to evidence.

swan-gtm Bundle

Use this skill when a deal is coming up for a forecast call, a stage change, when someone asks what's actually missing on a deal, or after a new call or email that might change qualification — deal review, deal inspection, deal qualification, MEDDPICC gap check, qualification gap. Input: one or more meeting transcripts and/or email threads for the deal (required) plus, optionally, the deal's current CRM/qualification field values (for reconciliation). It maps MEDDPICC/MEDDIC signal straight out of the transcripts and emails, citing the exact line behind every mapping, then reconciles that against the CRM values if supplied — separating confirmed risks from open unknowns and weighting gaps by deal stage. Can optionally write reconciled values back to a connected CRM, but only field by field and only with the user's explicit permission — never from a live connection alone.

swan-gtm Skill

Use this skill when reps hold too much pricing authority, discounts spiral by region, or approval bottlenecks stall deals. Builds the approval matrix by discount depth and deal size, SLA-backed quote workflows, and strategic override lanes that separate noise from genuine exceptions. Produces a matrix routing small discounts to reps, large discounts to leadership and non-standard terms to the deal desk, a three-stage quote process with 24 to 48 hour SLAs, and a 30-day audit loop on exceptions. Rule: if a rep can approve a discount without understanding the margin impact, the approval matrix is too loose. Trigger phrases: discount governance, approval matrix, pricing exceptions, deals stalled in approval, margin erosion, quote SLAs.

swan-gtm Bundle

Use this skill when CRM data is unreliable, a cleanup is overdue, or a team is considering a bulk correction. Produces an evidence-backed audit, a reviewable change plan, approved corrections, and controls that prevent the same defects from returning.

swan-gtm Bundle

Use this skill when the thing being sold to strangers isn't landing, or before writing a single line of cold copy — to build a new cold-traffic offer, audit an existing one against a hard bar, or diagnose why one that reads fine gets no replies. Covers cold email, cold DM, cold ads, and cold mail: any audience with zero trust and no reason to believe you. Produces an architected offer plus a pass/fail score against eight binary criteria. Trigger phrasings: "my offer isn't converting", "low reply rate", "nobody's booking", "fix my offer", "what should I offer", "score this offer", "is this offer any good", "we changed the copy and nothing happened".