Claude Code Skills — the Licence-Safe Directory

Stages relevant changes, writes a conventional-commit message, and pushes — in one command.

Opens a pull request with a structured description drawn from the full commit range, not just the latest commit.

Runs a complete pull request review covering security, test coverage, documentation, code quality, and performance impact in one workflow.

Senior security auditor subagent for comprehensive security assessments, compliance audits, and risk evaluations across systems, infrastructure, and processes.

Generates unit tests for a specific function or module with sensible edge cases — happy path, sad path, and 2-3 boundary cases.

Drafts a blog post, newsletter, or landing page from a brief — using the site's established voice.

Deep research subagent for Bryan Collins' content operation — gathers sources, frameworks, statistics and competitive analysis for articles, newsletters and YouTube scripts. Research only, no writing.

Applies, documents, or enforces brand guidelines — colour systems, typography, logo rules, imagery, and tone matrix — to keep marketing materials, products, and communications visually and verbally consistent.

Writes, rewrites, and improves marketing copy for homepage, landing, pricing, feature, about, and product pages — clear, compelling, action-driving copy grounded in conversion-copywriting principles.

Generates 10 headline variants against different frameworks (curiosity, benefit, controversy, listicle, how-to) and ranks them by predicted CTR and LLM-citability.

Drafts in a specific author's voice after reading 3-5 of their pieces — with attribution-safe output for transparent ghostwriting.

Analyses and rewrites tweets for maximum reach using insights from Twitter's open-source recommendation algorithm.

Audits, reviews, and diagnoses SEO issues across technical SEO, on-page SEO, and content — identifying what's blocking indexation or ranking and producing a prioritised action plan.

Scores a page for LLM-citability — direct answers, quote-ready structure, source attribution and FAQ coverage — on a 0-100 scale with specific improvement suggestions.

Generates JSON-LD schema markup for a page — Article, FAQPage, HowTo, Product, SoftwareApplication, BreadcrumbList.

Suggests contextual internal links for a page by scanning the rest of the site for topically-relevant anchors and proposing exact insertion points.

Rewrites a page's meta title and description for CTR on a specified target query — producing three variants of each with distinct angles.

Builds and deploys Vendors.ie via git push to main, which triggers Netlify's auto-deploy — no Netlify CLI used.

Checks the latest Netlify deploy for all sites (or a specific site if named) via the Netlify API and reports ready/building/error state.

Starts the Vendors.ie Astro dev server for local preview on port 4321, killing any existing Astro dev server first.

Expert Kubernetes architect for cloud-native infrastructure, GitOps workflows (ArgoCD/Flux), and enterprise container orchestration across EKS, AKS, GKE, and OKE.

Scrapes 3-5 competitor pages on the same topic, compares their stance, and identifies content gaps plus differentiation angles.

Summarises 3-5 academic papers on a single topic into a plain-English brief listing the core claim, method and limitations of each paper.

Converts DOCX, PDF, PPTX, and XLSX to high-quality markdown with automatic post-processing — fixing tables, image paths, code blocks, and CJK bold spacing that raw converters miss.

Analyses meeting transcripts and recordings to uncover behavioural patterns, communication habits, and actionable feedback on how you lead and listen.

Sweeps CTAs, URLs or brand terms across a repo under a tier-based policy — keep some, swap others, leave the rest for review.

Greps for residual outdated copy across a repo after a pivot — catching prose that escaped the CTA sweep.

Verifies a project's reference data — prices, models, dependencies — against upstream sources and flags staleness.

Automates the model lifecycle — promoting entries from current to legacy to deprecated to retired as their dates pass, and stripping references from content pages once a model is gone.

Runs a battery of drift and regression checks specific to one site — CTA routing, residual outdated prose, reference-data freshness, retired-model statuses, hub cross-linking and stray backup files under pages/.

Verifies that every page in a defined content hub links to the other pages in that hub — catches missing cross-links that break SEO topical authority and user journeys.

Creates new skills from scratch, iterates on existing ones, and runs evals to benchmark performance with variance analysis before you ship.

The canonical SKILL.md template from Anthropic's official skills repo — a folder with YAML frontmatter (name + description) plus the markdown instructions Claude follows when the skill is active.

Dry-runs a skill against a test input to verify trigger detection, output shape and side-effect safety before you ship it.

Audits a site for a legal disclaimer page and footer link, creates /legal-disclaimer and wires it in immediately after Privacy Policy when missing. Stack-agnostic across Next.js Pages Router, Astro and WordPress (WP skipped).

Checks every project dependency's licence — flags GPL contamination, commercially-incompatible licences and missing attribution.

Adds a new vendor to the Vendors.ie directory — generating the JSON data file, wiring it into the relevant category listing, and confirming the detail page renders.

Verifies a vendor's stored data against their live website — pricing, Revenue/ROS integration, PAYE Modernisation, Irish bank feeds, GDPR data residency, Irish support and free trial availability.

Presents a numbered list of 20 sites, loads the relevant memory file, and runs parallel git and gh checks to surface a session brief with sync status, open PRs and recent activity.

Audits GitHub Actions across 18 Flash Report and bryancollins99 repos for failures, timeouts and cancellations in the last 7 days.

Launches 3-5 QA subagents in parallel against the current project, each auditing a distinct dimension, then synthesises findings into one report ranked by severity.

Fires a Python urllib smoke test at the AI API endpoints on Vendors.ie, ReadingCurator and FluentAtDesk, flagging 500s and timeouts.

Crawls a live site using a Python stdlib crawler and reports internal links returning 4xx/5xx status codes.

Runs Lighthouse against the homepage of each live site and reports Performance, Accessibility, Best Practices, SEO, plus LCP, CLS and TBT for any flagged site.

Verifies the licence of a public repo (or a specific file within it) before you fork, republish or include content from it.

Generates a human-readable changelog between two git tags — grouped by feat, fix and refactor, with author attribution.

Lists merged and stale local branches, deletes the safe ones, flags the rest.

Drafts a pick / squash / reword plan for git rebase -i to clean up a feature branch before PR.

Walks through each conflicted file in a merge or rebase — reads both sides, proposes a resolution, explains the rationale.

Renames a skill’s slug everywhere — filename, frontmatter name, internal references, per-project overrides.

Extracts a recurring prompt from your chat history and scaffolds it as a new slash command.

Verifies a privacy policy page exists, is linked from the footer, and has a lastUpdated date under 12 months.

Audits a site’s content for affiliate and partnership disclosures per FTC / EU consumer rules.

Loads a site’s content-profile.md and monetisation-profile.md, injects them as a brief for content-production agents.

Scans a site’s published content for missing monetisation hooks — affiliate links, CTAs, email opt-ins, internal links to money pages.

Adds cross-reference links between two sister sites when the content naturally pairs — e.g. a procurement post linking to a matching vendor category.