Claude Skills Library
#download#toolkit#registry#claude-code#worksona
David Olsson
Claude Skills Library
Slash commands that turn Claude into structured workstreams. Point a command at a codebase and get back numbered reports โ scored, graded, cross-referenced, and ready to act on.
15 commands. 8 pipelines. 75 reports. Installs in 30 seconds.
What can you do with this?
1. Audit and improve code
Your codebase has problems you haven't found yet. Five specialist auditors examine consistency, repetition, security, patterns, and auditability โ then grade every finding and hand you a prioritized TODO. Run it again after fixes and get a delta report showing what improved.
How to audit your codebase before it audits you โ
2. Run a real security review
Not a linter. Six parallel agents tear through authentication flows, API endpoints, infrastructure config, protocol-specific attack surfaces (MCP, GraphQL, WebSocket), abuse vectors, and OWASP compliance. Produces a posture score and a remediation plan.
What a real security audit looks like โ
3. Document a project so someone else can run it
Twelve numbered reports from a single scan: project overview, tech spec, business benefits, innovation themes, features, extensibility, work zones, technical readiness, and principle alignment. Run it across a portfolio and get cross-cutting synthesis.
Documenting projects that don't document themselves โ
4. Find out how defensible your product actually is
Eight analysts examine your moat from every angle โ what's truly differentiated, where competitors will attack, which market inflection points could flip your position, and whether you control the value chain or just rent space on someone else's.
How defensible is your product, really? โ
5. Measure whether your UX actually works
Seven analyzers score your experience across workflow completeness, persona alignment, content coherence, onboarding friction, and code-to-experience gaps. The deliverable is a prioritized improvement plan grounded in the Three-Step Principle: any user, zero to productive, three steps or fewer.
Measuring whether your UX actually works โ
6. Fix your positioning and conversion
Five agents audit your content, copy, market positioning, UX patterns, and conversion funnels. Plus a standalone SEO audit. The output is a synthesis action plan sorted by impact ร effort.
UX and positioning: is your product saying the right thing? โ
7. Model what your infrastructure costs at scale
Service topology mapping, per-service cost projections from MVP to 10K users, LOC-to-cost correlation, technology roadmap, and a vendor-agnostic requirements spec. Know what you're signing up for before you sign up for it.
How much does your infrastructure actually cost at scale? โ
8. Generate a landing page from your codebase
Seven agents โ app auditor, screenshot analyst, strategy architect, design director, copywriter, page builder, growth advisor โ produce a standalone HTML page plus the strategy docs, copy deck, and promotion plan behind it.
Building a landing page from a codebase โ
9. Enforce a design system on AI-generated frontends
Claude builds frontends. Some drift. A pure grey sneaks in, Inter appears where a serif should be. This skill audits any HTML, React, or CSS artifact against a codified design system โ color tokens, typography, spatial composition, motion, component patterns โ and grades it.
Design systems that survive AI generation โ
10. Track SR&ED hours from git history
Score every commit, estimate qualifying hours, and produce a CSV ledger ready for your accountant. Built for Canadian SR&ED claims.
Tracking SR&ED hours from your git history โ
11. Ship to Vercel or Netlify in one command
Static sites, Next.js, SPAs. One command, live URL.
Shipping to Vercel or Netlify in one command โ
Download
The full toolkit. All 15 commands, all 10 library skills, all reference documents.
Download skills-and-pipelines.zip โ
Installs in 30 seconds:
unzip skills-and-pipelines.zip
cp -r clean-export/commands/* ~/.claude/commands/
cp -r clean-export/skills/* ~/.claude/skills/
Reference
The technical details โ report tables, sub-skill lists, output trees, trigger phrases.
Pipeline References
| Pipeline | Reports | Reference |
|---|---|---|
/doc-suite-generator | 13 (00โ12) | ref โ |
/infrastructure-cost-audit | 8 (00โ07) | ref โ |
/code-audit | 9 (00โ08) | ref โ |
/security-audit | 8 (00โ07) | ref โ |
/ux-audit | 7 (00โ06) | ref โ |
/moat-audit | 9 (00โ08) | ref โ |
/ux-content-audit | 11 (00โ10) | ref โ |
/landing-page | 10 (00โ09) | ref โ |
Standalone Commands
| Command | Reference |
|---|---|
/technical-specification | ref โ |
/technical-readiness | ref โ |
/technology-requirements-spec | ref โ |
/seo-audit | ref โ |
/worksona-first-principles | ref โ |
/worksona-themes | ref โ |
/commit-ledger | ref โ |
/deploy | ref โ |
Library Skills
| Skill | Used by | Reference |
|---|---|---|
project-scanner | All pipelines | ref โ |
readme-standardizer | doc-suite | ref โ |
business-benefit-analysis | doc-suite | ref โ |
innovation-themes | doc-suite | ref โ |
extensibility-analysis | doc-suite | ref โ |
work-zone-mapper | doc-suite | ref โ |
code-audit-suite | code-audit | ref โ |
landing-page-generator | landing-page | ref โ |
commit-ledger | commit-ledger | ref โ |
newsletter-asset-capture | standalone | ref โ |
How Reports Are Numbered
Each pipeline numbers its own reports starting at 00. No global numbering. The folder name encodes the pipeline:
docs/
โโโ 01-project-documentation/ โ /doc-suite-generator (00โ12)
โโโ 02-infrastructure-cost/ โ /infrastructure-cost-audit (00โ07)
โโโ 03-code-audit/ โ /code-audit (00โ08)
โโโ 04-security-audit/ โ /security-audit (00โ07)
โโโ 05-ux-positioning/ โ /ux-audit (00โ06)
โโโ 06-moat-audit/ โ /moat-audit (00โ08)
โโโ 07-ux-content/ โ /ux-content-audit (00โ10)
โโโ 08-landing-page/ โ /landing-page (00โ09)
75 reports across 8 pipelines. Run one or run them all โ each is independent.
Built by Worksona โ documentation, audit, and intelligence tooling for Claude Code.