openEHR Assistant
claudeopenEHR clinical modeling for AI assistants — archetypes, templates, compositions, AQL, CKM reuse search, and specification lookup.
8 skills · 3 commands · 3 agents · 1 MCP server · hooks
Human-facing documentation and content standards for AI assistants: technical writing, copy editing, AI-tell cleanup, marketing copy, SEO and AI citability, with claims grounded in cited evidence.
Plugin docs-editing from marketplace cadasto in Cadasto/plugin-marketplace. Commands read from the repo's manifest — 12 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
ai-seoUse when asked to make content citable by AI systems ("add or update llms.txt", "add JSON-LD or schema.org markup", "serve Markdown twins", "optimise for AI search or RAG retrieval", "why does the AI summarise our docs wrongly?"). Not classic search SEO (seo-audit).
copy-editingUse when asked to improve prose that already exists ("edit this", "tighten this", "review this page", "proofread", "cut this down", "fix the tone", "why does this read badly?"). Line-edits to house style and flags unsupported claims. Editing, not drafting (technical-writing); AI tells throughout is
docs-editingRouter for prose work ("improve these docs", "what should this document be?") or any request spanning technical-writing (new docs), copy-editing (tighten existing), humanize (AI tells), marketing-copy (landing and launch copy), seo-audit (search visibility), ai-seo (llms.txt, AI citability).
docs-lint-setupUse when asked to "set up Vale", "add prose linting", "bootstrap the docs linter", "add a prose-lint CI job", "lint for AI tells", or "why is Vale so noisy?". Writes .vale.ini, seeds the vocabulary, adds the ai-tells style; never overwrites an existing config unprompted.
humanizeUse when asked to remove AI writing patterns from existing prose, such as "humanize this", "this reads like ChatGPT", "remove the AI tells", "make it sound less robotic", "is this AI slop?". Finds tells, then restates without adding facts. Not general tightening (copy-editing) and never an authorshi
marketing-copyUse when asked for positioning or promotional copy ("write the landing page", "the hero section", "a tagline", "product or feature copy", "the launch announcement or release post", "make the pitch clearer"). Benefit-led copy for technical readers, claims grounded.
seo-auditUse when asked about search-engine visibility ("run an SEO audit", "fix titles and meta descriptions", "check headings, internal links, sitemap, robots.txt", "why isn't this page indexed?", "find duplicate or orphan pages"). Classic SEO, not AI citability (ai-seo).
technical-writingUse when asked to write documentation ("write a README", "document this API or feature", "write a how-to, tutorial, or reference page", "write release notes or a changelog entry", "structure the docs", "what should this document contain?"). New docs; editing existing prose is copy-editing.
prose-reviewerUse this agent to review documentation or page copy for the defects a linter cannot see: unsourced statistics, testimonials and superlatives; capability described as shipped when it is planned; inventories and counts that no longer match the tree; two document kinds merged into one file; terminology
seo-auditorUse this agent for a context-isolated discoverability sweep over a docs tree or published site: per-page titles, meta descriptions, single h1, heading order, canonicals, image alt text and link text; then robots.txt, sitemap coverage, redirect chains, orphan and duplicate-intent pages; then the AI-c
bash ${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh
bash ${CLAUDE_PLUGIN_ROOT}/hooks/prose-lint-on-save.sh
openEHR clinical modeling for AI assistants — archetypes, templates, compositions, AQL, CKM reuse search, and specification lookup.
8 skills · 3 commands · 3 agents · 1 MCP server · hooks
Spec-Driven Development for AI assistants — requirements, RFC-2119 specs, and ADRs with stable identifiers, machine-checked traceability, and the delivery pipeline that runs on them: workers, review into a findings file, close-out; two profiles.
8 skills · 4 agents · hooks
PostgreSQL coding standards for AI assistants: queries, jsonb, schema, indexing, performance analysis, safe migrations. PostgreSQL 18 and later.
8 skills · 2 agents · hooks
Idiomatic Go coding standards for AI assistants — formatting, errors, concurrency, testing, layout.
7 skills · 1 agent · hooks
Maintainer plugin for developing the openEHR Assistant MCP server and plugin — authoring guides, prompts, MCP tools, examples, and managing releases
4 skills · 1 agent · hooks
Idiomatic PHP coding standards for AI assistants — PHP 8.4+, PER Coding Style, PHPStan level 8.
2 skills · 1 agent · hooks
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.