By pettipol
Skill portabili cloud-safe dell'AI Harness: bibtex-conventions, major-revision-discipline, scientific-writing, diagram-design. Pensate per sessioni Claude Code on the web (VM Anthropic), zero dipendenze da ds4/Ollama/texlive/MCP locali.
Convenzioni BibTeX per gestione bibliografia: niente commenti % dentro {...}, standard ISO come @misc con howpublished, campi obbligatori title/author/year, DOI puliti 10.xxxx/yyyy, chiavi cognome_anno (duplicati _a/_b), accenti UTF-8 nativi in title/abstract, escape degli underscore letterali nel campo note. Use when the user is editing or generating a .bib file, adding or cleaning BibTeX entries, managing a bibliography, formatting DOIs or citation keys, or asks about BibTeX conventions. Pairs with latex-conventions and the doi-bib-verify command.
Create technical and product diagrams — architecture, flowchart, sequence, state machine, ER / data model, timeline, swimlane, quadrant, nested, tree, layer stack, venn, pyramid — as standalone HTML files with inline SVG. Ships with a neutral editorial skin and a first-run gate that prompts users to customize the style guide (colors, fonts) from their own website before generating. Includes annotation-callout primitive and optional sketchy variant.
Disciplina operativa per Major/Minor Revision (R2/R3) di manoscritti journal con tracked-changes e response-to-reviewers: twin baseline M0/M1, colour-coding per reviewer, patch idempotenti anchor-based, status DONE/OPEN/BLOCKED, submission Editorial Manager. Use when the user mentions "tracked changes", "Major Revision", "Minor Revision", "response to reviewers", "twin baseline", "baseline diff", "EM submission", "Editorial Manager", "REMEDIATION", or a reviewer (R2/R3); or when a project contains RESPONSE_TO_REVIEWERS.md / CHANGE_LEDGER.md / OPEN_POINTS_*.md, or a ~/.claude/plans/ plan references "Major Revision"/"REMEDIATION".
Write scientific content: paper sections, abstracts, methodology descriptions. Use when generating LaTeX content from simulation data or reviewing paper drafts.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Marketplace pubblico di plugin per Claude Code, contenente il plugin
harness-portable: 4 skill di disciplina/convenzione, cloud-safe (nessuna dipendenza da tool locali,
nessun dato personale):
| Skill | Cosa fa |
|---|---|
bibtex-conventions | Convenzioni BibTeX (chiavi, DOI, encoding) per bibliografie accademiche |
major-revision-discipline | Disciplina operativa per Major/Minor Revision di manoscritti (tracked changes, response to reviewers) |
scientific-writing | Scrittura scientifica: sezioni, abstract, metodologia |
diagram-design | Diagrammi tecnici come HTML+SVG standalone |
Le sessioni Claude Code on the web (claude.ai/code) non sincronizzano marketplace ospitati su repo
privati (verificato 2026-07-04). Questo repo è il mirror pubblico solo-skill del marketplace
harness-cloud che vive nel repo privato pettipol/ai-harness (fonte canonica: ogni modifica alle skill
va fatta lì e ri-specchiata qui).
Nel .claude/settings.json del repo in cui vuoi le skill (committato):
{
"extraKnownMarketplaces": {
"harness-cloud": {
"source": { "source": "github", "repo": "pettipol/harness-cloud-public" }
}
},
"enabledPlugins": {
"harness-portable@harness-cloud": true
}
}
Alla sessione successiva (locale o cloud) il plugin viene installato all'avvio e le 4 skill sono disponibili.
Uso personale; nessuna garanzia. Generato dall'AI Harness di Vittorio Villani, 2026-07-04.
npx claudepluginhub pettipol/harness-cloud-public --plugin harness-portableComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
This skill should be used when users need to generate ideas, explore creative solutions, or systematically brainstorm approaches to problems. Use when users request help with ideation, content planning, product features, marketing campaigns, strategic planning, creative writing, or any task requiring structured idea generation. The skill provides 30+ research-validated prompt patterns across 14 categories with exact templates, success metrics, and domain-specific applications.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems