By Bonny94ITA
Skill e contesto condivisi caricati in ogni sessione su qualunque progetto.
Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".
Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or "compress memory file"
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".
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.
Catalogo personale di skill riusabili per Claude Code. Una sola fonte di
verità — plugins/workspace-skills/skills/ — che si mantiene aggiornata dal
registry skills.sh e si propaga ai progetti reali
copiando i file in .claude/skills/.
skills.sh (npx skills)
│ refresh settimanale (cloud) → PR
▼
plugins/workspace-skills/skills/ ← FONTE DI VERITÀ (questo repo)
│ SessionStart hook, ad ogni sessione
▼
repo operativa/.claude/skills/ ← si aggiorna quando ci lavori
Due meccanismi automatici, una sola cosa da curare a mano (le skill qui dentro):
scripts/refresh-from-registry.sh, che reinstalla le sorgenti elencate in
scripts/sources.txt via npx skills e apre una PR se trova skill non
allineate. Funziona senza il Mac.SessionStart
hook che, a ogni avvio sessione (cloud o locale), ricopia le skill da questo
repo in .claude/skills/. La repo operativa si aggiorna quando ci si lavora,
non a vuoto.Perché file committati e non il plugin marketplace. Nelle sessioni cloud di Claude Code il marketplace non carica le skill (verificato; vedi claude-code#23910). L'unico metodo che le carica davvero è avere i
SKILL.mdcommittati in.claude/skills/— ed è quello che fa l'hook.
plugins/workspace-skills/skills/<nome>/SKILL.md # fonte di verità delle skill
scripts/refresh-from-registry.sh # refresh dal registry skills.sh (cloud/locale)
scripts/sources.txt # mappa owner/repo delle sorgenti
scripts/add-hook.sh # onboarda una repo con il SessionStart hook
templates/sync-skills-hook.sh # template canonico dell'hook
templates/bootstrap-prompt.md # iniezione via sessione cloud, senza clone locale
Aggiungere / modificare una skill
plugins/workspace-skills/skills/<nome>/SKILL.md, commit, push.owner/repo a scripts/sources.txt
(così la routine la tiene aggiornata). Altrimenti resta gestita a mano.Onboardare una repo (nuova o esistente)
bash scripts/add-hook.sh /percorso/della/repo
# poi, dentro quella repo:
git add .claude && git commit -m "Add skills sync hook" && git push
Installa l'hook (merge sicuro se esiste già un settings.json). Da lì in poi la
repo si auto-allinea a ogni sessione.
Rinfrescare la fonte di verità dal registry
bash scripts/refresh-from-registry.sh # in cloud lo fa già la routine settimanale
Bonny94ITA/SkillWorkspace (pubblico). Se lo rendi privato, hook,
refresh e bootstrap richiedono accesso in lettura autenticato.origin: vede ciò che hai pushato, non gli edit locali
non committati.npx claudepluginhub bonny94ita/skillworkspace --plugin workspace-skillsLazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Comprehensive 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.
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.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
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.
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.