Claude Skills by ccplugins

Use when starting hyperflow in a new project, re-initializing analysis, refreshing `.hyperflow/` cache, or installing multi-tool auto-detection shims (AGENTS.md, Cursor rules, GEMINI.md, CLAUDE.md). Trigger phrases — "init hyperflow", "set up hyperflow", "refresh hyperflow", "install hyperflow shims". Standalone setup; does **not** auto-chain into the feature flow.

Use when the user says "plan this", "decompose this task", "break this down", or wants the task file before any code changes. Writes `.hyperflow/tasks/<slug>.md` with batched sub-tasks, then **auto-chains into `/hyperflow:dispatch`** — no manual gate.

Use when the user is exploring a design idea, weighing approaches, has an ambiguous request, or says "should I", "how should we", "what's the best way to". Asks structured questions, proposes 2–3 approaches, walks the design section-by-section. On approval, **auto-chains into `/hyperflow:scope`** — no manual gate.

Use when encountering bugs, test failures, runtime errors, unexpected behavior, broken builds, or "this doesn't work" reports. Systematic root-cause analysis before any patch — never blind-patches symptoms. Standalone (off the spec → scope → dispatch chain). Ends with a thinking-tier review of the fix.

Use when the user explicitly asks to hand a task to Codex — "use codex", "delegate this", "send it to codex", "交给codex", "派给codex", or the /delegate command. Runs the full dispatch lifecycle with frozen acceptance criteria and a binding independent judge. NEVER auto-dispatch — delegation happens only on the user's word. If a task looks Codex-shaped (bulk mechanical edits, wide read-and-report analysis, test scaffolding), you may offer the option in ONE line; if the user doesn't take it, drop it.

Use when composing the task brief and acceptance criteria for a Codex dispatch (invoked from dispatching-to-codex). Covers the self-contained brief format and how to write acceptance checks that actually protect you — weak checks are the sneakiest way a dispatch goes wrong.

Compile an Anthropic-style skill — a directory with a SKILL.md and optional references/ — into a deterministic, runnable workflow via the rote CLI. Use when the user says "compile this skill", "graduate this skill" (the retired name for the same operation), "make this skill deterministic", "make this skill faster/cheaper", "turn this skill into a workflow", "turn this skill into code", "harden this skill for production", or complains that a skill is slow, expensive, or unreliable as a backgro...

Wire a compiled rote pipeline up as an MCP tool so Claude can trigger the deployed workflow directly. Use when the user says "register my compiled pipeline", "serve my pipelines over MCP", "trigger the workflow from Claude", "hook the pipeline up to Claude", or asks what to do after `rote compile` and deployment. Covers `rote register` and `rote serve` plus the `claude mcp add` wiring.

Find screenshots shared/accumulated during this Claude Code session and, with the user's approval, move them to the Trash (no permanent delete — recoverable). Use before ending a session, when asked to tidy the Desktop/screenshots folder, or when the screenshot-janitor Stop hook suggests cleanup. Triggers include "clean up screenshots", "delete screenshots", "tidy my desktop", "remove the screenshots".

自然语言意图分析 → 技能推荐 → 自动安装。当你描述需求时，Claude 自动分析意图、从市场中发现匹配的技能、安装后调用。

A disciplined loop for implementing, fixing, refactoring, or unblocking a single feature or slice in an existing codebase. Reads the relevant docs/specs first and reports drift before coding, splits work into small file-disjoint commit units, and for each unit runs a build/test gate then dispatches two independent reviewers in parallel and reconciles their findings before handing off a commit you run yourself (it never auto-commits). Use when the user says things like "implement this feature"...

Use when the user shares a social video/post link or local video and wants it understood — an Instagram (instagram.com), TikTok (tiktok.com), YouTube or YouTube Shorts (youtube.com/youtu.be), or X/Twitter (x.com/twitter.com) URL, or a local .mp4/.mov file, OR when they say "analyze/watch/transcribe this video/reel/post." Downloads it, transcribes the audio, extracts frames Claude can see, and produces a thorough breakdown.

Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, and MCP artifacts to disk from books, notes, transcripts, exports, datasets, slide decks, files, URLs, code, and recurring source workflows.

Research, write, code, analyze, present, and develop proposals for thermal-fluid mechanical engineering work with source-aware rigor. Use for heat transfer, fluid mechanics, thermodynamics, HVAC, energy systems, turbomachinery, pumps, piping, CFD, experiments, correlations, standards, datasheets, papers, patents, AI/ML tools, computer vision, sequence regression, surrogate modeling, research coding, Overleaf, VS Code, GitHub, git, federal grant proposals, DOE/NSF/NASA-style narratives, invent...

When the user has the Tycana plugin installed but appears to be new (no items, empty context, or MCP connection issues) — guide them through getting started.

When the user discusses tasks, planning, productivity, work priorities, what to do next, progress reviews, or mentions something they need to do, track, or remember — use Tycana as persistent memory and productivity intelligence.

Verifies and formats APA 7 Korean academic citations across 14 source types, augments DOIs via CrossRef, and applies CopyKiller 99-rule avoidance. Use when the user requests APA 인용 검증, 참고문헌 양식 확인, CrossRef DOI 보강, 박사 논문 인용, or CopyKiller 회피.

Progetta e installa un'infrastruttura di sicurezza a 4 livelli dove il cuore (dati e chiavi) è offline e staccato, lo scudo è invisibile agli scanner e il server reale è nascosto. Usare quando l'utente vuole un sistema "chiuso in una scatola", un reverse proxy invisibile, un'alternativa self-hosted a Cloudflare, server nascosto, VPN WireGuard, o backup offline irraggiungibili. Trigger - "fortezza", "scatola chiusa", "offline", "invisibile", "nascosto", "mini cloudflare", "reverse proxy", "air...

Implementa autenticazione sicura quando un sito/app richiede registrazione, login o account utente. Copre verifica email con codice, autenticazione a due fattori (2FA/TOTP), passkey e chiavi di sicurezza, hashing password, sessioni e recupero account. Trigger - "login", "registrazione", "verifica email", "codice di verifica", "2FA", "doppio fattore", "autenticazione", "passkey", "account utente".

Aggiunge a un sito/app un agente di difesa che rileva e blocca richieste malevole (SQL injection, XSS, path traversal, brute force, bot) con rate limiting, blocklist IP e modalità lockdown che chiude il sistema preservando i dati. Trigger - "blocca attacchi", "anti-attacco", "firewall", "WAF", "lockdown", "difendi il sito", "rate limiting", "sotto attacco".

Applica regole di sicurezza (hardening) ogni volta che si costruisce, modifica o revisiona un sito web o un'app. Copre security headers, CSP, HTTPS, validazione input, cookie, CORS, upload, gestione errori e OWASP Top 10. Trigger - "crea un sito", "costruisci un'app", "metti in sicurezza", "proteggi il sito", "hardening", "security headers", "build a website".

Protegge dati di pagamento e abbonamenti quando un sito/app gestisce checkout, carte, subscription o fatturazione. Copre integrazione sicura Stripe/PayPal, verifica firma webhook, PCI-DSS, GDPR, minimizzazione dati e ciclo di vita degli abbonamenti. Trigger - "pagamenti", "checkout", "abbonamento", "subscription", "Stripe", "PayPal", "carta di credito", "fatturazione", "privacy dei pagamenti".

Aggiunge alle repository GitHub dei siti workflow di sicurezza automatici - scansione dipendenze vulnerabili, ricerca di segreti/chiavi nel codice, analisi statica CodeQL e Dependabot. Trigger - "sicurezza repo", "GitHub Actions di sicurezza", "scansione repository", "metti la sicurezza nella repo", "dependabot", "secret scanning".

Query the weft event log with filters. Use only when user types /ev-query.

Abort the current weft workflow. Use only when user types /wf-abort.

Propose a weft workflow from conversation context. Scans skills, identifies gaps, builds template with loops.

Launch the weft TUI dashboard in a new terminal window. Use only when user types /wf-dashboard.

Edit an existing weft workflow template. Use only when user types /wf-edit-template.

Create a new weft workflow template interactively. Use only when user types /wf-new-template.

Preview a weft workflow template with full step details. Use only when user types /wf-preview.

Rebuild weft state.json from the event log. Use only when user types /wf-rebuild.

Initialize a weft workflow from a template or inline steps. Use only when user types /wf-start.

Show current weft workflow state and recent events. Use only when user types /wf-status.

Transition the current weft workflow step. Use only when user types /wf-step.

Promote an open-source project across CN & EN channels — reads the repo, generates per-channel tailored copy, auto-submits issue/PR-type channels via gh, assists the rest. Use when the user wants to 宣传/推广/publicize/launch/submit their open-source project, or asks "帮我把这个项目投到阮一峰周刊/HelloGitHub/Show HN".