recommend-modelIntelligent, preference-driven model recommendation across fal.ai, Replicate, WaveSpeedAI, and MiniMax (Hailuo). Asks the user a short set of preference questions (workload, priority — quality vs speed vs cost, max budget per output,…budget-estimatorEstimate API costs for a planned pipeline or for an entire script before any generation runs. Reads pipeline SPEC.md(s), the storyboard, and `brief/tools-and-models.md`, then projects cost per shot and total — with a low / typical / high range that accounts…comfyui-exportExport an AI-Video-Producer pipeline to ComfyUI workflow JSON — produce a workflow the user can load in ComfyUI to reproduce (or approximate) a hosted-API pipeline locally. Best-effort: maps fal/replicate model calls to equivalent ComfyUI…comfyui-importImport a ComfyUI workflow JSON (the API-format export from ComfyUI's "Save (API Format)" option, or the UI-format graph JSON) and turn it into an AI-Video-Producer pipeline SPEC plus stage runners. Maps Comfy nodes to pipeline stages, surfaces the model…model-researcherResearch what fal.ai and Replicate (and optionally other providers — Runway, Kling, Pika, Hedra, ElevenLabs, OpenAI) currently offer for a given workload — text-to-image, text-to-video, image-to-video, lip-sync, voice, upscaling, interpolation — and recommend…script-to-ttsReformat an existing script for a specific text-to-speech model (ElevenLabs, OpenAI TTS, Google, Azure, Hume, Chatterbox, etc.). Splits VO into model-friendly chunks, inserts pacing/emphasis/SSML markers where the model supports them, strips bracketed visual…text-to-image-to-videoTwo-stage pipeline that generates a still image from a text prompt (Flux/SDXL/Imagen) then animates it into a video clip (Kling/Runway/Hailuo/Wan). Use when the user wants tight visual control over the opening frame before motion.text-to-video-directSingle-step text-to-video generation (Sora, Veo, Kling text mode, Hailuo). Use for quick exploratory shots or when motion is more important than precise framing.
explorador de repositórios
danielrosehill · Repositórios e skills representativas - Página 3
Visão por repositório de 1.248 skills coletadas em 192 repositórios do GitHub.
activate-bundleApply a named bundle from the Claude Vault inventory — activates all plugins and MCP servers the bundle declares in the current project. Use when the user names a bundle ("activate the podcast bundle").deactivate-mcpRemove an MCP server from the current project's .mcp.json and disable it in .claude/settings.json. Symmetric counterpart to activate-mcp.deactivate-pluginDisable a plugin in the current project by removing its entry from .claude/settings.json enabledPlugins. Symmetric counterpart to activate-plugin.update-vaultRefresh the vault — pull plugin updates and regenerate the skill-index used by vault-search. Use when the user asks to "update the vault" or after adding new plugins to the inventory.vault-searchFind a dormant skill or plugin in the vault by keyword. Use when the user describes a task ("trim silence", "look up a medication") and the matching tool may live in a dormant plugin.activate-mcpMount an MCP server from the Claude Vault inventory in the current project by writing to .mcp.json and enabling it in .claude/settings.json. Use when the user wants to "activate", "mount", or "add" a vault MCP server to the current repo only.activate-pluginEnable a plugin from the Claude Vault inventory in the current project by editing the project's .claude/settings.json. Use when the user wants to "activate", "turn on", or "enable" a vault plugin for the current repo only.bundle-createSave the current project's active plugin and MCP set as a reusable bundle in the Claude Vault inventory. Use when the user has a project configured the way they like and wants to capture that combination for reuse.
apply-layersCompose the active snippet from each chosen category into a single delimited block and write it into the configured target file (default ~/.claude/CLAUDE.md). Within a category at most one snippet is active; across categories they layer.apply-recipeActivate a named recipe — a pre-bundled set of style snippets shipped with the plugin (or saved by the user). Plays the recipe's banner image as a fullscreen pop-out animation with sound, writes the bundled snippets into the managed CLAUDE.md block, logs the…clear-layersStrip the style-switcher managed block from the target file and clear active_layers in config.json. Equivalent to "no styles applied" without deleting any snippets.list-recipesList all available recipes — both shipped (bundled with the plugin) and user-saved — showing id, name, tagline, layer count, and which one is currently active.onboardFirst-run setup for style-switcher. Creates the user-level data directory and writes config.json. Default apply target is a delimited fragment inside ~/.claude/CLAUDE.md, since the plugin layers multiple snippets together rather than swapping single…swap-recipeSwitch from the currently active recipe to a different one in a single step — clears the existing managed block, applies the new recipe (with banner pop-out and sound), and logs the swap as a single history entry.add-snippetAdd a named style snippet to a category in the user's library. Creates the category directory if it doesn't exist. Snippets are short tonal fragments — register, terseness, hedging, formatting — meant to be layered together via apply-layers.current-layersShow which snippet is currently active in each category and what the composed block in the target file looks like. Read-only.
delete-preference-ruleRemove a Wireplumber preference rule — by filename, by matched device name, or by description. Restarts Wireplumber so the change takes effect immediately. Use when a rule is no longer wanted or is causing wrong-device routing.dictation-mic-tuneDiagnose and tune a microphone for speech-to-text dictation — evaluate level, apply RNNoise/noise-cancellation virtual source, set a higher software gain, and optionally persist the noise-cancelled source as the default. Use when the user dictates frequently…easy-effects-bindingsSTUB — manage EasyEffects presets and bindings. Apply/remove input or output presets (compressor, EQ, RNNoise GUI, etc.) and bind a preset to a specific device so it auto-loads on connect.list-audio-devicesList Pipewire audio sinks and sources with their IDs, descriptions, default-status, and current state. Use when the user asks "what mics/speakers are connected", needs IDs to feed into other skills, or is debugging why an expected device is missing.list-preference-rulesList all custom Wireplumber rules currently active on the system — device priorities, routing rules, profile overrides. Use to see what's been set before adding/removing.mic-level-checkSample a microphone for a few seconds and report peak/RMS level, clipping, and silence. Use to confirm a mic is actually picking up audio and roughly at the right gain. Quick diagnostic — for full dictation tuning use dictation-mic-tune.microphone-preference-rulesCreate persistent Wireplumber rules that auto-prefer specific microphones when connected — e.g. "if the Jabra headset is connected, always make it the default mic; otherwise fall back to the laptop array". Use when the user is tired of manually switching mics.route-on-device-connectSet up combined-sink / fan-out output routing — e.g. "when the Jabra is connected, also play audio through it without changing the default speakers". Use for the case the GUI can't handle: simultaneous output to multiple sinks, or conditional routing tied to…
add-newsletterRegister an additional Buttondown newsletter alongside any already configured. Captures slug, display name, API key reference, user directory, and optional default flag. Use when the user has a new newsletter to manage from the same Claude Code setup.add-templateAdd a reusable email template to the local template store. Templates are markdown files with YAML frontmatter (subject, audience, scope, tags) used as starting points for new emails. Scope is either `global` (any newsletter) or a specific newsletter slug.cli-referenceReference and lightweight wrapper for the official Buttondown CLI (github.com/buttondown/cli). Use when the user prefers CLI operations over raw API calls — sending drafts, listing subscribers, managing emails from the terminal. Resolves the API key for the…list-emailsList recent Buttondown emails (drafts, scheduled, sent) for a specific newsletter via the Buttondown API. Grounds the request shape in the locally cached docs before calling.list-newslettersList all Buttondown newsletters registered with the plugin — slug, display name, user directory, and which one is the default. Read-only; use when the user asks "which newsletters are configured" or to look up a slug before invoking another skill.list-templatesList all email templates in the local template store — name, subject, scope (global or newsletter slug), tags, last updated. Read-only.onboardFirst-run setup for buttondown-mgmt. Registers one or more Buttondown newsletters (each with its own API key reference and user directory), provisions the shared template store, and clones the official Buttondown docs into the local cache.send-emailCreate a draft or send a Buttondown email for a specific newsletter, optionally starting from a local template. Confirms before any send — sends are not reversible.
capture-via-apiCapture a ChatGPT conversation as raw JSON by calling the authenticated backend API from inside the browser tab. Use when importing from a chatgpt.com/c/ URL or a /share/ link. This is the primary, complete capture route.render-typst-pdfRender a ChatGPT conversation as a styled PDF using a Typst template, with colour-coded user and assistant turns, a metadata cover block, artifact callouts and a sources page. Use when the user wants a PDF, a document to read or share, or to be identified by…capture-via-domFallback capture of a ChatGPT conversation by scraping the rendered DOM with scrolling. Use only when capture-via-api fails. Lossy - no timestamps, branches, tool messages or artifact payloads.conversation-to-contextImport a ChatGPT conversation into the current repository as agent context. Use when the user wants to bring a ChatGPT thread into a project, pull a chat into context, or save a conversation for Claude to read later. Writes a Markdown transcript to context/…extract-artifactsPull generated documents, canvas docs, code blocks, images and attachments out of an imported ChatGPT conversation and save them as real files. Use when a conversation produced a document, code, or images worth keeping separately.extract-sourcesCollect the sources a ChatGPT conversation cited into a de-duplicated list, as a sources section, footnotes, or a standalone bibliography. Use when the user wants the references, links or citations from a chat.import-chatgpt-conversationImport a ChatGPT conversation into local files. Use when the user gives a chatgpt.com URL or shared link, asks to save/export/archive a ChatGPT chat, wants a transcript with user and assistant turns marked, or wants a ChatGPT thread as Markdown, JSON or PDF.…import-export-archiveImport conversations from an official ChatGPT data export zip or conversations.json. Use for bulk import, for old or deleted conversations, or when the browser route is unavailable. Also the only route that carries generated images as real files.
author-durable-skillWrite an approved site skill so it survives small UI changes and fails loudly when it does not — handles, assertions, provenance.drift-probeRe-verify a site plugin's load-bearing routes and handles, and report CHANGED with what moved — before a user hits it as a wrong answer.map-site-apiMap the JSON endpoints a site's own pages call, so skills can read data from a stable endpoint instead of scraping rendered markup.observe-pageObserve one page or a list of pages in the browser and write an observation note — what data is there and which durable handles reach it.pick-browser-routeDecide how to reach a site — the user's own signed-in Chrome by default, headless Playwright for public pages, plain fetch when it works.propose-site-skillsTurn observations of a site into a ranked roster of candidate skills for the user to approve or reject before any are written.publication-gateClassify every observation as publishable, private, or never-recorded before committing — plus the stop rule for security findings.repair-broken-skillFix a site skill that broke when the site changed — re-observe the surface, move the handle up the ladder, and record what moved.
interactive-debuggingCollaboratively debug a misbehaving Linux desktop app or service in real time with the user. Two modes — live (tail logs while the user reproduces) and retrospective (something just happened, capture evidence before it gets buried). Produces a diagnosis and…boot-inspectInspect boot health on a systemd Linux system — failed units, slow services, kernel boot messages, and boot-to-boot comparison. Use when the user reports slow boot, services not starting, or wants to check post-reboot health. Targets Ubuntu/Debian + Wayland…inspect-oom-eventsFind past out-of-memory kill events in the journal — both kernel OOM killer invocations and userspace systemd-oomd / earlyoom kills — and reconstruct what was running at the time. Use when the user reports an unexplained freeze, lost work, or a process…journal-inspectRun targeted journalctl queries to surface only the relevant log lines for a debugging task — by unit, time window, priority, boot, or kernel/user scope. Emits structured output (JSON or short-form) suited for AI analysis. Use when the user reports a problem…log-inspectInspect non-journal log sources on a Linux desktop — Xorg/Wayland session logs, application logs in ~/.cache and ~/.local/state, /var/log/* leftovers, and dmesg — using AI-friendly tools (ripgrep, jq, structured queries) that produce focused, parseable output…setup-oom-protectionInstall and configure userspace OOM protection (systemd-oomd or earlyoom) so a desktop running out of memory kills the offending process before the kernel hard-locks the machine. Use when the user reports freezes under memory pressure, or proactively when…validate-persistent-journalVerify that systemd-journald is configured for persistent storage so logs survive reboot — essential for diagnosing hard crashes and unexpected reboots. Configures it if not. Use proactively on any new desktop, and as a precondition before any post-crash…investigate-last-crashOpen a forensic investigation into the most recent Linux crash, freeze, or unexpected reboot. Collects kernel dumps, previous-boot journal, userspace core dumps, and sar metrics, correlates them around the crash timestamp, and writes a findings report. Use…
captureTurn what was said in this session — a dump, a dictated voice memo transcript, or a conversation — into a dated session note, and file it against the threads it belongs to. Use when the user has finished talking and wants it written down, or says "capture…close-issueClose or park this workspace — a retrospective on what changed, what didn't, and what graduates to the persistent background context layer. Use when the user says "I think this is done", or when a review finds the issue has gone quiet for months.context-syncPropose writes back to the persistent background context layer — the non-issue-specific things learned in this workspace. Use at the end of a session, when closing the workspace, or when the user says "remember that".draft-messageDraft something hard to write — a message to the other party, a boundary, a resignation, a script for a conversation, or a letter never meant to be sent. Use when the user says "help me write this", "what do I say to them", or wants to get something out of…perspectivesRe-read the same events through other lenses — the other person's account, a neutral observer, the user in five years, someone who loves them. Use when the user says "how else could I read this", is stuck in one account, or wants to steelman someone they're…start-sessionOpen a session in this therapy workspace — load the frame, the working agreement, open threads, recent sessions and a scoped background brief, then hand the floor over. Use at the start of any session, or when the user says "let's start", "I'm back", "where…therapist-briefProduce a short handover to take to an appointment — a therapist, GP, psychiatrist or intake assessment. Chronology, what the person wants from the hour, and the questions they mean to ask. Use when the user mentions an upcoming appointment or says "help me…thread-reviewCross-session review — what recurs, what has moved, what has gone quiet, and whether the frame of the issue still fits. Use when the user asks "what keeps coming back", monthly-ish, or before a therapist brief.
box-mapManage box maps — track which items are in which physical boxes (or rooms / shelves / storage units) so the user can find things without opening every box. Reads/writes the box and location fields on items in inventory/master.json and produces a per-box…find-duplicatesIdentify duplicate or near-duplicate items in the workspace inventory — exact name matches, fuzzy name matches, and functional duplicates (multiple kettles, multiple HDMI cables of the same length). Outputs a grouped duplicates report and recommends which to…generate-action-listGenerate a printable / portable action list as CSV and optionally PDF — throw-out lists, donation pickup lists, resale queues, insurance schedules, or box labels. Pulls from analysis/* reports already produced by the other skills, and renders via Typst…hype-giveaway-postGenerate a deliberately over-the-top, hype-y social media post for an item the user is giving away or selling — Buy Nothing groups, Facebook Marketplace, Freecycle, Olio, Yad2 freebies. Treats every item like a flagship product launch. Tongue-in-cheek by…identify-donation-targetsIdentify items worth donating rather than discarding, and for each one suggest specific donation organizations near the user that would actually benefit from it. Geo-aware — reads geography from workspace.json and proposes locally relevant charities,…identify-resale-targetsIdentify items in the inventory worth selling rather than discarding or donating. Estimates resale value, suggests the right marketplace per item (geo-aware — e.g. Yad2/Facebook Marketplace IL for Israel, eBay/Craigslist/FB for US, Gumtree/eBay for UK), flags…import-inventoryImport a possession/household inventory from any format the user supplies — CSV, Excel, JSON, Markdown table, free-text bullet list, photo of a handwritten list, or a folder of mixed files — and normalize it into the workspace's canonical item schema.…setup-workspaceInitialize a Declutter Genie inventory workspace at a user-chosen path. Sets up the canonical folder layout (inventory, imports, analysis, box-maps, outputs), writes a starter config (geography, currency, household name), and stores a pointer in…
export-formatsUse when you need to export a generated taxonomy to a non-database format — CSV, TSV, JSON, NDJSON, SQL seed file, or YAML.generate-from-specUse when you need a custom taxonomy generated from a spec — product categories, evaluation types, content classifications, domain-specific enumerations.generate-standardUse when you need a canonical reference taxonomy — ISO 3166 countries, ISO 4217 currencies, ISO 639 languages, US states, Canadian provinces, IANA timezones, HTTP status codes, MIME types. Offline-first, cached.hierarchical-taxonomiesUse when you need a parent/child taxonomy — categories and subcategories, tree structures, nested enumerations, organizational hierarchies.load-to-mysqlUse when you need to load a taxonomy into MySQL or MariaDB — create table with charset/collation, load data, support upsert/replace/append modes.load-to-postgresUse when you need to load a generated taxonomy into Postgres — create table, load data, support upsert/replace/append modes, log the operation.load-to-sqliteUse when you need to load a taxonomy into SQLite — create table, import data, support upsert/replace/append modes, type columns appropriately.onboardingUse on first run or when the user asks how to get started — explain the plugin, walk through the data directory, show a worked example.
repo-to-gdriveUpload a generated document (PDF, markdown, etc.) to Google Drive via the configured Google Workspace MCP server (gws-personal by default, gws-dsrholdings or other overridable). Use when the user says "upload this PDF to Drive", "send this doc to Google…generate-pdf-from-outputsUse when the user wants to generate a styled PDF from repository outputs using Typst with IBM Plex Sans and a clean brand palette. Triggers on phrases like "generate a PDF", "make a PDF from outputs", "typst PDF", "pdf this".repo-to-docs-indexPublish an already-generated PDF (or other file) into a configured docs-index repository — copies it into a YY/MM/DD/<slug>/ folder, writes meta.json, runs the repo's build-index.sh if present, then commits and pushes. Use when the user says "publish this PDF…repo-scanScan a local Git repository and emit a manifest of its text sources (README, docs/, planning/, report/), embeddable images (diagrams/, graphics/, images/, banner.*), and repo metadata (name, slug, git remote, HEAD commit, derived title and summary). Shared…repo-to-blog-postSynthesize a concise, first-person, technical blog post (markdown, with frontmatter) from a GitHub repository's README, docs, and planning files. Writes intro / body / conclusion in a no-marketing-fluff voice. Use when the user says "turn this repo into a…repo-to-docs-configureInteractive setup for the repo-to-docs plugin — writes ~/.config/repo-to-docs/config.json with author details, default license, Typst footer toggles, index-repo publishing targets, and Google Drive settings. Use when the user says "configure repo-to-docs",…repo-to-internal-docGenerate a private or internal-use PDF from a repository — same Typst engine as repo-to-pdf, but with no repo URL in the footer, no license line, and an optional CONFIDENTIAL header. Default output to ~/Documents/internal-docs/. Use when the user says "make…repo-to-pdfConvert a GitHub repository's content (README, docs/, planning/, diagrams) into a polished public-facing PDF via Typst, with an optional AI-generated cover banner and configurable footer (repo URL, license, author). Use when the user says "turn this repo into…