agent-deploy-scriptUse when the user wants to create an agent-specific, low-verbosity variant of the current repo's deployment script for AI agent execution. Triggers on phrases like "create agent deploy script", "agent-deploy.sh", "make a quiet deploy script for agents".build-and-push-debianUse when the user wants to push changes to GitHub, build a new debian version incrementing the version, and upgrade the local package. Triggers on phrases like "build and push", "push then build debian", "release and install locally".build-debian-packageUse when the user wants to build a new version of the debian package in the current repo, increment the version, and install locally. Triggers on phrases like "build the debian", "build new debian version", "rebuild and install package".create-package-releaseUse when the user wants to increment to the next version and create a GitHub release/tag that triggers a debian build workflow. Triggers on phrases like "create a release", "new version release", "tag and release".debug-local-toolUse when a local application, CLI tool, or service on the user's Linux workstation isn't working and needs interactive debugging. Triggers on phrases like "X isn't working", "debug X", "X is broken", "fix X on my machine", "troubleshoot X".npm-publishPublish the current package to npm. Bumps the version, ensures npm login, fetches the OTP from 1Password, and runs npm publish. Use when the user asks to "npm publish", "publish to npm", "release this package", or "bump and publish".release-dev-projectFull release workflow for public dev projects — commit, push, bump version, build debian, install locally, create GitHub release with .deb attached. Triggers on phrases like "release this project", "new release", "publish a release", "release and deploy",…setup-debian-buildUse when the user wants to set up a build script in the current repo to package it as a debian. Triggers on phrases like "set up debian build", "create a build script for debian", "add debian packaging".
مستكشف المستودعات
danielrosehill · المستودعات و skills الممثلة - الصفحة ٥
عرض على مستوى المستودعات لـ ١٬٢٤٨ skills مجمعة عبر ١٩٢ مستودعات GitHub.
onboardFirst-run onboarding for the adb-ops plugin. Interview the user about the Android device connected via ADB — model, Android version, rooted status — then collect folder mappings (phone path to local path, with labels and use cases). Writes profile and…bloatware-logView, search, and summarise the bloatware operations log at <workspace>/bloatware-log.jsonl. Use when the user asks "what bloatware did I remove", "show my debloat history", "what did I disable on this phone", or wants to audit past package operations before…device-statusReport the status of Android devices connected via ADB — serial, manufacturer, model, Android version, battery, storage, and whether the device matches the onboarded profile in <workspace>/profile.yaml. Use when the user asks "is my phone connected", "what…import-mediaImport media (photos, videos, voice memos, downloads) from the connected Android device to the local computer using saved mappings from <workspace>/mappings.yaml. Supports "import new since last run" (incremental) or full sync. Use when the user says "import…pull-folderPull an arbitrary folder (or single file) from the connected Android device to the local computer via `adb pull`. Unlike import-media this is ad-hoc — the user supplies the phone path and optional local destination. Use when the user wants "just grab…push-folderPush a local folder or file to the connected Android device via `adb push`. Uses mappings from <workspace>/mappings.yaml when the direction is `push` or `bidirectional`, or accepts ad-hoc source/destination from the user. Use when the user wants to "sync…remove-bloatwareRemove or disable Android bloatware (carrier apps, OEM pre-installed apps) via ADB using `pm uninstall --user 0` or `pm disable-user`. Logs every operation to <workspace>/bloatware-log.jsonl so the history is auditable and reversible. Use when the user wants…take-screenshotCapture a screenshot from the connected Android device via ADB and pull it to the local computer. Defaults to saving under ~/Pictures/Phone/Screenshots/ with a timestamped filename, or uses the screenshots mapping from <workspace>/mappings.yaml if the user…
context-briefAssemble a scoped background briefing for a workspace or a task — read only the entries whose scopes match, and say which they were. Use at the start of a session in a consumer workspace, or when the user asks "what do you know about me for this".context-exportProduce a portable bundle of the whole store — every entry as markdown, plus INDEX.md, scopes.yaml and a manifest. The conformance test for portability. Use when moving backends, backing up, or checking the store is actually portable.context-initFirst-run setup for the personal context layer — choose a backend, pick a store location, scaffold it, and write machine-local config. Run before any other personal-context skill. Triggers on "set up personal context", "where should my context live", "init…context-writeThe write path — draft an entry in full, show it, confirm scope and sensitivity, write it, index it, commit it. Use when the user says "remember that", when another skill has candidates to write, or when a consumer workspace proposes writes back.ingestTurn material the user already has — journals, notes exports, message archives, old therapy notes, a CV, letters — into context entries with provenance. Use when the user points at files or a folder and says "read this", "here's my journal", "use these notes".intake-interviewSectioned, resumable interview that builds the personal context store from conversation — basics, people, history, patterns, care, preferences. Use for a first pass when there is nothing to ingest, or to fill a section the user chose to skip. Triggers on "run…context-reviewPeriodic maintenance of the store — staleness, contradictions, over-broad scopes, orphaned links, entries that should be split or merged, and anything the user wants removed. Use every few months, or when a brief surfaces something that is no longer true.gap-scanRead what the store already holds and work out what is missing, thin, stale or contradictory — then ask targeted questions instead of generic ones. Use after ingestion, periodically, or when the user says "what's missing", "what else do you need to know".
docs-lookupLook up Tampermonkey documentation — metadata keys (`@match`, `@grant`, `@run-at`, etc.), the GM_* / GM.* API, and configuration. Fetches the official docs page on demand to stay current.new-userscript-repoSet up a brand-new development workspace for a single userscript. Asks public or private, creates the GitHub repo with the chosen visibility, installs this plugin at project scope inside it, and ends. The user opens that repo in a fresh Claude Code session…bump-versionBump a userscript's `@version` (semver), update README, commit, tag, and push. Tampermonkey only auto-updates installed scripts when `@version` increases — forgetting this means users never receive fixes.generate-readmeGenerate or refresh a userscript repo's README.md from its `==UserScript==` metadata block — install button, what it does, supported sites, version, license. Idempotent; safe to re-run after metadata changes.new-userscriptScaffold a new Tampermonkey userscript with a complete `==UserScript==` metadata block, sensible defaults, and a starter IIFE body. Drops it in the user's userscripts base directory if configured, otherwise asks where to place it.onboardFirst-run setup for userscript-development. Optionally records the user's userscript repos base directory so other skills can default new userscripts there. Skipping is fine — the plugin works without it.publish-userscriptPublish a userscript to GitHub so it can be installed via Tampermonkey's "Install from URL" using the raw GitHub URL. Wires up `@updateURL` and `@downloadURL` in the metadata block, commits, and pushes.test-userscriptValidate a userscript end-to-end in a real Chrome tab via the Claude in Chrome MCP. Loads the target page, simulates the script's effect, reads console logs and DOM state, and reports whether the script's behavior matches its `@description`.
connect-as-clientUse when you need to register a relay server as an MCP client in your local Claude install.onboardFirst-run setup for agent-relay. Captures the relay URL, this machine's client_id, optional shared token, and the roster of peer clients (friendly name -> client_id). All written to $CLAUDE_USER_DATA/agent-relay/config.toml -- never into the plugin directory.…setup-relay-serverUse when you need to deploy the MCP relay server to a remote SSH host.create-sessionUse when you need to create a new session for participants to communicate through.relay-statusUse when you need to check the health and status of the relay server.send-fileUse when you need to send a file to a relay session.send-messageUse when you need to send a text message to a relay session.tail-sessionUse when you need to read new messages from a relay session.
install-advancedInstall the optional advanced security-audit layer on top of the core AV set — Lynis (system hardening audit), chkrootkit (second-opinion rootkit scanner), AIDE (file integrity DB), debsecan (Debian/Ubuntu CVE scanner). Lets the user pick a subset; doesn't…install-coreInstall the core AV tool set on Linux — ClamAV (clamscan + clamd + freshclam), ClamTk (GUI front-end), rkhunter. Uses the package manager recorded by `onboard`. Configures freshclam to run as a service, runs an initial definitions update, and updates…onboardFirst-run setup for linux-av-manager. Picks a scan-results folder (default ~/linux-av-manager/scans/), records distro/package-manager info, detects which AV tools are already installed, and offers to install the core set (ClamAV, ClamTk, rkhunter). Triggers…scanRun an on-demand security scan with one or more installed tools — ClamAV (clamscan / clamdscan against home or a chosen path), rkhunter, chkrootkit, Lynis (system audit), AIDE (integrity check). User picks scope (quick / deep / specific path) and which…scheduleSet up periodic AV scans on a Linux desktop using systemd timers (preferred) or cron. Schedules definition updates plus scans (ClamAV, rkhunter, Lynis) at user-chosen cadences (e.g. daily definitions refresh, weekly quick scan, monthly deep scan). Wires…ufw-maintainMaintain an existing UFW ruleset on a Linux desktop — list current rules, diff against the saved baseline, add or remove individual rules, dedupe redundant entries, flag overly-permissive rules (any-source allows, broad port ranges), and snapshot the new…ufw-setupSet up UFW (Uncomplicated Firewall) on a Linux desktop with conservative, desktop-appropriate defaults — deny incoming, allow outgoing, allow established/related, allow common LAN-only services if present (mDNS, KDE Connect, syncthing) only after asking. Does…update-definitionsRefresh signature databases and definition files for every installed scanner — freshclam (ClamAV), rkhunter --update, lynis update info, AIDE differential check (does NOT promote a new baseline), debsecan suite refresh. Reads installed flags from plugin…
add-printerUse when the user wants to register a new printer on the networked CUPS server.check-cups-firewallUse when CUPS connections are timing out and you suspect ufw firewall is blocking ports.diagnose-network-printingUse when network printing fails and you need one-shot triage across all layers.discover-printers-arpUse when mDNS discovery fails or the user wants to scan all devices on the subnet.discover-printers-bonjourUse when you want to scan the LAN for printers via mDNS/Bonjour.list-printersUse when you want to see all configured printers on the networked CUPS server.onboardUse when the user installs the plugin and needs to configure it for the first time.print-fileUse when the user wants to print a local file to a networked printer.
analyze-harAnalyze a HAR file (HTTP Archive — exported from Chrome/Firefox DevTools → Network tab → Save all as HAR with content) and produce a normalized inventory of the endpoints it captured, with inferred request/response schemas, auth scheme detection, and a…capture-via-proxyCapture network traffic via a local mitmproxy instance and emit a normalized capture file the rest of the plugin can analyze. Use when the user wants to capture traffic from a desktop app, mobile app on the same network, or a browser without using DevTools —…create-domain-mapProduce or update a versioned "domain map" document for a single host — a curated, human-readable summary of what's been learned about a target across one or many capture runs. Aggregates endpoints, auth scheme, pagination style, rate-limit signals, ToS…disclose-findingHelp the user act as a good-faith reporter when a capture run incidentally surfaces something that looks like an unauthenticated endpoint exposing data that probably shouldn't be public, a leaked token in a response, or another security-relevant finding.…generate-openapiGenerate a draft OpenAPI 3.1 spec from an endpoints inventory produced by analyze-har, capture-via-proxy, or observe-tab. Reads endpoints.json + inferred schemas and emits openapi.yaml plus openapi.json. Use when the user wants to build a stable client…init-private-repoSet up a private GitHub repository for version-controlling the user's domain maps and capture history. Creates the repo via gh, clones locally to a user-chosen path, scaffolds the standard layout (maps/, captures/, README, .gitignore), and registers the local…observe-tabOptional convenience path — observe a live browser tab via the claude-in-chrome MCP server (read_network_requests) and build an endpoint inventory as the user interacts with the page. Useful when the user is already driving a tab and doesn't want to set up a…setupFirst-run setup for Browser-Data-Capture — provisions the user data folder under the standard $CLAUDE_USER_DATA pattern, optionally registers a path to the user's private maps repo for version-controlled storage, and verifies dependencies (mitmproxy, genson,…
batch-render-typstBatch-render N PDFs from a directory of JSON data files against a Typst template. Use when the user wants to render many documents at once (e.g. a month of invoices, a batch of certificates) using a Typst template they already have or just scaffolded.define-brand-profileCapture the user's brand identity — colour palette, fonts, logo, business name and registered address, tax/VAT IDs, contact details — into a reusable brand profile that every other skill in this plugin consumes. Use when the user wants to set up branding for…extract-brand-from-siteVisit a user-supplied website URL and infer brand identity from it — colour palette, typography, logo, business name, address, contact details — then write a brand profile the plugin's other skills consume. Use when the user says something like "use the brand…ingest-document-sampleTake an existing document sample (PDF/image/Word) — typically an invoice, receipt, statement, or business letter — and convert it into a Typst template plus a JSON schema describing its variable fields. Use when the user says they have an example document…new-typst-templateScaffold a parameterised Typst template for batch document rendering. Use when the user asks to create a Typst template, build an invoice/receipt/statement/report/letter template, or set up a JSON-data-driven Typst document for batch CLI rendering. Produces a…recommend-rendering-serviceRecommend a document rendering engine or service for the user's stack and constraints, and produce a worked integration example for the chosen one. Covers Typst CLI, Carbone, PDFMonkey, APITemplate.io, DocRaptor, Docmosis, Adobe Document Generation API, and…scaffold-n8n-doc-pipelineGenerate an n8n workflow JSON that takes a webhook payload, renders a document via the user's chosen rendering engine, and stores or returns the resulting PDF. Use when the user wants to "set up automated invoicing in n8n", "build an n8n doc-gen workflow", or…schema-from-samplesGiven multiple samples of the same document type (e.g. five different invoices), infer a unified JSON schema covering every variable field across all samples. Use when the user wants to design a robust template that handles real-world variation rather than a…
download-resumeDownload Daniel Rosehill's resume / CV — public PDF, agent-readable JSON, or open the CV web page. Use when the user says "download my resume", "get my CV", "fetch resume JSON", "open my CV page", or similar.profilesOpen Daniel Rosehill's profile on a specific external network — LinkedIn, X (Twitter), GitHub, YouTube (main or tech channel), npm, Kaggle, DeviantArt, or Pexels. Use when the user says "open my LinkedIn", "go to my X", "youtube channel", "npm profile",…pull-bioFetch Daniel Rosehill's bio from his About page and load it into the conversation. Use when the user says "pull my bio", "get my bio", "fetch about page", "load my bio", or needs bio text for a profile / proposal / intro.view-blogOpen one of Daniel Rosehill's blogs in the browser — personal blog or tech blog (Hey It Works). Use when the user says "open my blog", "personal blog", "tech blog", "hey it works", or similar.view-huggingfaceOpen Daniel Rosehill's Hugging Face profile pages — models, datasets, or spaces — in the browser. Use when the user says "open my HF models", "view my datasets", "show my spaces", "hugging face profile", or similar.contactOpen Daniel Rosehill's contact form or newsletter subscription page in the browser. Use when the user says "open my contact form", "newsletter signup", "subscribe page", "contact page", or similar.update-marketplaceRefresh the local cache of Daniel Rosehill's Claude Code plugin marketplace so newly published plugins/updates show up. Use when the user says "update marketplace", "refresh plugins", "pull latest plugins", "marketplace update", or after pushing a new…view-github-reposOpen Daniel Rosehill's public GitHub repositories in the browser. Supports three sort orders — latest (default, by recently pushed), stars, and alphabetical (A–Z). Use when the user asks to "see my repos", "open my GitHub", "list my repos by stars", "show…
scrape-articleScrape an article from a URL via the user's localhost (preserves Israeli IP for geo-restricted sites) and save a clean markdown capture. Use when the user gives a URL and wants the article body saved, or says "capture this article", "scrape this", or…setup-toolsFirst-run / re-check setup for Local-Web-Capture. Verifies the data directory exists, installs the Rung-1 headless extractor (webclaw), sets up the Rung-4 real-browser path (bb-browser), seeds sites.yaml, and flags Playwright MCP for removal once validated.…batch-captureCapture a list of URLs in one job. Saves each article individually with a timestamp, then produces a summary report across the batch (markdown always; PDF optional via Typst). Supports two report modes: human-summary (readable prose + per-item cards) and…batch-to-pdfCompile a batch of captured articles into a single PDF via Typst. Each article gets a header block showing the source URL and capture date, a page-numbered footer runs throughout, and a cover + table of contents open the document. Use when the user wants a…capture-translateCapture an article from a URL (via the normal localhost scrape path) and save a translated version alongside the original. Default language pair is Hebrew → English; supports arbitrary source → target. Saves to ~/local-web-capture/translations/. Use when the…scrape-priceCapture product name + price (and optional unit price, stock, SKU) from an Israeli e-commerce URL via the user's localhost, saving a structured JSON snapshot under ~/local-web-capture/prices/<domain>/. Use when the user wants to track a price on Yad2,…capture-listBrowse, search, or summarise what's in the local-web-capture data directory (~/local-web-capture/). Use when the user asks "what did I capture recently", "find my captures of X", "list articles from ynet", or wants a table of recent captures.scrape-authenticatedTier-3 escalation — capture an article or page from a paywalled, logged-in, or aggressively-gated site by driving the user's real Chrome via bb-browser (login state + cookies + user's IP). Use ONLY when scrape-article reports that headless rungs failed…
apply-podcast-presetApply a recommended parametric-EQ DSP preset tuned for spoken-word / podcast listening to a Music Assistant player. Tames sub-bass rumble, lifts vocal presence (1–4 kHz), and softens sibilance (~6–8 kHz). Use when the user wants a one-shot "make this speaker…referenceShared reference for the Music Assistant local API — base URL, auth, the WebSocket command bus, the DSP/EQ schema, and the data-storage layout this plugin uses. Load when another skill in this plugin needs to know how to talk to the server, what DSP shape to…control-playerSend a playback command to a Music Assistant player — play, pause, stop, next, previous, or set volume. Use when the user asks to control a specific player by name (e.g. "pause the living room", "skip track on kitchen", "set bedroom to 40%").list-playersEnumerate all players known to the Music Assistant server along with their current state (playing/paused/idle), volume, and currently-playing track if any. Use when the user asks what players are available, which are active, or needs a player_id to target…onboardFirst-run setup for the media-assistant-ops plugin. Capture the user's local Music Assistant deployment URL + API key, snapshot the current speaker/player roster for future context, vet the overall setup (providers, connectivity, auth), and summarise the…save-dsp-settingsSnapshot a Music Assistant player's current DSP (EQ bands + filters) configuration and persist it as a named preset under $CLAUDE_USER_DATA. Use when the user has dialed in an EQ on a player and wants to capture it so it can be restored later, shared across…statusVerify the plugin can reach the configured Music Assistant server. Hit /api/info with the stored API key and report server version, uptime, and player count. Use when the user asks whether the server is reachable, suspects a connectivity issue, or wants a…update-dsp-settingsApply a DSP configuration to a Music Assistant player — either by loading a previously saved preset from disk or by adjusting specific EQ bands/filters in-place. Use when the user wants to switch a player to a saved preset ("apply night-mode to living room")…