Productivity
ai-capability-assessment
Assess how well the user uses AI, from the evidence in their chat history, memory and files, and write an AI Capability & Progress Portfolio with scores, growth from first attempt to now, next levels and the projects that prove it. Use when the user asks to assess, score, rate or audit their AI skills, or wants an AI portfolio for recruiters, applications, LinkedIn or GitHub.
$ npx skills add VidhishaJain/claude-skillsagent-browser-current-browser
Connect agent-browser via CDP to the user's already-open Windows Chrome/Edge (not a fresh/headless instance) from inside WSL2, without restarting the browser or closing its tabs. Use whenever the user asks to read, click, or automate something in "the browser I already have open" / "現在のブラウザ" / "既存のブラウザ" (e.g. check Google Calendar, read a page they're logged into) rather than a brand-new agent-browser session. Also use it when the user names a Chrome profile or tab group to work in (e.g. "Work の『調査』グループで"), or when several agents use the browser concurrently.
$ npx skills add nabinno/agent-skillsspec-workflow
Entry point and shared contract of the spec-driven, AI-assisted software lifecycle (spec-plan → spec-implement → spec-review → spec-close). Use when the user asks how the spec/tech-plan workflow works, where a change currently stands, which phase comes next, how to list or resume open tech plans, or how to configure the workflow for a repository (`.spec-workflow.yml`). Also use before invoking a phase skill when the repository conventions (plan directory, status values, quality commands, documentation map) are not yet known. This skill performs no phase itself: it inspects status, resolves conventions, and routes the user to the correct phase skill.
$ npx skills add dashie/ai-skillsstate-machine
Use when the user wants a task run as a state machine, workflow or step-by-step graph (Graphviz DOT) that the agent follows, including one that loops over a queue of items, fans items out to parallel subagents and waits for all of them, or keeps values between steps across context resets; when the user hands over a stored machine.dot to reuse; asks to draw, show or edit the machine; asks "where are we" in one; or a machine.dot run is already active in this session.
$ npx skills add coldstar96/state-machine-skillwordpress-security-checklist
Audit a WordPress site against the WordPress Security Checklist (wpsecuritychecklist.org) or explain and walk through its hardening items. Use when someone asks to check, audit, review, or harden the security of a WordPress install, codebase, server, or public URL; asks whether wp-config.php, .htaccess, plugins, users, or file permissions are secure; or asks what a checklist item means and how to apply it. Also triggers on "is my WordPress site secure", "WordPress hardening", "checklist de segurança WordPress", "lista de seguridad WordPress".
$ npx skills add WP-Security-Checklist/skillskill-scout
Spots recurring workflows in the user's requests that deserve a dedicated skill and proposes them as evidence-backed candidate cards, extends an existing skill when it already covers part of the need, flags missing connectors, and security-scans any third-party skill before recommending it. Use when the user asks "what skill should I create", "suggest skills", "what could I automate", "which skills or connectors am I missing", or reviews their usage, and whenever they submit, evaluate or want to install a third-party skill. Also use opportunistically in any session: if a request repeats a known workflow, makes the user re-explain rules, chains stable steps with no existing skill, or forces copy-paste for lack of a connected tool, suggest it in one line at the end of the answer. Not for writing a specific skill the user has already chosen (use skill-creator). Never creates or modifies a skill without the user's explicit approval.
$ npx skills add Adminseb/skill-scoutscan-to-docx
Transcribe scanned documents (PDF pages, JPG/PNG scans, typewritten or printed pages, often with handwritten corrections) into an editable Word .docx, carefully applying manual edits (strike-throughs, caret insertions, margin notes), checking grammar/spelling, and producing a local review app where the user resolves uncertain passages and exports the .docx. Use this whenever the user wants to OCR, transcribe, "convert to text" or "convert to Word/docx" a scan, photo of a page, or scanned PDF — in any language (Slovene, English, German, ...) — even if they don't mention handwriting, review, or an app. Also use when they say things like "pretvori v besedilo", "prepiši ta PDF", "scan to Word", or ask to do "the same as sample1" for other files.
$ npx skills add karlovsek/scan-to-docx_skillsrepo-onboarding
- Investigates, understands, and bootstraps software repositories by discovering their technology stack, architecture, development commands, testing infrastructure, and existing conventions. Establishes a centralized project-context documentation system, generates customized AI agent instructions for AGENTS.md, CLAUDE.md, and GEMINI.md, and defines a structured development workflow with decision tracking, project roadmaps, feature planning, task management, progress tracking, and verification gates. Use when onboarding a new repository, initializing an AI-assisted development workflow, or standardizing an existing project's documentation and agent instructions.
$ npx skills add thanhdt942/skillslocal-data-storage-and-privacy
Use when an app stores data in the browser (localStorage, IndexedDB) or handles files the user uploads, imports or drops in. Defines what goes where, and the hard rule that uploaded data is sensitive and must never be sent over the network. Covers import, export, backup, clearing data, diagnostics and a no-leak checklist.
$ npx skills add viciouskinid/Skill.mdgas-leak-audit
Audit an AI agent, workflow, repository, or organization for Generation, Accounting, and Search (GAS) leaks: wasted production, unmeasured costs, lost knowledge, and broken learning loops. Produce an evidence-backed leak register, prioritized repairs, and a recurring inspection schedule. Use when asked to diagnose AI inefficiency, self-audit an agent, map business workflows, detect repeated work or lost knowledge, or measure system learning.
$ npx skills add leo-guinan/gas-leak-audit-skillemail-deliverability-audit
Audit a sending domain's email authentication (SPF and its 10-lookup limit, DKIM, DMARC, MX, MTA-STS, TLS-RPT, BIMI) by looking up its DNS records, explain every problem in plain language and give the exact DNS record that fixes it. Use when the user asks why emails land in spam, wants to check SPF/DKIM/DMARC, sets up a new domain for cold email or newsletters, or asks whether they meet the Gmail, Yahoo or Microsoft sender requirements.
$ npx skills add mailbeast/cold-email-skillsfolder-structured-agent-workflows
Use when designing, setting up, or debugging a sequential, multi-stage AI agent workflow with human review between stages, for example when a user asks to 'organize an agent pipeline as folders', 'replace a multi-agent framework with files', 'write stage contracts or CONTEXT.md files', or 'control what context each step sees'. Applies a folder-as-architecture method: numbered stage folders, layered context loading, plain-file handoffs and review gates. Not for workflows needing real-time multi-agent collaboration, high concurrency, or fully autonomous operation without human review.
$ npx skills add peaknr35/-Skillsmithurgent-first
Puts the urgent items in a pile first, by rules an expert wrote, and quotes the exact words behind every flag. Use it when someone asks to triage my issues, what should I look at first, which of these are urgent, prioritise this queue, sort this backlog or worklist by urgency, what changed since last week or the last release, group related reports, make a maintainer digest, explain a flag, or to build and test a triage pack for my field. Works on GitHub issues and pull requests (any public repo), on-call or support tickets, and JSONL, CSV, FHIR or HL7 exports. It never lowers a priority and never produces a "safe to ignore" list.
$ npx skills add logitsolutionsai/urgent-firstjob-hunt-partner
A job search partner for any profession, level and country. It first asks the user about their field, target roles, location and constraints, then finds and scores roles, audits and adapts resumes and CVs, audits portfolios and work samples, writes outreach (LinkedIn connection notes, DMs, referral asks, informational interview invites, follow-ups) and keeps an application tracker in Notion, Google Sheets, Excel or a plain table. Use this whenever someone is job hunting or changing careers, or asks for help with a resume, CV, cover letter, portfolio, LinkedIn message, referral, recruiter reply, job posting, interview pipeline or application status, even if they never say the words job search.
$ npx skills add mahdiverse/job-hunt-partnerrepo-radar
repo-radar. Build a one-page HTML dashboard of a GitHub repo (open pull requests sorted by what they need, open issues by whether anyone is on them, a graph of how PRs, issues and plan boxes link, and recently closed work by release), set it up to rebuild every day with a GitHub Action, watch several repos at once from a watch list with an overview page, and compare a team's plan file with GitHub. Use when someone wants a status dashboard or morning view of a repo or of several repos, asks "where are we", "where am I", "how are my teams' repos doing", "what is left in my section", "what needs review", "is my PR on the plan", wants their PR put on the plan, or runs the weekly plan refresh.
$ npx skills add sv642-hub/repo-radarmusic-skill
Make, check and understand music from a terminal, for an agent that can't hear it. Use when someone wants music made - a house or techno track, a beat, a loop, a bed under a video or a voice, music at an exact length, tempo or key, stems or MIDI - or wants to know what's in a piece of audio ("what's the BPM", "what key is this", "where's the drop", "why is this mix muddy"), or needs audio checked before it goes out (loudness in LUFS, true peak, clipping, mono compatibility). Also for why a groove works - syncopation, swing, microtiming, voice leading, breakdown and drop - and for checking music a generative model made.
$ npx skills add kylefritz/music-skillweekly-review
Build a one-page weekly review from the user's calendar, email and tasks — what got done, where the time went, what slipped, and the three priorities for next week. Use when the user types /weekly-review, asks for a weekly review, a week recap, "how did my week go", or wants this scheduled every Friday.
$ npx skills add AdrienBalcioglu/weekly-reviewrecording-to-obsidian
Turn a meeting recording or a lecture's materials (audio/video, transcripts or subtitles, slides pdf/pptx, notebooks, code, handouts, whiteboard photos) into linked Obsidian notes. Transcribes recordings locally with Whisper (bundled script). Meeting mode writes a meeting hub (TL;DR, decisions, action items in Obsidian Tasks format with owners, due dates and transcript timestamps), ADR-style decision records, durable topic notes and a series MOC. Lecture mode writes a lecture MOC, dense anchor notes and fine-grained atomic notes with PDF++ slide links and Mermaid diagrams. Use whenever the user wants meeting minutes, a recap, action items, study notes, a MOC or a knowledge base from a meeting, a call, a class or a talk — even if they only say 'make notes from this recording'.
$ npx skills add T0MYYY/recording-to-obsidianclose
USE WHEN the user asks to close work: "wrap up", "shut down my day", "close this milestone", "end of sprint", "before we close". NOT FOR closing files/apps/windows, git close, or "close the PR".
$ npx skills add ryan-baum/open-close-kithandoff
Use whenever you work in any project folder or codebase (start, end, after big changes, before a compact or reset): create handoff.md and ai-handoff-summary.md if missing, keep both updated.
$ npx skills add KuyaLoy/handoff-skillopen
USE WHEN the user wants to begin a work container or ceremony: "start my day", "open a milestone", "plan a sprint", "new client", or start a session/week/project/research/brief/skill/experiment/direction/goal/conversation. NOT FOR opening files/URLs/apps, git operations, or "open a PR".
$ npx skills add ryan-baum/open-close-kitantigem-browser-qa
Use when performing E2E browser testing, exploratory QA, form validation, accessibility audits, layout/ergonomics checks, visual regression, PWA/offline verification, i18n/Indic rendering tests, or runtime diagnostics on web/PWA apps in AntiGem's browser_mcp
$ npx skills add vijaychaudhari88/antigem-browser-qabrand-discovery
Run a structured, resumable multi-session brand identity interview across 8 modules (purpose, positioning, audience, personality, voice, narrative, founder tension) using laddering, 5 Whys, and projective techniques, persisting answers to disk and producing a master brandbook (90_SYNTHESIS.md). Use when creating or repositioning a brand, briefing designers or writers, or making implicit founder knowledge explicit.
$ npx skills add youssefmahni/skillsharedev-arquitecto-software
Úsala para implementar sistemas, módulos o funcionalidades cuando el usuario define la arquitectura y espera que el agente solo escriba el código. Cubre investigación previa de repositorios, foros e internet, diagramas de las partes relevantes, preguntas en lugar de suposiciones, propuesta de arquitectura y árbol de archivos, y aprobación explícita antes de tocar código. Actívala cuando el usuario diga "tengo la arquitectura", "solo escribe el código", "no inventes", "investiga repos similares", "hazme el diagrama y dime qué archivos tocarás" o "espera mi aprobación". No la uses para arreglos triviales de una línea ni para prototipos donde el usuario delega el diseño.
$ npx skills add fer-prieto/opencode-skill-software-architect