Productivity

Emotional-discipline tool that makes the user plan for failure BEFORE a big money move. Runs a pre-mortem, stress-tests the position, writes kill criteria, checks exit costs and reversibility, separates story from numbers, applies a cooling-off gate, and saves a decision-journal entry. Also reviews past journal entries into a blind-spot report. Use whenever the user asks whether to commit money or take on debt, even if the question sounds routine, such as buying a stock, ETF, mutual fund, crypto, property or plot, locking savings in an FD or lock-in product, a personal or vehicle loan, EMIs, or buying on credit. Also use for FOMO, tips, limited-time pressure, pre-mortem, kill criteria, decision journal, exit plan, or review my past decisions, even if the skill is not named. Analysis and structure only. Never gives buy/sell advice. Not financial advice.

Find good meeting times for a group of Google Workspace users, inside each person's Google Calendar working hours and time zone, and optionally send the invite. Use when the user asks to find a time, schedule or book a meeting, or check when several people are free. Attendees can come from anywhere, such as a Slack message's reactions, a list of names, or a doc. Needs a shell and the gws CLI.

Evaluate a job offer or recruiter message (LinkedIn, email, headhunter) for the user. Interviews them about their current package, estimates NET take-home pay for the current job and the offer (local social security, income tax, autónomo costs for B2B), checks fit against their CV, scores conditions (remote, benefits, career trajectory), proposes the 2-3 recruiter questions that matter, and drafts the reply (decline or ask for details). Use whenever the user pastes a recruiter message, a job description, or asks "is this role worth it / I got an offer / LinkedIn message", even if they do not say "evaluate".

Turns a project scope into a branded quote and statement of work PDF (phases, deliverables, hours and rates or fixed fees, contingency, payment schedule, assumptions, out of scope, timeline, terms and a signature block), with totals computed by a script so the math is always right. Also makes a one-page rate card of services and rates. Use when someone asks for a quote, estimate, proposal with pricing, SOW, budget for a creative or freelance project, a rate card, or help pricing a project. Usage - /project-quote followed by the client and a description of the work, or "rate card".

Plan, check or repair a multi-day road trip using recorded constraints and a deterministic checker for drive times, sunset cutoffs, fuel range, opening hours, time zones, lodging and bookings. Starts with a structured intake that asks the traveller, in multiple-choice rounds, about route, drivers, hotel brand or loyalty program, room and budget, daily distance, pace, interests and things to avoid. It then keeps the plan updated as bookings are pasted in. Use this whenever the user wants to plan a road trip or self-drive holiday, sanity-check or fix an existing driving itinerary (including a PDF or spreadsheet), ask whether a driving day is realistic, compare route options, or adjust a trip already planned, even if they don't say "road trip" (自驾, driving from X to Y over N days, campervan or rental car routes). Not for trips with no driving, or for single-journey directions.

Route gh-aw design, creation, diagnosis, patching, active debugging, and upgrade requests to the right strategies.

Share documents through LinShare - send files to people by email (inside or outside the organisation), list or revoke what was shared, list and download files received, ask people to send files, and work with team workgroups and workspaces (browse, upload, download, manage members). Use when the user asks to share, send, transfer or receive a file "via LinShare", to check or cancel a LinShare share, or about a LinShare workgroup, workspace or shared space.

Orchestrate xplan, xreview plan, xwork, and xreview work in child sessions (or subagents when child sessions are unavailable), resolve findings, and finish with all task-owned code and .agents records committed locally. Use only when the user invokes xauto or explicitly requests this autonomous workflow. Do not invoke kauto or push changes.

Pre-release/publish sanity check for a build2 third-party package (initial submission, new version, or new revision) on the local or specified repository. Runs the packaging review checklist against the repository, including testing the installed case and the source distribution out-of-tree, and reports findings. Read-only: makes no changes, local or externally visible (no commits, no pushes, no GitHub issues/PRs/comments, no email). Use when the user wants to sanity-check packaging before publishing, run the packaging review checklist locally, or runs /build2-review or /build2 review. Do not use for ordinary source-code review of a build2 project (that is /review). Do not use for creating the package (that is build2-package). Do not use to act as an official cppget.org reviewer performing the actual GitHub review (that requires opening an issue/PR, merging, and emailing [email protected], which is out of scope here).

Run full investigation workflow for customer issue - searches knowledge base, documentation, code, and external trackers, then recommends test environment

Smart sales & growth analyst for retail shops, cafés, e-shops and small businesses, in any country and in English or Persian. Takes Excel/CSV sales exports (Shopify, Square, WooCommerce, Lightspeed, SumUp, local POS or accounting exports such as Sepidar/Hamkaran/Mahak/Holoo, Pohoda, DATEV; Gregorian or Shamsi dates; EUR, USD, CZK, Toman/Rial or any currency), computes sales KPIs, customer segmentation (RFM), product performance (ABC, rising/declining items), inventory health (low and dead stock), diagnoses what is hurting the business, proposes concrete marketing campaigns (email/SMS/social, offers, seasonal calendar) and delivers a management report (chat summary, Excel report, HTML dashboard, or PDF/Word). Use this skill whenever the user shares or mentions sales files, orders, invoices, receipts or POS exports, asks why sales dropped, wants to compare months or years, find best/worst sellers, segment customers, build a customer or SMS/email list, plan a discount or campaign, or wants a sales report/dash...

This skill should be used when users want guidance on Spec-Driven Development methodology using GitHub's Spec-Kit. Guide users through executable specification workflows for both new projects (greenfield) and existing codebases (brownfield). After any SDD command generates artifacts, automatically provide structured 10-point summaries with feature status tracking, enabling natural language feature management and keeping users engaged throughout the process.

Link every new or updated note into an Obsidian or markdown knowledge vault graph so nothing is orphaned. Use whenever you write or edit a vault note, meeting summary, inbox item, or related page.

Catch the errors and omissions before payday.

Guided job-interview preparation. Builds a candidate profile and story inventory, briefs each round, runs mock interviews as a tough mentor (score out of 10, critique, rewrite), iterates every answer until it reaches 9+, and files it into a living markdown question bank. Also writes session handoffs, from-memory post-interview debriefs, pre-interview cheat sheets, and opportunity fit checks. PM-first with deep AI/Technical PM coverage, works for any role. Use when the user says "interview prep", "mock interview", "be my interviewer", "rate my answer", "question bank", "I just finished an interview", "debrief", "cheat sheet", "prep me for this round", "should I take this role", or shares a JD and wants to practise.

Explains how an AI agent skill works by taking it apart: its trigger description, frontmatter, SKILL.md routing, reference files, scripts, load order, risks and a best-practice scorecard, then shows the analysis as an interactive web page. Use when the user wants to understand, review, audit, compare or learn from a skill (a folder with SKILL.md), or asks what a skill does, when it triggers, what it loads or runs, or how it is built. Not for writing a new skill from scratch; use skill-creator for that.

Use when a programmer asks what to learn, or wants books, talks, papers, courses, career/interview resources or coding-practice sites on software fundamentals.

Turn a priced Bill of Quantities (BOQ) into a first-draft, cost-loaded construction programme that imports into Primavera P6 (XER) - activities by trade and location, logic learnt from 73 real P6 schedules, the BOQ money and quantity on every activity. Claude reads every BOQ line (English, Portuguese, Spanish) and types it to a trade and location with a reason, the totals are checked to the cent, then the planner answers a short list of questions the BOQ cannot answer (locations, layout, contract period, three known durations, which site works go early) and the draft is built. Use when someone has a BOQ / bill / orcamento / planilha orcamentaria and wants a baseline schedule, programme or WBS drafted from it, a cost-loaded schedule without a schedule to start from, or a P6 XER built from a BOQ. Not for loading a BOQ into a schedule that already exists (use p6-cost-loader) and not a cash-flow forecast.

Estimates how long software work will take when coding agents do it, from measured agent runs, as P50/P80/P90 ranges with a critical path and the human part stated separately. Use whenever anyone asks how long software work will take, a feature, a fix, a plan, a roadmap or a task list, even when agents are not mentioned, and whenever a timeline is quoted in days, weeks or months. Assume agents do the implementation unless told otherwise. Not for non-software work.

Realistic mock job interview for any job title, followed by a blunt scored report. Use when the user wants to practice or prepare for a job interview, rehearse answers, simulate a recruiter, HR, behavioral, technical or manager interview, or says things like "mock interview", "interview me", "prepare me for my interview", "entretien d'embauche", "simule un entretien", "prépare-moi à mon entretien".

Gets finished posts into a social media scheduler (or posted by hand) safely. Queue-only with explicit timezone offsets, live dedup against scheduled and already-published posts, media readiness checks, correct post types (shorts, reels, carousels, first comments, manual-posting reminders), alt text, a link gate that sends copy back for a rewrite rather than stripping it, and confirmation before anything goes live. Writes and keeps a scheduling manifest for each pack. Works with any scheduler; Publer is the worked example. Use when someone says "schedule this", "queue these posts", "put this in Publer", "book in this week's content", "post this on Tuesday at 7", "move that post", "what's already scheduled", or hands over a finished content pack to go out.

Realistic DevOps, SRE, platform, cloud or DevSecOps mock interview with live incident scenarios, system design and a blunt scored report. Use when the user wants to practice or prepare for a DevOps / SRE / platform engineer / cloud engineer / DevSecOps / Kubernetes interview, rehearse technical questions on Linux, Docker, Kubernetes, Terraform, CI/CD, cloud or observability, or says "devops mock interview", "SRE interview", "interview me on Kubernetes", "entretien DevOps", "simule un entretien SRE".

Import GTFS transit feeds, query station/stop/pathway/route/trip/calendar/shape data, edit connections, nodes, routes, trips, and stop times, compare trip service patterns and schedules, export changes to GTFS CSV, and open a local browser dashboard with the gtfs-tools CLI. Use when working with GTFS data, transit stations, pathways, routes, trips, schedules, or accessibility audits.

Build a non-disruptive "Email Automation" section inside an app's admin panel: lifecycle reminders (welcome, abandoned cart, post-purchase, upsell, win-back) with proven funnel timing, personal copy, a free WYSIWYG editor, conversion stats, and admin-only tables. Ships paused and reuses the app's email connection. Use for email automation, drip/lifecycle email, abandoned-cart recovery, or an "Email Automation" admin menu. Triggers: "email automation", "drip campaign", "abandoned cart emails", "reminder emails", "lifecycle emails", "welcome sequence", "win-back emails", "upsell emails".