Communitygithub.com

SkillMedev/skills

Runs the full Getting Things Done loop - capture, clarify, organize, reflect, engage - building a trusted system of context lists, a projects list with defined next actions, and a weekly review habit. Use when someone says "I'm overwhelmed and things are slipping through the cracks", "set up GTD for me", "help me do a brain dump and organize it", or "my to-do list is a mess". Do NOT use for just running the weekly review ritual itself - use weekly-review instead - or for clearing an email backlog - use inbox-zero.

What is skills?

skills is a Claude Code agent skill that runs the full Getting Things Done loop - capture, clarify, organize, reflect, engage - building a trusted system of context lists, a projects list with defined next actions, and a weekly review habit. Use when someone says "I'm overwhelmed and things are slipping through the cracks", "set up GTD for me", "help me do a brain dump and organize it", or "my to-do list is a mess". Do NOT use for just running the weekly review ritual itself - use weekly-review instead - or for clearing an email backlog - use inbox-zero.

Works with~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/SkillMedev/skills/tree/HEAD/skills/gtd-system

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

Getting Things Done

The goal is a clear head: every commitment captured in a system more trustworthy than memory, so the mind stops rehearsing open loops at 2 a.m. The costly failure this skill prevents is the half-adopted system - lists that exist but aren't trusted, so the user runs both the lists and the mental inventory, and gets the overhead of both with the relief of neither. Trust comes from one thing: the weekly review. A GTD setup without it decays into another abandoned app within 3 weeks.

Inputs to collect

  1. Current tools: where tasks, calendar, and notes live today. Default: keep the user's existing tools - GTD is tool-agnostic, and a tool migration on day one doubles the failure risk.
  2. Open commitments: work, personal, waiting-on-others. Gathered in Step 1, not asked up front.
  3. Contexts that fit their life (@calls, @computer, @errands, @home, @agenda-boss). Default: those five; label the guess.
  4. A weekly review slot: a recurring 60-90 minute block. Non-negotiable - get a day and time on the calendar before finishing setup.

Operating procedure

The five steps run in order because each consumes the output of the last: clarify processes what capture collected; organize files what clarify decided.

Step 1: Capture

Collect everything with the user's attention on it into one inbox - no judging, no organizing yet. Sweep with a trigger list: projects promised to others, projects others owe you, emails needing replies, calls to make, errands, home maintenance, health appointments, finances, people to reconnect with, ideas parked in your head. Keep prompting "what else is taking up space? Keep going" until two prompts in a row return nothing. A first full capture typically yields 50-150 items; a list of 15 means the sweep stopped early.

Step 2: Clarify

Process each inbox item, one at a time, top to bottom, with one question: is it actionable?

  • No → trash it, file it as reference, or park it on Someday/Maybe.
  • Yes → determine the very next physical action.
    • Takes under 2 minutes → do it now; tracking it costs more than doing it.
    • Someone else should do it → delegate, and log it on Waiting For with who and since when.
    • Otherwise → defer it to Next Actions or the Calendar.

Any outcome requiring more than one action is a project. The project goes on the Projects list; only its next action goes on an action list.

Next-action phrasing rules - an action must start with a physical verb and be executable with no further thinking:

Bad: "Dentist." "Q3 planning." "Mom's birthday."

Good: "Call Dr. Reyes' office at 555-0142 to book a cleaning." "Draft the three Q3 options in a doc and send to Ana for reaction." "Order the blue teapot from the saved cart before Friday."

The bad versions are topics - each forces a re-decision about what "doing it" means every time it's read, which is exactly the fatigue the system exists to remove.

Step 3: Organize

Sort clarified items into exactly these lists:

  • Next Actions - concrete actions grouped by context (@calls, @computer, @errands).
  • Projects - every multi-step outcome, each with a defined "done" and at least one next action on an action list.
  • Waiting For - delegated items: what, who, since when.
  • Calendar - only items that must happen at a specific day/time. The calendar is sacred territory: no "should do Tuesday" wishes, because one ignored calendar entry teaches the user to ignore all of them.
  • Someday/Maybe - not now, revisited weekly.

Step 4: Reflect - the weekly review

The anchor of the whole system, 60-90 minutes, same slot every week: empty every inbox to zero; review the calendar two weeks back (loose ends) and two weeks ahead (prep needed); walk the full Projects list and confirm every project has a live next action - any project without one gets one on the spot; nudge stalled Waiting For items; scan Someday/Maybe for anything to activate or delete. Use the checklist below. For a deeper standalone treatment of this ritual, pair with weekly-review.

Step 5: Engage

Choose work by four filters, in order: context (what can be done here), time available (what fits before the next commitment), energy (match hard tasks to sharp hours), priority. Working from the lists - not from memory or the loudest ping - is the payoff of Steps 1-4.

Worked artifact: filled weekly review checklist

WEEKLY REVIEW - Fri 3:00-4:15pm

GET CLEAR
[x] Email inbox to zero (processed 34; 5 became actions)
[x] Notes app + desk pile processed (7 items captured)
[x] Head sweep with trigger list (4 new items)

GET CURRENT
[x] Calendar -2 weeks: found un-sent follow-up to Priya → @computer action
[x] Calendar +2 weeks: passport appt Tue - added "Print confirmation" to @home
[x] Projects list (14 projects): 2 had no next action
      - "Hire contractor" → "Text Luis for the referral's number"
      - "Q3 offsite" → "Email venue for quote by Monday"
[x] Waiting For: invoice from Dana 12 days old → nudge sent
[x] Someday/Maybe: activated "Set up 401k rollover" → new project

GET AHEAD
[x] Top 3 outcomes next week: venue booked / draft review done / rollover started

Deliverable

Produce a complete GTD system: a processed-to-zero inbox, a Projects list where every project has a defined done-state and a live next action, context-grouped Next Actions phrased verb-first, a Waiting For list with dates, a calendar containing only hard commitments, a Someday/Maybe list, and a recurring 60-90 minute weekly review block with the checklist above.

Do NOT

  • Do not put priorities or wishes on the calendar - polluting it kills its authority.
  • Do not leave any project without a next action; a project with no next action is a worry, not a plan.
  • Do not write topic-style actions ("Taxes") - every read of one costs a re-decision.
  • Do not skip capture when overwhelmed and jump to reorganizing lists. Overwhelm is almost always uncaptured loops; return to Step 1 first.
  • Do not build the system without booking the weekly review. That is the difference between a system and an app with old lists in it.

Quality bar

  • Inbox at zero after processing; nothing parked "to decide later."
  • Every next action starts with a physical verb and names enough detail to start without thinking.
  • Every project has a done-state and a live next action; every Waiting For has a who and a since-when.
  • Calendar contains only day/time-specific commitments.
  • A recurring weekly review block exists on the calendar with the checklist attached.

Individual skills in this repo

This repo contains 11 individual skills — each has its own dedicated page.

SkillMedev/skills

Designs REST API surfaces - resource naming, HTTP method and status-code semantics, error shapes, pagination, and filtering - and delivers an endpoint spec a consumer can build against without asking questions. Use when someone asks "how should I name this endpoint", "what status code should this return", "should this be PUT or PATCH", "how do I paginate this list", or is reviewing an API before it ships to external consumers. Do NOT use for planning breaking-change rollouts and deprecation windows - use api-versioning-strategist instead; for GraphQL type and resolver design - use graphql-schema instead; for generating client SDKs from an existing spec - use api-client-generator instead; for designing inbound webhook endpoints - use webhook-receiver-hardener instead.

SkillMedev/skills

Turns data and charts into a decision-driving narrative structured as headline finding, trend, implication, and recommended action - with finding-led chart titles, context for every number, annotation guidance, and honest flags on any conclusion the data cannot support. Use when someone says "turn these numbers into a story", "what's the takeaway from this data", "help me present these results to leadership", or has charts but no narrative. Do NOT use for compressing a long document into a one-pager - use executive-summary instead - or for running the analysis that produces the findings - use eda-playbook instead.

SkillMedev/skills

Use when a task needs live or historical money data - "convert USD to EUR", "current/past exchange rate", "FX rate on this date / over this range", or "current price of Bitcoin/Ethereum, market cap, 24h change". Frankfurter (ECB reference rates, no key) is the FX default; CoinGecko's free keyless tier covers crypto. Do NOT use for stock quotes or equities - no keyless stock API survives verification, say so instead of guessing; do NOT use for country economic indicators like GDP or inflation series - use government-open-data instead; if the request is a vague "I need live data", route through public-data-api-picker.

SkillMedev/skills

Builds a driver-based FP&A operating model linking business inputs to P&L, balance sheet, and cash flow outputs. Use when building an annual plan, preparing investor materials, running scenario analysis, or stress-testing the business.

SkillMedev/skills

Use when a task needs live geographic lookups - "geocode this address", "what's at these coordinates" (reverse geocoding), "lat/lon for this city", "which country/state is this ZIP or postal code in", or "country facts: capital, currency, population, flag". Nominatim (OpenStreetMap) is the geocoding default; Zippopotam for postal codes; APICountries for country facts. All keyless. Do NOT use for weather at a location - use weather-climate instead; do NOT use for country-level statistics over time (GDP, population trends) - use government-open-data instead; if the request is a vague "I need live data", route through public-data-api-picker.

SkillMedev/skills

Processes any email backlog to zero using the 4Ds - Delete, Delegate, Defer, Do - with a mass-archive strategy for the obvious, a touch-each-email-once discipline, and a keep-it-clear system of batched processing windows, ruthless unsubscribing, filters, and a minimal folder setup. Use when someone says "I have 5,000 unread emails", "help me get to inbox zero", "email is eating my whole day", or treats their inbox as a to-do list. Do NOT use for drafting the reply emails themselves or prioritization rules for an ongoing support queue - use email-triage instead - or for protecting focus time around the email windows - use deep-work-planner instead.

SkillMedev/skills

Runs structured coaching sessions using values clarification and the GROW model, ending every session with one committed action, a deadline, and an if-then plan for the likely obstacle. Use when someone says "I feel stuck in my life", "help me figure out what I want", "hold me accountable to my goals", or "coach me through this decision". Do NOT use for building a stress toolkit - use stress-management instead - or a journaling practice - use journal-framework; for a standing goal-tracking system, use goals-accountability. Coaching, not therapy: signs of clinical distress route to a licensed professional.

SkillMedev/skills

Classifies incident severity (SEV1-4) using impact, scope, and urgency signals and decides who to page. Use when an alert fires or a report comes in and a severity call must be made quickly.

SkillMedev/skills

Use the Skill Me catalog from inside any conversation - discover, install, and manage Claude skills through the Skill Me MCP, and load installed skills automatically each session.

SkillMedev/skills

Writes and tunes PySpark jobs - join strategy and broadcast size limits, shuffle-partition sizing, skew diagnosis and salting, UDF avoidance, caching, and output file layout - with concrete size and skew thresholds. Use when someone asks "why is my Spark job slow", "should I broadcast this join", "one task takes forever while the rest finish", "my job OOMs during a join", or is writing a new PySpark ETL job. Do NOT use for Kafka topic, consumer-group, or streaming-pipeline design - use kafka-pipelines instead; do NOT use for single-machine dataframe work that fits in memory - use pandas-expert instead.

SkillMedev/skills

Builds clean, performant, accessible SwiftUI views with correct state ownership, scoped invalidation, and smooth list scrolling, and reviews existing SwiftUI code against a concrete frame-time and re-render budget. Use when someone asks "why does my SwiftUI list stutter", "should this be @State or @Observable", "my whole screen re-renders when one row changes", "how do I animate this transition", or wants a SwiftUI view built or refactored. Do NOT use for cross-platform React Native apps - use react-native-pro instead; do NOT use for Flutter widget trees - use flutter-widget-architect instead; do NOT use for Android Compose UIs - use jetpack-compose-builder instead.

Related Skills