ADHD-friendly productivity coaching: daily planning (/today, /energy), end-of-day capture (/checkin), weekly scheduling (/plan-week) and review (/weekly), life-direction reviews (/review), goal-to-project alignment (/align), project lifecycle (/intake, /breakdown, /reentry, /sunset), idea capture (/spark), brain dump (/dump), task triage (/triage), decision journaling (/decide), and pattern analysis (momentum, overdue-rescue) with adaptive tone calibration
Plugin coach from marketplace jdh-agents in jdh313/jdh-agents. Commands read from the repo's manifest — 2 days ago.
alignThis skill should be used when the user says "/align", "which projects serve my goals", "what should I focus on to learn [X]", "align my projects", "goal to project mapping", "which of my projects help with [X]", "what existing projects support [goal]", "am I working on the right things", or "focus
breakdownConversational project decomposition into ADHD-friendly, sequenced Linear issues. Auto-detects whether to decompose from scratch or recompose drifted existing tasks. This skill should be used when the user says "/breakdown", "break this down", "decompose [project]", "what are the tasks for [project]
checkinProvides a quick end-of-day pulse that reads the morning's priorities, captures what actually happened, and writes a brief end-of-day section to the daily note. This skill should be used when the user says "/checkin", "end of day", "how did today go", "daily reflection", "what did I get done", "wrap
coach-toneProvides personality guidelines, tone calibration by energy level, and response patterns for ADHD-friendly productivity coaching. This skill should be used when the user asks coaching questions like "what should I do next", "I'm stuck", "I can't focus", "I got distracted", "how's my day going", or w
decideThis skill should be used when the user says "/decide", "decision journal", "log a decision", "I need to decide", "record this decision", "why did I choose", "document this decision", or "decision record". Captures structured decisions with context, options considered, rationale, and revisit conditi
dumpThis skill should be used when the user says "/dump", "brain dump", "I need to get everything out of my head", "what's on my mind", "mental clutter", "dump my thoughts", "clear my head", "everything is swirling", or "I'm overwhelmed with stuff to do". Unstructured multi-item brain purge with optiona
energyThis skill should be used when the user says "/energy", "I'm tired", "low energy", "what should I work on", "I can't focus", "energy check", "match tasks to energy", or "I'm in the zone". Reorders today's tasks based on current energy level -- you don't need motivation, you need the right task for y
intakeThis skill should be used when the user says "/intake", "new project", "start a project", "I want to build", "project kickoff", "add a project", or "I have an idea for a project". Structured new project onboarding with a WIP awareness check -- impulse control without gatekeeping. The opposite of /su
plan-weekForward-looking week scheduling with a 3-priority constraint that maps tasks across days without overloading -- complements /weekly (which reviews) by scheduling ahead. This skill should be used when the user says "/plan-week", "plan my week", "schedule my week", "what's my week look like", "week ah
reentryGathers context from Linear and Obsidian to create a structured briefing for returning to a paused or dormant project. This skill should be used when the user says "/reentry", "help me get back into [project]", "where did I leave off", "catch me up on [project]", "what was I doing on [project]", "re
reviewThis skill should be used when the user says "/review", "monthly review", "quarterly review", "life review", "big picture check-in", "theme setting", "zoom out", "life direction", or "what am I doing with my life". Provides a structured life-direction review across career, health, home, hobbies, rel
sparkThis skill should be used when the user says "/spark", "I had an idea", "I want to try", "what if I", "this looks cool", "new interest", "capture this idea", or "I'm curious about". Low-friction idea capture to a monthly sparks log -- validates the dopamine hit without committing to a project. Speed
sunsetThis skill should be used when the user says "/sunset", "close this project", "archive [project]", "I'm done with [project]", "sunset [project]", "I need to let go of [project]", or "shut down [project]". Guides intentional project closure with a structured conversation that captures restart context
todayThis skill should be used when the user says "/today", "plan my day", "what should I focus on today", "morning planning", "daily priorities", "start my day", or "daily planning". Provides a structured morning check-in that converges on 3 priorities through an adaptive coaching conversation with ener
triageThis skill should be used when the user says "/triage", "overdue tasks", "clean up my tasks", "task backlog", "reschedule overdue", "my tasks are a mess", "triage my tasks", or "what's overdue". Provides guilt-free batch processing of overdue Todoist tasks with reschedule/do/drop/delegate actions an
weeklyThis skill should be used when the user says "/weekly", "weekly review", "review my week", "week in review", "what should I focus on this week", "weekly planning", or "weekly check-in". Provides a structured weekly review conversation that audits project attention, enforces WIP limits, and converges
momentumUse this agent when the user asks "what patterns do you see", "show me my trends", "momentum check", "am I making progress", "what have I been focusing on", "focus history", "where does my time go", "pattern analysis", or "what's my trajectory". Analyzes historical coaching notes from Obsidian to su
overdue-rescueUse this agent when the user asks "overdue patterns", "why do my tasks slip", "task rescheduling patterns", "what keeps getting delayed", "chronic overdue", or "task health". Analyzes Todoist overdue tasks and activity history to surface patterns -- chronic reschedulers, project health, completion t
project-pulseUse this agent when the user asks "what projects have I neglected?", "stale projects", "project health check", "audit my projects", "which projects need attention", or "what's been dormant". Scans Linear projects and Obsidian project/hobby notes to classify activity levels and surface neglected work
Curates, catalogs, retrieves, and maintains your library of notes and knowledge in an Obsidian vault. Workflow-shaped (Capture / Process / Retrieve / Maintain) and agent-mediated (skills draft, agents execute). 19 skills + 4 agents + 6 references, coupled to the vault conventions in ~/Loose Ends/.claude/rules/{wiki.md,catalog.md} and the Templater templates in ~/Loose Ends/Templates/.
19 skills · 4 agents
Software craftsmanship discipline skills: grill (the interview primitive — walk a design tree one question at a time, facts looked up by subagent rather than asked, no acting until shared understanding), grill-with-docs (that loop applied to vocabulary, against per-repo CONTEXT.md glossaries), diagnose, prototype, tdd, improve-codebase-architecture, grok (stateful multi-session codebase comprehension with supersession-aware understanding records), zoom-out (adapted in part from mattpocock/skills, MIT), infra-review (architecture/security review of Terraform+Atlantis PRs), quiz-me (opt-in active-recall comprehension check after a code explanation), interrogate-model (holistic representability review of a domain model — the legitimate scenarios and personas it cannot express), design-by-stories (design an artifact's shape — schema, template, data model, config — by modeling its actors and user stories first, then deriving the shape from the stories), and lucid-architecture-diagram (drive AWS cloud architecture diagrams in Lucid, including the two silent-failure modes of its API). derive-conventions (derive a repo's unwritten house style from its own code, adjudicate each inferred rule with the human, and write the approved set to CONVENTIONS.md so the review agents stop re-deriving it). wizard (author an interactive bash wizard that walks a human through the steps only they can perform — third-party dashboards, credentials, CI secrets, one-off cutovers — from a hardened template), resolve-conflicts (recover each side's intent from commits, PRs, tickets and NDR heads before resolving a merge, rebase, or jj conflict; detects git vs jj and follows that VCS's own mechanics), and wait-what (user-invoked: re-pitch a message that did not land, in Simplified Technical English using the repo's own vocabulary) — all three adapted from mattpocock/skills, MIT. screen-critique (critique a UI screen design in a fixed order — purpose against its neighbouring screens, then structure,
19 skills · 3 agents
Personal SDLC scaffolding for AI-assisted development. A lightweight, ephemeral 'contract' between user and AI drives each code change from captured idea to verified done; the durable layer (CLAUDE.md, ndr atoms, README) lives elsewhere. Lifecycle: capture -> draft -> implement -> close.
7 skills · 2 agents
PM helpers for team Linear workflows. Skills for a PM-mode planning session (read the real state, slice work into cold-handoff tickets, confirm every write), single-ticket authoring (a short shaping interview, body composed to the shared issue-body spec), the weekly grooming loop (per-person WIP), plan-to-tickets breakdown (assignee-aware), chart-first mapping of efforts too large to plan in one session, questionnaires that pull a blocking decision out of someone else's head, and end-of-cycle retro notes (attribution + Linear-first output). Composes with the linear plugin; ndr and librarian integrations are optional externals.
7 skills
Interpret Klippain Shake Tune results for 3D printers: diagnose issues from PNG graphs, explain findings, recommend fixes, and track results over time. Supports belt comparison, input shaper, vibration profile, axes map, and excitation tests.
1 skill · 5 agents
A suite of conversational thinking tools — reflect (Socratic mirror, never recommends, always saves), mull (thinking partner, probes AND contributes opinions, saves substantive sessions only), and converge (advisor, leads with a researched recommendation plus confidence % and refines it one question at a time). Plus a paired evaluation track: first-principles (evidence-first interview that produces a signed-off needs map before any option is named) hands off to solution-research (turns that map into a systems-first parallel-research handoff prompt).
5 skills
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.