weekly-task-audit
Scans last 7 daily notes to find rolling tasks, yo-yo patterns, and chronically stale items. Use when "task audit", "audit my tasks", "what rolled forward".
Найдите подходящую возможность для вашего агента.
Scans last 7 daily notes to find rolling tasks, yo-yo patterns, and chronically stale items. Use when "task audit", "audit my tasks", "what rolled forward".
Compress memories into structured summaries using low-cost AI models (Claude Haiku, GPT-4o-mini). Triggers when memory count exceeds 50 or token estimate exceeds 40000. Outputs structured JSON with compression metrics.
Generates 14–21 day running plans tailored to onboarding data and recent performance.
Responsive design assistance including breakpoint generation, fluid typography, container queries, and mobile-first/desktop-first strategy guidance. Use when creating responsive layouts or adapting designs for multiple screen sizes.
Troubleshoot Olakai monitoring issues. Use when events aren't appearing, KPIs show wrong values, or custom data is missing.
Create and validate breathing-synchronized features for breathe-together-v2. Mode 1 creates visual features responding to UTC-based global breathing cycle (inhale/hold/exhale/hold). Mode 2 validates and debugs why entities aren't responding visibly to breathing synchronization. Includes integration patterns, ECS trait querying, system registration, damping/easing, and systematic 8-point validation.
Create weekly summaries by aggregating daily summaries for Gastrohem WhatsApp conversations. This skill should be used when the user asks to generate weekly summaries, see what happened during the week, or prepare plans for next week (e.g., "Make weekly summary", "Generiši sedmični summary", "Weekly report for 20.10-27.10"). Aggregates activities per person, detects completed tasks, and generates next week's plan.
Claude Code プラグインの skill 仕様知識。スキルの正しい形式、フロントマター、description のベストプラクティスを提供。Use when creating, updating, or maintaining skills, understanding skill structure, or implementing SKILL.md files. Also use when user says スキル, SKILL.md, skills.
Translates planned workouts into execution cues, purpose explanations, and common mistakes to avoid. Use before workouts when user asks "what should I do?" or "how do I run this session?" with beginner-friendly guidance.
UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
Expert guidance for creating stunning, professional 2025 UI designs using Tailwind CSS and shadcn/ui. Ensures clean minimal aesthetics, 8px grid consistency, mobile-first responsive patterns, and WCAG accessibility compliance. Use when designing interfaces, reviewing UI, creating components, or when visual design needs modern professional standards.
MCP-free Todoist integration with GTD coaching. Uses Python CLI (scripts/todoist.py) to query Todoist API v1 directly. Provides semantic understanding of the user's GTD structure (outcomes as sections, team vs personal, 3-tier ontology), query patterns, and outcome quality coaching. Also handles weekly review orchestration and pattern detection. Triggers on 'clean up outcomes', 'team priorities', 'Q4 review', 'is this a good outcome', 'weekly review', 'am I overcommitting', 'check my patterns', 'should I take this on', 'I said yes to', 'another meeting', 'they asked me to', 'scope creep', 'this grew into', 'freedom score', or ANY Todoist-related task. (user)
Autonomous browser agent for complex multi-step web tasks. WHEN: User needs complex web automation, multi-page workflows, form filling sequences, tasks requiring multiple browser actions. WHEN NOT: Simple single-action tasks like one click (use browser_click), one navigation (use browser_navigate), one extraction (use browser_extract_text).
See the main Data Freshness and Latency skill for comprehensive coverage of freshness monitoring and SLO tracking.
Mobile-first responsive design patterns for Slotify. Use this skill when building UI components, implementing responsive layouts, or optimizing for touch interactions. Covers Tailwind CSS breakpoints, touch targets, and PWA considerations.
Role and project workload overview. Use when user wants to see their current workload, role balance, or status across roles/projects. Auto-triggers on phrases like "how am I doing", "workload", "what's on my plate", "role balance", "project status", "hur ligger jag till", "arbetsbelastning", "rollbalans".
Identifies missed training sessions and proposes plan reshuffles with motivational support. Use for weekly check-ins, when multiple sessions are skipped, or when user asks for help getting back on track.
Manage a personal knowledge capture system. Use when the user wants to capture ideas, track todos, organize projects, review their synap, or mentions "synap", "brain dump", "capture this", "add to my list", "what's on my plate", "what should I focus on", or "daily review".