发现 Skills

Demonstrates skill structure with progressive disclosure and best practices for skill development

Run a structured reflection or debrief after any learning experience, project, procedure, or performance to turn raw experience into durable skill. Use this skill whenever the user wants to do an after-action review, write a learning journal entry, debrief a session, run a post-mortem, reflect on what went well and what to improve, turn a recent experience into a lesson they will remember, create a reflection document after completing a course chapter or training, or consolidate learning from a recent event — even if they do not use the words "reflection" or "retrieval." Works for students, professionals, coaches, clinicians, writers, teachers, and anyone learning from experience. Do NOT use this skill to build a spaced repetition quiz system (use retrieval-practice-study-system) or to analyze an external document for content (use a different skill).

Multi-agent council using real subagent spawning (Task() tool), deterministic CLI state management, and file-based handoffs. Orchestrator stays lean while specialists execute in fresh contexts.

Opportunity Solution Tree (Teresa Torres) — a continuous discovery artifact mapping desired outcomes → opportunities → solutions → assumption tests. Use when prioritizing discovery work, structuring weekly customer interviews, mapping multiple solutions to one problem, or auditing whether your roadmap actually moves outcomes.

Systematic performance profiling for Node.js, Python, and Go applications. Covers CPU flamegraphs, memory leak detection, bundle analysis, database query optimization, N+1 detection, load testing with k6, and before/after measurement methodology. Use when diagnosing slow endpoints, memory growth, large bundles, or preparing for traffic spikes.

Tailor a resume to a specific job description by extracting target keywords, scoring keyword match, and rewriting bullets for impact and relevance. Use when applying to a specific role, optimizing for ATS keyword match, or when the user mentions resume tailoring, job application, ATS optimization, or cover letter customization.

Create API services and React Query hooks for data fetching

Example scaffolding and checklists for developing Home Assistant custom integrations. Use when building or reviewing a custom integration based on the included example templates.

International tax structures — double taxation treaties, BEPS, Pillar 1/2.

name: signal-processing description: Signal processing for financial data — wavelets, Fourier analysis, noise filtering. Use when extracting signals from noisy financial data.

Find incomplete migrations, legacy fallbacks, dual code paths, and deferred work causing unnecessary complexity. Entry point for /do-more:deferred-work-cleanup command.

Keep track of systemic problems with your workflow so they don't get lost. Add items, or run a retrospective to brainstorm and implement solutions. Entry point for the /do:retro command.

Audit alignment across strategy, architecture, plans, and implementation. Ensures planning documents remain effective and aligned over time. Supports quick, medium, and thorough intensity levels.

Review and delivery phase — user reviews the completed build, then chooses how to finish (merge, PR, keep working, or discard). Use after the build phase completes all vertical slices.

Your product sounding board. Work through product decisions conversationally — Claude gathers context, challenges assumptions, captures decisions, and creates Linear issues.

Validate API behavior against expected contracts using captured requests, responses, and schema checks.

Generates business/company names across 10 categories (Descriptive, Metaphoric, Invented, Founder-based, Acronym, Compound, Foreign, Playful, Geographic, Legacy) with USPTO trademark screening, domain availability checking, and 0-100 scoring. Use when users need company/product/brand naming for new business launches, rebranding, trademark strategy, IP protection naming, evaluating current name strength, or any naming/branding tasks requiring systematic analysis with legal clearance.

Unified database operations for the BidDeed.AI and Life OS ecosystems. Use when: (1) logging insights, activities, or learning sessions, (2) querying historical data from any table, (3) the user says "log this" or "save to database", (4) storing auction results, task states, swim times, or health metrics. Database: mocerqjnksmhcjzxrewo.supabase.co

Use this skill whenever the user asks for two or more Zotero actions in one request, especially resolve-then-write chains such as metadata lookup, local attachment discovery, note updates, collection placement, attachment import, attachment replacement, or trash.

Give structured feedback using the SBI model and CFR framework

Social media content creation and scheduling strategy

Add "Open in molab" badge(s) linking to marimo notebooks. Works with READMEs, docs, websites, or any markdown/HTML target.

Create Cursor rules for persistent AI guidance. Use when the user wants to create a rule, add coding standards, set up project conventions, configure file-specific patterns, create RULE.md files, or asks about .cursor/rules/ or AGENTS.md.

Scrapes posts from any public Facebook Page or personal Profile timeline, returning structured data including post text, author info with profile picture, engagement metrics (likes/comments/shares), full reaction breakdown (Like/Love/Wow/Haha/Sad/Angry/Care as both array and flat counts), hashtags and external links, media assets with full thumbnail URLs and dimensions, page ad library status, and collaborators. Use when user wants to scrape Facebook posts, extract Facebook page content, get Facebook post data, collect Facebook engagement stats, download Facebook posts, monitor a Facebook page, crawl Facebook timeline, get Facebook reactions, get like count comment count share count from Facebook, Facebook post bulk export, Facebook social media analytics, get profile picture, get page ad library status, fetch Facebook collaborators. Supports date range filtering (afterTime/beforeTime) and cursor-based pagination for bulk collection.