regression-analysis-modeling
Perform comprehensive regression analysis and predictive modeling using linear regression, decision trees, and random forests. Use when you need to predict continuous values like housing prices, sales forecasts, demand predictions, or any numerical target variables. Includes automated feature engineering, model comparison, and visualization with Chinese language support.
retention-analysis
Analyze user retention and churn using survival analysis, cohort analysis, and machine learning. Calculate retention rates, build survival curves, predict churn risk, and generate retention optimization strategies. Use when working with user subscription data, membership information, or when user mentions retention, churn, survival analysis, or customer lifetime value.
rfm-customer-segmentation
Perform RFM (Recency, Frequency, Monetary) customer segmentation analysis on e-commerce data. Use when you need to analyze customer value, identify VIP customers, or create marketing segments. Automatically cleans data, calculates RFM metrics, applies K-means clustering, and generates visualization reports with Chinese language support.
funnel-analysis
Analyze user conversion funnels, calculate step-by-step conversion rates, create interactive visualizations, and identify optimization opportunities. Use when working with multi-step user journey data, conversion analysis, or when user mentions funnels, conversion rates, or user flow analysis.
growth-model-analyzer
增长模型分析技能 - 提供全面的增长黑客分析工具，包括裂变策略评估、用户细分、Uplift建模、ROI优化等。支持多种增长场景的机器学习建模和智能决策建议。适用于用户增长、营销优化、产品迭代等增长分析场景。
ltv-predictor
基于RFM模型和回归算法的客户生命周期价值(LTV)预测分析工具，支持电商和零售业务的客户价值预测。使用时需要客户交易数据、订单历史或消费记录，自动进行RFM特征工程、回归建模和价值预测。
code-generator
Generates production-ready analysis code in Python, R, SQL. Invoke when user wants reusable code for data analysis, ML, or visualization.
data-analysis
通用的 6 阶段数据分析助手：数据质量→探索性分析→假设生成→可视化→代码生成→综合报告。提供完整的方法论和模板！
data-explorer
Performs exploratory data analysis, statistical analysis, and pattern discovery. Invoke when user wants to analyze data, find patterns, statistical testing, or get deep insights.
hypothesis-generator
Generates testable research hypotheses and experimental designs. Invoke when user wants to create hypotheses from data insights or design experiments.
internet-data-analysis
互联网数据分析技能集合 - 包含AB测试、归因分析、内容分析、漏斗分析、增长模型、LTV预测等专业技能
quality-assurance
Data quality validation and analysis accuracy verification. Invoke when user wants data quality checks, validation, or result verification.
report-writer
Generates comprehensive analysis reports, executive summaries, and technical documentation. Invoke when user wants to create written reports from data analysis.
visualization-specialist
Creates data visualizations, charts, and interactive dashboards. Invoke when user wants to create plots, graphs, or visual representations of data.
codify-context
Codify knowledge from the current session into the right layer of the context architecture (GC, a repo CLAUDE.md, a path scoped rule, a skill's learned rules, a hook, a tool doc, or auto memory), routing by trigger and admitting to always loaded files only through the placement tests. Use this skill whenever the user says "codify" followed by a topic, wants to capture something they just figured out, asks to document a pattern or convention, or says something like "we should write this down" or "future me needs to know this." Also trigger when the user discovers a gotcha, foot gun, or non obvious behavior worth preserving. Named after the "plan, delegate, assess, codify" Level 4 compounding loop. This is the write in counterpart to `assist:groom-context`, which audits and prunes the same context architecture.
create-presentation
Build a polished reveal.js presentation deck for an internal demo, talk, or share-out. Generates a single-file HTML deck with RYLLC brand styling, served locally via `npm run preso`. Use this skill whenever Forni says "build a presentation", "make a deck", "let's prep a demo", "create a preso", references an upcoming demo or talk that needs slides, or invokes `/assist:create-presentation`. Also trigger when Forni wants to walk through work to an audience and asks how to assemble it. Decks live under `preso/YYYY-MM-DD_<slug>/` in whichever repo the work was done.
draft-applications
Drain the work search queue. Consume queued postings from the Pinole work API (through the pinole CLI) and produce a complete application package per role, one at a time, in this order: fit sanity check, cover letter, application question responses, hiring manager research, follow up email draft, then log the application activity and mark the posting applied once Forni confirms submission. Use whenever Forni says "apply to the queue", "run the applications", "apply to <company>", or queued postings exist after a recruiter sweep. Replaces the retired job-apply skill.
groom-context
Audit and redesign the context architecture (every CLAUDE.md, rules file, learned-rules.md, tool doc, and the auto memory index that loads into Claude Code sessions) so rules are stated once, never in contradiction, and enforced at the point of use rather than scattered, duplicated, or buried. Use this skill whenever Forni says "groom context", "groom-context", "we forgot a basic again", "the context is sprawling", "the rules keep getting lost", "clean up the context", or invokes "/assist:groom-context". Also invoked as a closing step by the monthly path of assist:reflect. This is the cleanup counterpart to assist:codify-context, which writes knowledge into the same architecture.
handle-budget
Categorize and approve YNAB transactions, building a payee rules engine that gets smarter each run. Runs as a dry run by default and never writes without explicit approval. Use whenever Forni mentions YNAB, categorizing spend, cleaning up the budget, approving transactions, the unapproved queue, payee cleanup, or wants a clean read on where money is going. Also trigger for "/assist:handle-budget", "tidy the budget", or "categorize my spending".
keep-alive
Keep the session's prompt cache warm while Forni steps away, with a self paced loop that wakes every 50 minutes and does nothing else unless given a watch task, then end it the moment he is back. Use whenever Forni says "keep alive", "keep this alive", "keep the cache warm", "I'm heading out", "going for a run", "back in an hour", or invokes "/assist:keep-alive", optionally with something to watch while he is gone ("keep alive and watch the landers").
mise
Morning prep sync for Forni's workstation. Pulls latest in ~/Eudaimonia and ~/Eudaimonia/Craft/Development/personal/homebase, then runs homebase's setup.sh to deploy dotfiles and refresh brew, npm globals, IDE extensions, and Claude plugins. Use this skill whenever Forni says "mise", "mise en place", "prep the station", "morning sync", "get the station ready", or otherwise wants his dev environment neat and tidy before the day's work. Also trigger for "/assist:mise". Named after mise en place: everything in its place before service.
permissions
Hoist project-level permissions into user-level settings, collapsing similar entries into wildcards. Use this skill whenever the user says "hoist permissions", asks to clean up their project permissions, wants to promote permissions to user level, or mentions that they're tired of re-approving the same tools across projects. Also trigger when the user says "move permissions up" or asks for help organizing `.claude/settings.local.json`.
plan-meals
Weekly meal planning, shopping list generation, and pantry aware grocery runs. Produces a plant based, seasonal, batch prep friendly meal plan for the week, authored into the Pinole app, plus a consolidated shopping list grouped by store. Use this skill whenever the user mentions meal planning, wants to plan the week's food, asks for a shopping list, wants help figuring out what to cook, mentions batch prep, macros, recipes, a grocery run, a Sprouts or Costco trip, or says things like "back on the healthy eating train" or "kick the takeout habit." Also trigger for "/assist:plan-meals", "meals for the week", or "what should I cook". Prefer invoking this skill even when the user's ask is oblique (e.g., "I want to stop eating out" or "I need to hit my macros this week") since meal planning is usually the underlying need.
plan-training
Training plan scheduling, weekly retrospectives, and training adjacent constraint validation. Use this skill whenever the user mentions training, lifts, runs, swims, yoga placement, recovery days, the recomp block, asking to schedule a training session, or asking to look back / retrospect on a past training week. Also trigger for "/assist:plan-training", "schedule my training", "what does training look like this week", "how did last week go", "training retro", "this week's lifts", or any request that touches the block plan in `Constitution/Fitness/`. Independently usable, and also called by `/assist:plan-week` during Monday planning.
plan-trip
Group trip and getaway planning. Scope the trip, pull live lodging availability, present options with per head cost, verify before booking, research the constraint that actually drives the trip (weather windows, permit and reservation release dates, access rules), hand off the booking, then capture a trip doc and schedule the time sensitive follow ups. Use this skill whenever Forni mentions planning a trip, a getaway, a group house, a cabin or Airbnb or VRBO for a crew, a basecamp for a race or hike or backpacking objective, finding lodging for friends, splitting a house, acclimation lodging, or asks "where should we stay", "find us a place", or "book the house" for an upcoming adventure. Also trigger for "/assist:plan-trip", "plan the Aspen trip", "find a house for the boys", or "we need a place for the loop weekend". Trip records live under `~/Eudaimonia/Craft/Adventure/`; this skill is the workflow counterpart to the Adventure planning conventions documented there.
plan-venture
Direction-setting session for a venture. First-principles positioning (Dunford), adversarial critique walked one finding at a time, brand and naming decisions, a multi-fidelity roadmap, and full artifact true-up (docs, Linear, calendar, Todoist). Use this skill whenever Forni wants to plan a business's direction, asks "what is this business", wants to work through positioning or strategy from scratch, questions whether the ladder is against the right wall, wants a brand or naming workshop, or invokes "/assist:plan-venture". Also trigger for a Monday planning block that turns strategic ("direct the energy before scheduling more work"). Weekly slotting stays in assist:plan-week; this is the deeper, occasional session that decides what the weeks are for.
plan-week
Weekly planning, calendar management, and Monday planning session task slotting. Use this skill whenever the user mentions weekly planning, the Monday planning session (07:00, first thing in the deep work block; it ran on Sundays until 2026-08-30), slotting tasks, finding free time, checking what their week looks like, moving or swapping calendar events, or wants help fitting something into their week. Also trigger when the user asks about V2MOM measure coverage. Training plan scheduling lives in `assist:plan-training`; this skill calls into it during the weekly planning session.
refine-process
Refine a recurring process (a skill's workflow, a checklist, a pipeline of phases) through a structured, iterative pass with the user. Use this skill whenever Forni says "refine this process", "take a pass at this workflow", "the phases feel off", "let's rework how we do X", or asks for a watchful or deliberate redesign of any multi step process. Also trigger when a process refinement emerges mid session (directives like "move phase X before Y" or "merge these steps") and the user wants it done properly rather than ad hoc. The refinement counterpart to `assist:codify-context` (which writes knowledge) and `assist:groom-context` (which prunes it); this skill reshapes workflows.
reflect
Guided reflection at the boundaries Forni looks back on (weekly, monthly, quarterly, yearly). A dialogue-driven retrospective, not a journal reader. Brings the quantitative spine the paper journal misses (movement, overconsumption tally), then reflects by conversation against the V2MOM frame. Use this skill whenever Forni says "reflect", "let's reflect", "reflect on the month", "monthly reflection", "look back on May/the month/the week", "end of month", "retrospective", "retro", "weekly reflection", or invokes "/assist:reflect". Also trigger at quarter or year boundaries when Forni wants to look back. Monthly is the default. Weekly retro is also called by `assist:plan-week` before planning the next week. Quarterly hands off to the V2MOM eval walk.
report-unemployment
File the weekly Colorado unemployment payment request in MyUI+ from the activities ledger in the Pinole work API. Builds the reportable activity slate for the just ended claim week, drives MyUI+ through agent-browser attached to Forni's real Brave, walks the weekly payment request screens, and stops hard at both certifications for Forni's explicit yes. Use whenever Forni says "report unemployment", "request UI payment", "file the weekly claim", "MyUI+", mentions the Monday payment request task, or invokes /assist:report-unemployment. The claimer agent carries this method for background dispatch.
sharpen-saws
Run the weekly sharpen audit that moves collaboration one small step toward Levels 7 and 8 of the agentic engineering hierarchy. Verify each unattended routine fired and was consumed, close or ticket every deferral, take one cut from the always loaded context, groom one flag, and append a one screen log entry to LEVELS.md. Use this skill whenever the user says "sharpen", "sharpen saws", asks to "sharpen our process", or explicitly starts a sharpen session. Paired with the weekly Sharpen Saws block on Wednesdays. The sharpener agent carries this method for background dispatch.
triage-inbox
Triage the Gmail inbox to a settled state. Classify every email, draft a reply for anything needing a response, and turn action-without-response into a Todoist follow-up, then review and execute one email at a time. Handles unsubscribes, recurring-sender filters, and per-sender side actions inline as they come up. Use whenever the user mentions email triage, inbox cleanup, processing the inbox, clearing email, or getting to inbox zero.
wrap
Session wrap. Don't lose the thread, clean everything up, don't leave loose ends in your head. Scans every git repo touched this session for uncommitted or unpushed state, surfaces external commitments (pending replies, calendar holds, contract deadlines) from the recent conversation, prompts for codification of durable learnings, logs each loose end the user triages to Todoist (today if pressing, next Sunday otherwise), summarizes the session, and closes with a compaction ready line. Run it yourself, unprompted, the moment the session reaches its terminal state (the work landed, tickets closed, no question open), with a one line heads up rather than an offer. Also use it whenever the user says "wrap", "wrap up", "wrap the session", "wrap this up", "wrapping up", "clean up before I exit", "signing off", "done for the day", or invokes /assist:wrap. Pairs with /assist:mise as the bookend. Mise opens the kitchen for service. Wrap closes it cleanly after.
linear-lifecycle
Use when working with Linear issues, issue tracking, or project management. Uses the Linear CLI for zero-context issue management as a CLI alternative to MCP.
checkpoint
Save work in progress with commit and push (no PR). Use this when the user wants to save progress, push a checkpoint, or back up current work without creating a pull request.
complete
Finish work and reset local environment for next task. Use this when the user is done with a feature branch, wants to clean up after a merged PR, or needs to reset their workspace.
design
Start work on an issue with branch setup and implementation design. Use this whenever the user wants to begin a new task, start on a ticket, or set up a feature branch for development work.
groom-issues
Groom a Linear team's queue. Two modes, cycle grooming (when the team runs Linear cycles, trim the active cycle to a realistic slate) and backlog grooming (when the team has a backlog without active cycles, triage by priority, staleness, and intent). Use whenever the user mentions Linear grooming, triaging issues, pruning a backlog, sprint grooming, "the cycle is overstuffed", "let's clean up the queue", "groom the backlog", or wants to make decisions across many issues at once. All Linear access goes through the `linear` CLI.
iterate
Address PR review feedback and re-run the CodeRabbit CLI review on the new HEAD. Use this when the user needs to handle PR comments, respond to code review, or iterate on feedback from reviewers.
land
Drive the back half of SDLC autonomously. Run the CodeRabbit CLI review as the gate, watch CI, triage findings, merge (squash), then clean up. The agent (not GitHub) judges when feedback is addressed. Bails to the user on human review, hard CI failure, merge conflict, or time budget exceeded. Default next step after implementation; use when the user says "land it", "ship this", "merge when ready", or invokes /sdlc:land.
plan
Refine requirements on a Linear ticket through Socratic dialogue. Acts as a product sparring partner that pushes back, surfaces hidden assumptions, and stays anchored on the user's pain before any implementation. Use this when the user wants to think through a problem, clarify requirements, or evaluate options before starting design work.
review
Create PR for code review. Use this when the user is ready to submit their work, create a pull request, or send code for review.
photo-color
Adjust photo brightness, contrast, and saturation based on natural language prompts using GPT-5 text analysis. Use when the user asks to adjust brightness, change contrast, modify saturation, apply a specific style, or fix photo issues like washed out colors.
talk-dig
Analyze academic talk posters to discover and summarize the speaker's relevant papers. Extracts speaker info and topic from poster images, searches for their papers online, and provides comprehensive summaries.
todo
Systematic todo management approach. Analyze task clarity before adding; ask for details when needed to ensure actionability. Uses Obsidian's todo.md with three regions: Important (重要), Todo, Finish (完成). Trigger when user says "添加任务", "新任务", "记录待办", "管理任务" or needs task reasoning, priority judgment, or task breakdown.
config-backup
Use when users want to save, backup, copy, export, or version control their Claude Code configuration files (commands, skills, agents) from ~/.claude/ to another directory. Triggered by phrases like "save my claude settings", "backup my claude config", "sync claude configuration", "copy ~/.claude to somewhere", "export my commands and skills", or "archive claude settings before making changes".
config-restore
This skill should be used when users want to restore, reload, or copy their Claude Code configuration files (commands, skills, agents) from a backup directory back to ~/.claude/. Triggered by phrases like "restore my claude config", "reload claude settings", "copy config back to ~/.claude/", "restore from backup", "recover claude configuration", "import commands and skills from backup", "I accidentally deleted my commands", "restore my old skills", "copy config from backup", or "I need to recover my claude settings from a backup".
idea
Record ideas and thoughts to Obsidian vault. Creates structured idea notes with problem analysis and tags. Use when user says "记录想法", "有个idea", "记一下", "记录疑问", or captures inspiration/questions about technical problems, architecture, or research.
notebooklm
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.
photo-clipper
Crop photos intelligently based on natural language prompts using GPT-5 vision analysis. Use when the user asks to crop or trim a photo, remove parts of an image, focus on a specific subject, improve composition, or remove distractions from edges.
Page 632 of 1646 · 82296 results