claude

alex

Alex's cross-project skill library — product, engineering, GTM, data, and operating discipline.

1 on GitHubby Alex Yedibalianv0.8.0MITupdated 3 days ago
/

Plugin alex from marketplace alex-agents-skills in AlexYedi/alex-agents-skills. Commands read from the repo's manifest — 3 days ago.

What it installs

Skills (200)

  • content-correspondent

    Post-event content and outreach sequencing for NYC AI/tech events. Use this skill any time Alex mentions attending an event, returning from an event, or wants to follow up after one — even casually ("just got back from a founder session", "I'm at PMF x AI tonight", "need to write something about las

  • cto-architect

    Principal-level CTO and lead architect for technical strategy, system design, and build planning. Use when Alex asks for architecture help, system design, build planning, or CTO-level input — "architect this", "how should I build X", "review my technical approach", "CTO hat on", "let's do a build se

  • pattern-synthesis

    Generate a two-thesis synthesis LinkedIn post from two event research briefs. Use this skill when Alex wants to contrast two events into a single strategic post, when two event briefs in the same week pose opposing theses, when synthesizing ephemeral NYC AI/tech experiences into a recognizable docum

  • post-event-content-generator

    Generates the full post-event content and outreach output once Alex has raw event material to work from — voice notes, Granola transcripts, contact names, or even a quick freeform recap. Use this skill when Alex is ready to produce: contact bucket sorting, outreach DM drafts (per bucket), a LinkedIn

  • the-meddpicc-enterprise-deal-desk

    Evaluating large, complex enterprise deals, stress-testing account strategies, drafting executive-level business cases, or orchestrating multi-threaded buying committees.

  • winning-by-design-sales-excellence-framework

    Winning by Design\" Revenue Architect: Design scalable playbooks, map the customer journey, diagnose pipeline leaks, and write messaging centered around customer impact rather than product features.

  • event-research

    Research an upcoming event from a pasted calendar invite. Produces a structured brief, writes to Notion (5 databases) and HubSpot (contacts, companies, notes), and optionally enriches speakers via Apollo.

  • pre-event-content

    Generate pre-event content for NYC AI/tech events from completed research briefs. Produces LinkedIn posts (personal and "The Upcoming Week" roundup), speaker/host DMs with personalization, and prepared questions. Writes to Notion Content Drafts database. Use when Alex says "draft pre-event content f

  • project-ideation

    Generate project proposals from event topic intersections. Produces 3 scored ideas (2 feasible + 1 stretch) with architecture, timeline, and content moment analysis. Writes to Notion Project Ideas database.

  • update-anti-patterns

    Quick-access management of Alex's content anti-patterns list — add, remove, append, or amend words, phrases, or entire pattern categories. Use when Alex says "add [word] to the off-limits list", "remove [word] — I actually use that", "add a new anti-pattern category for X", "update the anti-patterns

  • update-voice-and-style

    Capture learnings about Alex's content voice and style preferences and propagate them to reference files and dependent content skills. Use when Alex gives feedback on generated content ("this felt too formal", "the hook on B was better because..."), when voice patterns emerge across multiple session

  • interview-prep-dossier

    Generate a job-search interview-prep dossier tailored on four axes — company × role × interview stage × interviewer. The first lens of the Market-Intelligence Engine. Use when Alex has an interview coming up and pastes a JD + company + interviewer + stage. Produces a synthesized dossier (Quick Take,

  • judge-build

    Build-quality judge: ONE Claude Sonnet reviewer scores a build artifact (a file, a file list, or a git range / PR) against build-quality@6, defects before scores, and raises flags. The harness computes the score and the final pass/flag (guarded privacy/spine paths always need human review). Alex is

  • role-radar

    Signal scanner — job search & tracking. Aggregates roles from legitimate sources (ATS boards APIs — Greenhouse/Lever/Ashby/Workable via curl — primary; + Apollo-at-targets, credit-gated, optional), dedupes on the ATS job-id, scores each against Alex's Target-Role ICP (me-model §1.5), and lands them

  • steering-interview

    Two-touch collaborative steering for any content deliverable. TOUCH 1 (Aim) — a light, skippable intake BEFORE research that points the fan-out (what to research deeper, who it's for, any strong upfront take). TOUCH 2 (Sharpen) — the collaborative gate AFTER the research/prep, where 2–3 genuine fork

  • tag-outcome

    Manual outcome-tagging ritual (<5 min) that closes the acted-on-value loop. Finds published Content Drafts that have an assigned Goal but no recorded Outcome, pulls the realized signal by goal type (HubSpot for connection/meeting; LinkedIn-native numbers for reach/engagement; owned-asset web analyti

  • objection-mining

    Systematically extract, classify, and pre-handle prospect objections from sales data. Build objection playbooks that turn 'no' into 'tell me more' — in cold outreach, discovery calls, and follow-ups.

  • transcript-analysis

    Extract actionable intelligence from sales call transcripts. Systematic frameworks for mining discovery calls, demos, and follow-ups to improve messaging, objection handling, and close rates.

  • transcript-conditioning

    Condition a raw single-event ASR/diarized transcript into reliable content inputs — resolve diarized 'Speaker N' labels to a known roster, normalize ASR-mangled entity names against a pre-event brief, and extract a confidence-scored verbatim quote bank. Upstream of content-correspondent. Use when po

  • account-tier-scoring

    Tier a book of accounts with Clay — turn a raw account list plus your ICP definition into tuned, auditable tiers (1–4 or A–F) with every score decomposed into visible, editable weights. Use whenever someone asks: tier my accounts, score this account list against our ICP, which accounts deserve outbo

  • account-tiering-workflow

    Stand up an always-on account-tiering workflow in Clay — a signal-triggered pipeline that fires per account as it enters an audience, enriches it, scores its fit for your product, tiers it, and writes the result back onto the record with no one in the loop. Use whenever someone asks: build me an acc

  • alert-reps-on-account-signals

    Turn a rep's target-account list into Slack alerts — load the accounts into a Clay Audiences segment, watch that segment with three Clay Signals (news and fundraising, new leadership hires at C-suite, VP, director and head level, and job postings), and post one Slack message per event into a channel

  • auto-research-public

    Autonomous cold email campaign launcher. Takes one target company domain, scrapes their website, generates an ICP with Claude, pulls matching leads via Prospeo, enriches emails + company descriptions, personalizes each lead with parallel Claude Code Task sub-agents (A/B/C variants), and uploads as a

  • blitz-list-builder

    Use the Blitz API to find decision-makers at specific companies when you already have a list of company domains. Best for SMB owner-finding, domain-to-people lookup, or supplementing Prospeo results. Outputs a CSV you can feed to the email-waterfall or directly to /cold-email-starter-kit for Smartle

  • campaign-copywriting

    Creates cold email copy through a stepwise confirmation process. Use when writing email campaigns, given a campaign strategy document, website, or client context. Confirms direction at each step before outputting final copy.

  • campaign-strategy

    Generates 15-25+ cold outbound campaign ideas with targeting strategies, AI personalization approaches, and value propositions. Use when planning campaign experiments for a client, given their website or business context.

  • clay-icp-matrix

    Turn an ICP described in your own words into an executable matrix — every dimension translated into the exact field and allowed value the platform will accept, classified as filterable now, verifiable later for a per-row price, or not observable at all. It reports what failed to translate instead of

  • clay-playbooks

    Index and shared harness for the 19 signal playbooks. Each playbook turns one buying signal (new in role, raised a round, hiring surge, pricing page, tech on website, ...) into one copy-ready sentence you can drop into a cold email. Every playbook ships three ways to run it: as a Claude skill, as a

  • cold-email-kickoff

    Single "start here" orchestrator for new cold email operators. Asks infrastructure-status questions first, then runs /icp-onboarding → /lead-magnet-brainstorm → /campaign-strategy in sequence, producing a consolidated campaign-plan.md. Ends with an interactive menu of next skills branched on whether

  • cold-email-starter-kit

    Complete beginner-friendly cold email toolkit. Walks from zero to launched campaign — domain purchase, inbox setup, list building, copywriting, enrichment, and sending via Smartlead or Instantly. Use when setting up cold email for the first time, launching a new campaign, teaching someone cold email

  • cold-email-weekly-rhythm

    Operational playbook for running cold email continuously. Prescribes what to do on Monday / Wednesday / Friday / biweekly / monthly / quarterly. Use this as your ongoing cadence once your first campaign is live. What separates hobbyist from top 1% operators isn't tooling — it's consistency. This ski

  • deliverability-incident-response

    Triage playbook for when cold email deliverability breaks. Decision-tree guidance for "I landed in spam", "bounce rate spiked", "domain blacklisted", "inbox blocked in warmup", "reply rate dropped". Tells you what to check first, what to fix, and how long the fix takes. Pair with /email-deliverabili

  • deliverability-test-public

    Compare reply rates, bounce rates, and positive reply rates broken down by inbox type (SMTP / Gmail / Outlook) for a Smartlead account. Use when you want to know "which inbox type delivers best" or when debugging unexplained deliverability differences across a mixed fleet. Operates via Smartlead API

  • disco-like

    Find lookalike companies via DiscoLike's 65M+ business domain database. Search by seed domains ("find companies like clay.com and apollo.io") or natural-language ICP text ("B2B cold email outreach"). Supports negation domains (exclude competitors/existing customers) and country filtering. Use when y

  • email-deliverability-audit

    Diagnostic audit for a running cold email program. Checks domain authentication (SPF/DKIM/DMARC), inbox health/reputation from Smartlead, bounce rate by inbox type, and optionally runs a spam placement test via Smartlead's Smart Delivery API. Outputs markdown report + CSV with per-domain/per-inbox s

  • event-follow-up-router

    Turn an event or webinar registrant export into a synced campaign plus a routed follow-up plan — reconcile every registrant against your CRM for free, write a campaign status for ALL of them including the ones nobody will contact, create records for the registrants your CRM has never seen, then qual

  • experiment-design

    Framework for running single-variable cold email experiments. Defines experiment types (list-only, copy-only, combined), confidence weighting, minimum sample sizes, and success criteria. Use when the user wants to improve a campaign, test a new list vs old one, or compare copy variants. Prevents the

  • find-decision-makers-at-company

    Find the actual decision-makers at a specific company with Clay — the named people, with title, LinkedIn, seniority, and current-employment evidence — for the thing YOU sell, not just whoever ranks highest. Use whenever someone asks: who are the decision makers at this company, find the VP of engine

  • get-top-conference-attendees

    Takes in (or finds) attendees you should connect with at your next conference, ranks and researches them, and adds them — along with their full research dossiers — to your Clay Audiences so you can enrich further or take action on them.

  • google-maps-list-builder

    Scrape Google Maps for local businesses by category and location, output CSV ready for cold email enrichment. Best for SMB campaigns targeting restaurants, clinics, gyms, salons, contractors, etc. Uses RapidAPI Maps Data API. Output feeds directly into /blitz-list-builder (to find owner contacts) or

  • icp-onboarding

    Conversational intake for cold email campaigns. Interviews the user about their business, ICP (Ideal Customer Profile), offer, lead magnets, and hard vs soft filters. Outputs a structured `client-profile.yaml` that every other skill in the repo reads from. Use at the very start of a new campaign or

  • icp-outbound-campaign

    Build an outbound campaign from your ideal customer profile: interview you for the ICP (who the buyer is, which companies, where, how many), turn it into a Clay people search you confirm in plain words, widen in declared tiers only if the strict ICP cannot reach your target, strip titles that match

  • icp-prompt-builder

    Interactive loop that builds and tunes an AI prompt for evaluating whether a company fits a client's ICP. Run after any list-building skill (disco-like, blitz-list-builder, google-maps-list-builder, prospeo-full-export) to qualify companies before scaling. Iterates batches of 10 companies with user

  • inbox-lifecycle-manager

    The weekly keep/cancel/promote/buy loop for a cold email sending fleet. Decides which domains are burned and should be cancelled, which warmed reserves to promote into campaigns, which capacity to demote, and how many new domains to buy — using measured reply, bounce, age and send-volume floors inst

  • kill-or-keep

    Judge every live outbound campaign against thresholds set before anyone looks at the numbers, and return one verdict per campaign: fix deliverability first, kill, scale, keep going, or too small to judge. One metric decides it, positive replies per send; opens and raw reply counts decide nothing. Re

  • lead-magnet-brainstorm

    Helps the user come up with free lead magnets or hooks to offer in cold emails. Asks about their business, what they can legally give away, and what would be genuinely valuable to their ICP. Returns 5-10 concrete offer ideas with example CTA phrasings. Use when the user says their campaign "needs a

  • list-builder

    META skill — build the largest possible qualified lead list for any request, end to end. Orchestrates discovery (Prospeo + GetLeads + Blitz + Google Maps + lookalike snowball from /list-expander), AI qualification with live-website verify, uncapped contact pull (GetLeads → Blitz → Prospeo), and prov

  • list-clearance

    Check a lead list before it goes anywhere near a sequencer, and return one verdict for the whole list: go, fix, or no-go. Seven gates, each pass or fail on its own: buyer title, firm fit, verified email, no block-list or suppression hit, not already in a live campaign, required fields present, and c

  • list-expander

    Expand a hard-to-build niche list from ~10 known-good seed companies into a full qualified TAM. Seed fingerprinting (how do good-fit companies ACTUALLY show up in the company database's filters) → lookalike generation (Prospeo company_lookalike, Exa findSimilar, Parallel.ai entity search) → filter m

  • list-quality-scorecard

    Pre-send quality scorecard for any lead list. Grades duplicate rate, title diversity, bad-title patterns, catch-all domain density, ICP fit, email verification coverage. Outputs a letter grade + action items BEFORE you send. Catches bad lists before they burn inboxes. Run after email enrichment, bef

  • monitor-buying-signals

    Watch a fixed list of target accounts for buying signals with Clay — funding rounds, M&A, executive hires, expansion and other news events — and turn each sweep into an evidence-backed digest of who to act on now. Use whenever someone asks: monitor my target accounts for buying signals, alert me whe

  • perfect-company-list

    Build a near-complete company list for any ICP by learning how your real customers label themselves, pulling every industry and keyword they use, judging every single row with a cheap AI model (Jev or gpt-5-nano), and running a Claygent lookalike loop until it runs dry. The method from the SCULPT 20

  • personalization-subagent-pattern

    Reusable approval-loop pattern for fanning out lead personalization across parallel Claude Code Task sub-agents. Shows the user 1 sample personalization, collects feedback, runs 10 more, approves, runs 10 more — stops when 2 consecutive rounds have zero edits, then scales to the full list. ALWAYS us

  • playbook-ad-library

    Produces a line about what a company is currently advertising on Facebook and Instagram, from the Meta Ad Library. Triggers on "are they running ads", "what are they advertising", "meta ad library", "facebook ads", "pull their ad copy", "who is spending on paid social". Outputs ad_library_line, a lo

  • playbook-ai-specificity

    Writes the one sentence that makes a generic offer feel written for this one company. Produces the tail of "I think we can help you ___". Triggers on "specificity line", "make it feel specific to them", "the specifically sentence", "why would they think this is for them", "personalize the offer not

  • playbook-case-study-page

    Finds a prospect company's own case-study or customer-stories page and pulls one named customer off it, so email 1 can open with "saw your work with Intercom". Triggers on "case study", "customer stories", "who are their clients", "saw your work with X", "name-drop one of their customers", "logos on

  • playbook-company-name-cleaning

    Turns the raw company-name string on a lead row into the short human form a person would say out loud, so it can be dropped into email copy. Triggers on "clean these company names", "company name variable", "strip the LLC and Inc", "the company names look robotic", "normalize company names for the c

  • playbook-creative-ideas

    The 3-bullet creative ideas email. Produces three per-company bullets that each sit in a slot the operator defined up front, so the model fills in the company detail and never invents a new idea. Triggers on "creative ideas campaign", "three ideas email", "I had a few ideas for you", "3 bullets", "u

  • playbook-first-name-cleaning

    Turns the raw first-name field on a lead row into the name a person would actually be greeted by, so it can open an email. Triggers on "clean these first names", "first name variable", "the greeting says Hi DR MATTHEW", "strip the titles off the names", "some rows have the whole name in the first-na

  • playbook-fundraising

    Produces a copy-ready sentence about a company's funding round, and the list-building filters that select companies which have ever raised or raised recently. Triggers on "raised a round", "recently funded", "companies that raised", "Series A list", "VC backed", "post funding outreach", "who just ra

  • playbook-google-site-search

    Checks whether a company''s own website mentions a specific keyword, using one simple Google site: query per keyword through a SERP API, and turns the hit into a copy-ready line. Triggers on "does their site mention X", "site: search", "find companies whose website says X", "filter this list by a ke

  • playbook-hiring-surge

    Produces a copy-ready clause about a company adding people to one specific department in the last 6 months, plus the department-level headcount counts that drive the segment gate. Triggers on "they're hiring", "hiring surge", "growing their sales team", "scaling the team", "headcount growth", "who a

  • playbook-job-posting-language

    Produces a copy-ready clause about a role a company is currently hiring for, filtered by language the client cares about (for example "cold call", "outbound prospecting", "Salesforce"). Triggers on "they're hiring", "job posting language", "who is hiring SDRs", "companies hiring for X", "find the hi

  • playbook-lookalikes

    Turns one customer case study into the tightest list of companies that would read that case study and see themselves. Decomposes WHY the case-study company resonates into concrete attributes, translates those attributes into database filters, intersects them with a lookalike anchor, then widens with

  • playbook-name-to-other-prospects

    Names 2 other right-fit people at the prospect's own company so an email can ask "is this you or them?" without ever naming the person being emailed. Triggers on "name two other people at the company", "who else works there", "should I be talking to someone else", "colleague name variable", "other p

  • playbook-new-in-role

    Produces a copy-ready clause about someone who recently started or changed into their current job title. Triggers on "who just started", "new in role", "recently promoted", "new VP of X", "job change signal", "people who just took the seat". Outputs new_in_role_line, a lowercase clause that complete

  • playbook-pricing-page

    Decides whether a company publishes public self-serve pricing and extracts its plan tiers, price points and feature axis. Triggers on "do they have a pricing page", "is their pricing public", "filter out enterprise quote-only companies", "what do they charge", "find their plans", "self-serve vs sale

  • playbook-social-link-finding

    Resolve a company domain to its verified official social profile URLs (LinkedIn, X, Facebook, Instagram, YouTube, TikTok). Triggers on "find their LinkedIn", "get the company LinkedIn URL", "find their Instagram", "we need social handles for this list", "which companies have a TikTok", "social links

  • playbook-tech-on-website

    Decides which named technologies a company actually runs on its website, verified against the live site. Triggers on "find companies using Shopify", "they're on HubSpot", "tech stack targeting", "technographics", "who uses Klaviyo", "companies running WordPress". Outputs a per-domain verdict (tech_c

  • playbook-warm-intros

    Build prospect lists where the prospect is already one hop from the client, and write the line that says so. Seven members, each with its own source. Current-customer alumni is the priority member - everyone who ever worked at one of the client's customers or case-study companies and has since moved

  • positive-reply-scoring

    Pulls replies from a Smartlead campaign, classifies each as positive/neutral/negative/OOO/bounce/unsubscribe using Claude, and reports the positive reply rate — the north-star metric for cold email. Use when the user wants to know if a campaign is actually working (not just getting replies, but gett

  • prepare-job-application

    For each company and role on a job seeker's list, find the open posting and the recruiter attached to it, rewrite the resume in that posting's own vocabulary without inventing any experience, and draft a short LinkedIn note to the recruiter — by building (once) and running a Clay workflow that finds

  • prospect-one-account

    Turn one company domain into a ready-to-review outbound package: what your CRM already knows about the account (recent activity, past opportunities, an engagement level), what public third-party signals say about timing (hiring, funding, leadership changes), the 3-4 director-plus people who own the

  • prospeo-full-export

    Export your entire Prospeo people search to CSV. Build filters in Prospeo's UI, then use this skill to extract every result via the API — even searches over 25K. Handles pagination, rate limiting, deduplication, and state-by-state splitting automatically. Pair with /icp-prompt-builder on a 50-person

  • prospeo-search-api
  • renewal-risk-radar
  • resolve-company-domain
  • signal-sourcer
  • smartlead-api
  • smartlead-campaign-upload-public
  • smartlead-inbox-manager
  • smartlead-spintax
  • spam-word-checker
  • tam-audience-loader
  • tam-builder
  • track-champion-job-changes
  • value-first-cold-email
  • zapmail-domain-setup-public
  • account-health-framework
  • account-qualification
  • advanced-prompting-techniques
  • advanced-rag-retrieval
  • agent-memory-and-guardrails
  • ai-agent-design-patterns
  • ai-build-vs-buy-and-model-adaptation
  • ai-engineering-foundations
  • ai-evals
  • ai-evaluation-methodology
  • ai-product-development-lifecycle
  • ai-product-okrs-and-metrics
  • ai-product-strategy
  • analyzing-financial-statements
  • analyzing-user-feedback
  • api-design-and-evolution
  • api-gateway-and-service-mesh
  • api-security-and-lifecycle
  • approval-loop-fanout
  • architectural-quanta-and-modularity
  • architecture-characteristics-and-tradeoffs
  • architecture-styles-monolithic-and-distributed
  • asynchronous-messaging-patterns
  • battlecard-library
  • behavioral-product-design
  • book-distiller
  • brand-storytelling
  • build-sprint
  • building-agents-with-langgraph
  • building-mcp-servers
  • building-sales-team
  • building-with-llms
  • campaign-benchmarking
  • causal-decision-modeling
  • code-reuse-in-distributed-systems
  • cold-email-personalization
  • competitive-analysis
  • concurrent-systems-foundations
  • conducting-user-interviews
  • consensus-and-strong-consistency
  • consulting-acceptance-bar
  • consulting-agent-contract
  • consulting-ai-suitability-scoring
  • consulting-automation-design
  • consulting-behaviour-specification
  • consulting-benefits-case
  • consulting-boundary-setting
  • consulting-constraint-analysis
  • consulting-cost-time-baseline
  • consulting-failure-design
  • consulting-process-recovery
  • consulting-roadmap-sequencing
  • consulting-tacit-work-elicitation
  • consulting-task-decomposition
  • content-marketing
  • copy-frameworks
  • creating-financial-models
  • creative-iteration-playbook
  • cross-functional-collaboration
  • data-architecture-frameworks
  • data-contract-framework
  • data-engineering-lifecycle-and-principles
  • data-mesh-domain-topologies
  • data-ownership-and-distributed-data
  • data-storage-and-modeling-patterns
  • database-designer
  • dataops-and-modern-data-platforms
  • deal-patterns
  • decision-intelligence-fundamentals
  • decision-simulation-and-monitoring
  • defining-product-vision
  • delegating-work
  • design-engineering
  • design-system
  • designing-growth-loops
  • distributed-caching-patterns
  • distributed-system-patterns
  • distributed-systems-essentials
  • distributed-workflows-and-sagas
  • embedding-models-and-domain-adaptation
  • enterprise-data-integration-and-distribution
  • eval-harness
  • evaluating-new-technology
  • evaluating-trade-offs
  • event-streaming-with-kafka
  • eventual-consistency-mechanics
  • exec-briefing
  • exec-dashboard-blueprint
  • expansion-playbook
  • experiment-design-kit
  • firmographic-analysis
  • forecast-discipline
  • frontend-dev
  • fullstack-dev
  • git-collaboration-workflows
  • git-fundamentals-and-workflow
  • git-power-user-techniques
  • head-of-product-engineering
  • icp-matrix-builder
  • insights-repository-kit
  • intent-signals
  • iterative-engineering-practices
  • jtbd-fundamentals-and-interviewing
  • jtbd-strategy-and-organization
  • knowledge-graph-applications
  • knowledge-graph-modeling
  • knowledge-graph-platform-integration
  • launch-marketing
  • launch-tiering
  • lead-prioritization
  • lifecycle-mapping
  • llm-conversation-memory-and-multimodal

Subagents (10)

  • builder
  • career-strategist
  • content-correspondent
  • cto-principal-architect
  • diagnostician
  • head-of-product
  • learning-coach-mentor
  • research-analyst
  • reviewer
  • systems-analyst

MCP servers (1)

  • notion

    connects to: https://mcp.notion.com/mcp

View source on GitHub

More from AlexYedi/alex-agents-skills

All 4 plugins →

Active coding discipline enforcer based on Karpathy's 4 principles: surface assumptions, keep it simple, make surgical changes, define verifiable goals. Ships 4 Python tools (complexity_checker, diff_surgeon, assumption_linter, goal_verifier), a review agent, /karpathy-check slash command, and a pre-commit hook. All tools stdlib-only.

1 skill · 1 command · 1 agent

1

Audit datasets for completeness, consistency, accuracy, and validity. 3 stdlib-only Python tools: data profiler with DQS scoring, missing value analyzer with MCAR/MAR/MNAR classification, and multi-method outlier detector.

1 skill

1

Hypothesis testing, A/B experiment analysis, sample size calculation, and confidence intervals. 3 stdlib-only Python tools with Z-test, t-test, chi-square, effect sizes, power analysis, and Wilson score intervals.

1 skill

1

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

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

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

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

career-ops-hq/career-ops 82,253

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

Maintain alex?

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.

claude & codex plugins4 plugins