AI & ML

skillmedev Skill

Selects and executes a credible causal identification strategy - RCT, natural experiment, difference-in-differences, regression discontinuity, instrumental variables, or matching - ranked by assumption strength, with a confounder checklist, falsification tests, and a defensible effect estimate. Use when someone asks "did X actually cause Y", "how do I measure impact without an A/B test", "is this correlation causal", or needs to defend an effect estimate from observational data. Do NOT use for designing the data-collection study itself (sampling, instruments, power) - use primary-research instead; for reading out an already-run A/B test, use ab-test-analyzer instead.

akunikkola Bundle

Suomalaisen voimassa olevan lainsäädännön ja oikeuskäytännön haku, lukeminen ja oikea viittaaminen oik.ai-, laki.ai- tai Finlex-MCP:n avulla. Käytä tätä skilliä AINA kun tarvitaan ajantasaista lakitekstiä, pykälän sisältö, KKO:n tai KHO:n ennakkopäätös, hovioikeuden, markkinaoikeuden, työtuomioistuimen tai vakuutusoikeuden ratkaisu, hallituksen esityksen perusteluja, tai kun käyttäjä kysyy "mitä laki sanoo", "onko tästä oikeuskäytäntöä", "mikä on voimassa oleva pykälä", viittaa säädösnumeroon (esim. 410/2015) tai ratkaisutunnukseen (KKO:2024:15). Triggeröi myös aina ennen kuin lainaat pykälää tai oikeustapausta muistista – tarkista se ensin lähteestä.

skillmedev Skill

Prepares real estate agents for offer and inspection negotiations with a two-sided position worksheet, offer-strength evaluation beyond price, repair-vs-credit-vs-price-reduction decision rules, escalation-clause mechanics, and a pre-set walk-away number. Use when an agent says "we got three offers, help me compare", "prep me for this negotiation", "the inspection came back rough", or "should we counter or accept". Do NOT use for job-offer or compensation negotiation - use salary-negotiation instead - or for investment term negotiation, which is term-sheet-negotiation.

skillmedev Skill

Wins listings before competitors are invited by nurturing homeowner leads with quarterly home-value updates, an equity-position letter, lifecycle triggers like a neighborhood sale, and the CMA offer as the conversion event. Use when an agent says "how do I get more listings", "nurture my seller leads", "a homeowner asked what their house is worth", or "how do I stay in front of past clients and my farm". Do NOT use for keeping buyer leads warm - use buyer-nurture-sequence instead - or for the pricing presentation itself, which is cma-narrative-builder.

skillmedev Skill

Use the Skill Me catalog from inside any conversation - discover, install, and manage Claude skills through the Skill Me MCP, and load installed skills automatically each session.

skillmedev Skill

Converts open-house visitors into clients with door capture, a same-evening first touch, a 3-touch follow-up sequence, and buyer-signal triage by financing and timeline. Use when an agent says "follow up with my open house leads", "what do I send open house visitors", "my sign-in sheet goes nowhere", or "how do I work an open house". Do NOT use for generic B2B follow-up cadences - use sales-followup-cadence instead.

skillmedev Skill

Turns a comparative market analysis into a pricing story a seller accepts - defensible comp selection, plain-language adjustments, the overpricing-cost math, and a price-band recommendation aligned to portal search brackets. Use when an agent says "help me present my CMA", "the seller wants to list too high", "how do I justify this price", or "Zillow says their house is worth more". Do NOT use for negotiating the offers that come in after listing - use re-negotiation-prep instead.

skillmedev Skill

Writes the full foundation grant proposal for a nonprofit - need statement grounded in local data, a logic model with real numbers (inputs to activities to outputs to outcomes), SMART objectives, an evaluation plan sized to organizational capacity, a budget narrative where every line traces to an activity, and a credible sustainability answer. Use when a nonprofit leader says "write the full grant proposal", "we got invited to submit", "build our logic model", "our proposal needs an evaluation plan", or "the funder wants a budget narrative". Do NOT use for the initial one-page letter of inquiry - use grant-loi-writer instead - and do NOT use for corporate sales proposals - use sales-proposal-writer instead.

skillmedev Skill

Converts custom freelance work into fixed-scope, fixed-price productized offers using the scope-box procedure, a 3-tier structure with the middle tier as the target, and deliverable definition rules. Use when a freelancer says "how do I productize my services", "I want to stop trading hours for dollars", "package my offer", "every project is a custom quote", "design my service tiers", or "clients keep asking what exactly they get". Do NOT use for choosing a pricing model for a software product - use saas-pricing instead; for the overall pricing rationale of a business, use pricing-strategy.

apoorvjain25 Bundle

Execute any task at frontier quality. Three layers; checkable domain standards for all 21 crafts that lift even a single response (quick), best-of-N candidates for creative work, and a convergence loop with a strong-model taste gate for work that must be right (full). Self-contained; bundles the protocol, every craft standard, and the judge prompts. Standards distilled from the frontier tier (Claude Fable 5). Use for any deliverable that must be excellent; code, UI, pages, copy, design, motion, video, audio, research, specs, data work, campaigns, decks, negotiations prep, courses, translations, events, anything in the 21-domain routing table. Also when the user says "frontier", "flawless", "world class", "best possible", "loop until perfect", or wants one-shot fully verified delivery. Optional argument names the deliverable and a mode.

skillmedev Skill

Writes MLS and portal listing copy that sells the property - lead with the differentiator, translate features into benefits, specifics over adjectives, platform length limits, and a fair-housing-safe banned-claims list. Use when an agent says "write my listing description", "make this MLS copy better", "describe this house for Zillow", or "punch up my listing remarks". Do NOT use for e-commerce product listings - use product-description-writer instead, or amazon-listing-optimizer for Amazon listings.

mchenr Bundle

Find the SRA benchmark model QPS and latency at a target normalized container CPU load, such as "32T 60% CPU", "CPU load target", "capacity point", "QPS at target CPU", or "measure model throughput under a CPU budget". Use for TensorFlow predictor_server/brpc_client benchmark sweeps on wd_dcn, din_mmoe, bst_mmoe, or similar SRA SavedModel workloads when Codex must choose coarse and fine QPS ranges, validate CPU quota normalization, run/interpret benchmark results, and report the target CPU capacity point.

mchenr Bundle

Use when building or modifying SRA benchmark TensorFlow SavedModels for predictor-server hardware inference benchmarking, especially when deriving train/export scripts and inference TSV generators from pbtxt/reference graphs such as wd_dcn or wide_and_deep.

vorim-ai-labs Skill

AI agent identity, permissions, trust scores, and audit trails via Vorim AI. Gives your OpenClaw agent a cryptographic identity so every action is verified, permissioned, and logged.

itamarb2010-jpg Skill

List every skill and specialist agent in this Minecraft-plugin toolkit, grouped by phase, with the recommended end-to-end workflow. Use this when the user asks what skills/commands are available, what this toolkit can do, which skill to use next, how the pieces fit together, or just types /help. Reads the skills and agents live from disk — never invents them.

fabiopacifici-bot Bundle

Local markdown file entries for OpenClaw agents. Cross-agent facts, decisions, and context stored as curated files.

ninadnj Bundle

Answer questions grounded in a set of documents (RAG), with citations.

cgray-redhat Bundle

Classifies user questions and routes to the right Red Hat agentic interface — Sales Assistant (shadowbot.io), Dataverse Agent (agent.dataverse.redhat.com), or Dataverse MCP skills in Cursor. Pulls capability context from The Source. Use when the user asks which agent to use, wants to query Sales Assistant or Dataverse Agent, or needs help routing sales vs data questions.

helloxkk Skill

Install, list, and remove MCP servers (Model Context Protocol) for AI coding tools. Use whenever the user mentions installing an MCP, adding an MCP server, Model Context Protocol, playwright MCP, browser MCP, filesystem MCP, or says an MCP isn't working / can't be called / isn't loading. Also triggers on "I want to use tool X but can't access it" — that's often a missing MCP. Supports both ZCode (mcp.servers) and Claude Code (mcpServers) config formats.

vladimir-cheskidov-sub-zero Bundle

Use whenever PhpStorm MCP is available for PHP project context, semantic-first navigation, inspections, structural search, refactoring, validation, and on-demand overlays before falling back to low-level or external tooling.

daddia Skill

This skill should be used when the user runs "/balanced-scorecard:practice-setup" (with optional --quick, --full, --redo, --check-integrations, or --resume), asks to "set up the balanced-scorecard plugin," "teach Claude our strategy map," or wants to redo that setup after the sector, perspective model, or cadence changes materially. Writes the shared org profile and the balanced-scorecard practice profile.

daddia Skill

Check installed community skills for updates. Shows a diff and requires explicit approval before applying. Use when the user says "check for updates", "update my skills", "anything new for my installed skills", or when invoked from the registry-sync agent.

daddia Skill

Engagement-profile interview that recommends and installs a starter pack of community strategy skills. This IS the practice setup for the whole ecosystem — it asks what kind of strategist you are and recommends what to install first. Use on fresh install, when the user says "get me started" or "what should I install", or to re-run the integration-availability check after adding or removing an MCP connector.

cgray-redhat Bundle

Runs structured evaluations on a Cursor Agent Skill by executing each eval prompt with and without the skill, grading assertions, and writing a summary report. Use when the user asks to run evals, evaluate a skill, test skill quality, or benchmark skill performance.

cgray-redhat Bundle

Checks and refreshes MCP and service connections for Google Workspace (gws), Slack, The Source, Dataverse, Atlan, Sanity, and Playwright. Use when the user asks to refresh connections, check MCP auth, fix expired tokens, verify gws/Slack access, or reconnect integrations before running other skills.

cgray-redhat Bundle

Guides a structured data analysis by asking intake questions (availability, permission, acquisition), then discovers data via Atlan and Dataverse MCP, checks access, and delivers findings or access-request guidance. Use when the user wants to analyze enterprise data, find data products or tables, check Dataverse access, request data access, or explore whether Red Hat has data for a business question.

weizheng9493 Bundle

Cross-agent shared memory for Codex, Claude, and compatible skill runtimes. Use when the user wants multiple AI agents to share durable context, technical decisions, project notes, long-term facts, preferences, or a portable file-backed memory protocol that both Codex and Claude can install and use.

qamarcos Skill

Execute exploratory/manual QA against a web app, driven by either a ticket's test plan or a single ad-hoc scenario the user describes. Use whenever the user asks to "run a manual test", "fazer um teste manual", "execute this scenario", "validate this ticket manually", "manual test for TICKET-XXXX", or otherwise wants the agent to step through a behavior in the real app and report pass/fail with evidence. Pulls context from the ticket + linked docs, asks the user for anything it cannot access, and drives the app via a one-off Playwright run (headed by default) reusing this repo's fixtures.

daddia Skill

This skill should be used when the user asks "is our org too top-heavy," "do we have too many layers," "is this manager's span reasonable," or needs span of control and layer count diagnosed against known patterns for over- and under-management.

daddia Skill

This skill should be used when the user asks to "design the target operating model," "what should our TOM look like," or needs current-state and ambition translated into a future operating model across capability, organization, process, technology, and data.

sid732 Bundle

Preflight a PDF, scan, or screenshot locally before sending it to the model. Extracts the embedded text layer, OCRs image-only pages on-device with Apple Vision, and flags genuinely visual pages (tables, charts, diagrams) for the vision model, which cuts vision-token cost. Use whenever the user shares a PDF or image to read, summarize, or extract from.

smirnov-labs Bundle

Use when reviewing an implementation plan document (docs/superpowers/plans/*.md or similar) for LLM-style overengineering before implementation. Runs a rubric-driven Claude pass plus a Codex adversarial pass, merges findings, and proposes specific edits to slim the plan. Triggers on 'check this plan for bloat', 'is this overengineered', 'detect overengineering', or invoked as /detect-overengineering.

daddia Skill

This skill should be used when the user asks to "build a RACI," "who actually owns this decision," "clarify decision rights," or has a decision or process that needs explicit roles assigned with single-point-accountability enforced.

daddia Skill

This skill should be used when the user asks "is our structure right for our strategy," "should we reorganize," "why does coordination feel so slow," or needs the current or proposed structure tested against the actual coordination need the strategy requires.

daddia Skill

This skill should be used when the user asks "will this reorg actually stick," "does our reward system support the structure we want," "why are people still behaving the old way after the reorg," or needs the proposed or current structure checked against rewards, process, and people capability for genuine alignment — the Star Model integration check.

daddia Skill

This skill should be used when the user asks "does our matrix structure actually work," "who wins when the two bosses disagree," "is this matrix reporting relationship viable," or has a dual-reporting relationship that needs a tie-breaker rule checked or forced into the open.