В каталоге 183 730 навыков в 14 категориях.
Review organizational expenses for policy fit, business purpose, evidence, coding, approval, duplication, anomaly, alloc...
Design an expense-tracking sheet that survives real receipts — the capture-at-spend habit, the category set that matches...
Track business expenses, categorize spending, manage budgets, and generate financial reports
Phenomenological reflection on the conversation itself. What was it like? What did I learn? What do I want to say unprom...
Habilidade inspirada no HKUDS OpenSpace para gerir "Security Experience Trips" e evoluir o conhecimento coletivo do SOC.
System-of-record for the public Lightning Instrumentation Headless Connect REST API route that retrieves Agentforce Vibe...
Anti-AI-slop design system for distinctive, premium interfaces. Bold typography, dark-first #060610, fluid clamp() type,...
The artifact is correct and nobody can use, learn, or read it. Use when every component metric is green but the end-to-e...
Create, extend, deploy, review readiness for, or activate an App MCP, a Salesforce custom hosted MCP server for an Aura...
Use this skill to analyze a Salesforce Aura component bundle (.cmp, .app, .evt, .intf, Controller.js, Helper.js, Rendere...
Extracts, retrieves, and applies CMS brand guidelines (voice, tone, style, colors, typography) to generated content. Use...
Author a Salesforce Digital Experience brand (a "brand.json") so the VS Code Brand Toolkit can load, edit, and preview i...
Renders, embeds, or displays existing Salesforce CMS content in a React or Angular uiBundle app: installs the CMS toolki...
Own product experience decisions for client surfaces: user jobs, information architecture, routes and navigation intent,...
Use this skill to run a visual-craft audit of a rendered UI and produce an evidence-grounded Craft Report across Useful,...
Designs user interactions, flows, and wireframes from requirements
Use when a product, UX, or scope tradeoff comes up. Pick what's better for the person using it over what's easier to bui...
Score the visual quality of the public surfaces the experience-audit organ captured — layout, typography, coherence, tru...
Capture task outcomes, score performance, and derive rules as token priors for continual learning without model weight c...
Use when you need to create a brand new Lightning Web Component from a Figma design, a Product Requirements Document, or...
Lightning Web Components with PICKLES methodology and 165-point scoring. Use this skill when the user creates or edits L...
Migrate legacy Salesforce UI stacks onto modern LWC — Aura → LWC conversion completeness verification and Lightning Out...
Use this skill to review a Lightning Web Component (.html, .js, .css files) for right-to-left (RTL) internationalization...
Use when running Salesforce Lightning Preview for an app or a single LWC component to extract the runtime DOM for inspec...
Assess whether a specific Lightning web component can serve its user's purpose as an HXL declarative widget. Use for LWC...
Convert a specific existing Lightning web component (LWC) into a declarative HXL / Agentforce widget, end to end. Gates...
Creates, modifies, or manages Salesforce Experience Cloud LWR sites via DigitalExperience metadata. Always trigger when...
Create / provision / set up a NEW Digital Experience (Communities) / Experience Cloud site — employee service, IT suppor...
Searches for and retrieves existing content and media (articles, blogs, news, FAQs, events, products, images, logos, ico...
Selects the most relevant experiences, projects, awards, and credentials from the master context based on JD keywords.
Documentation pattern for translating brand platforms into modular experience systems.
MUST activate when the project has a uiBundles/*/src/ directory and the task involves deploying to an org or post-deploy...
MUST activate to localize / internationalize a uiBundles/*/src/ project (React or Angular): extract hardcoded user-facin...
CDO-posture skill that authors a kensaiapp instance's visual experience layer — the fence and the direction every produc...
Content-Manager-posture skill that authors a kensaiapp instance's verbal experience layer — the limits and the inherited...
Use to run an autoresearch-style experiment loop — improve a measurable artifact by trying changes, measuring against on...
Use when creating ASCII art to guide your artistic approach
Run parallel experiments across git worktrees. Define competing approaches to the same problem, dispatch sub-agents to i...
Design, run, and evaluate a controlled A/B test (split test) on your ad accounts with evidence discipline — one variable...
Test an intervention or compare alternatives through a bounded empirical trial with declared evaluation criteria and sto...
Experimental design and execution specialist. Designs, implements, validates, and runs in-silico experiments with proper...
Designing A/B tests: hypothesis docs, sample size, feature flags, significance analysis, CUPED, SRM detection, switchbac...
Hypothesis-list–driven iteration loop for Orbit Wars experiments under `backend/pipeline/{imitation|rulebase|reinforce}/...
Analyze completed experiments and craft executive-ready summaries with insights and recommendations.
Prepare an experiment brief outlining hypothesis, design, success metrics, and operational plan.
Given a research goal, use existing skills, training reports, and references to propose a small, concrete experiment pla...
Analyze GRPO training runs for learning dynamics and pipeline performance. Use when diagnosing training issues, reviewin...
Replay-driven post-mortem skill for finished Orbit Wars experiments. Selects the analysis target by priority (most recen...
Analyze completed growth experiment results, validate hypotheses, generate insights, and suggest follow-up experiments....
Audit experiment integrity before claiming results. Uses cross-model review (GPT-5.4) to check for fake ground truth, sc...
Audit experiment integrity before claiming results. Uses cross-model review (external reviewer backend) to check for fak...
Turn assumptions, funnel opportunities, and product questions into a prioritised, feasibility-checked experiment backlog...
Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deplo...
Experiment Coach — validates ideas before launch and runs growth experiments after it, from inside the chat. Use when so...
You are a coding standards expert specializing in experiment configuration with hydra yaml.
Decide when to A/B test vs just ship. Framework for experiment planning and prioritization.
Comprehensive guide to A/B testing, multivariate testing, statistical significance, and experiment analysis for data-dri...
"Design rigorous experiments following best practices. Use when: (1) Planning research studies, (2) Grant proposal devel...
Use when the user wants to design experiments, plan ablation studies, structure baselines, or create incremental evaluat...
Turn a refined GIScience / remote sensing / spatial data science proposal into a detailed, claim-driven experiment roadm...
Design robust experiments to test product hypotheses. Define metrics, sample size, and success criteria.
<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->
Design product experiments to test hypotheses. Use when the user says "run an experiment", "A/B test this", "build-measu...
A discipline for designing experiments (A/B tests, multivariate, holdouts) so the results actually answer the question y...
Generates a rigorous experiment design given a hypothesis. Use when asked to design experiments, plan experiments, creat...
Toolkit for structuring hypotheses, variants, guardrails, and measurement plans.
Run an end-to-end workflow that chains the skills `refine-research` and `experiment-design`. Use when the user wants a o...
Use when planning product experiments, writing testable hypotheses, estimating sample size, prioritizing tests, or inter...
Use when designing product experiments, A/B tests, holdouts, staged rollouts, quasi-experiments, or low-traffic validati...
Design statistically rigorous A/B tests and interpret experiment results. Use when asked to design an experiment, run an...
Maps the assumptions behind an innovation initiative (desirability, feasibility, viability), picks the riskiest one, and...
Use for Crewrift-specific experiment discipline recipes when optimizing a player.
Execution runner for Orbit Wars experiments under `backend/pipeline/`. Takes a single hypothesis (one line in `hypothese...
Systematically analyze experiment failures and optimization setbacks to identify root causes and define validation plans...
Audit experiment integrity against the evidence ledger. At L2 (repo + result files present) a fresh cross-model reviewer...
Maintain or extend the advisory governance layer that classifies experiment usefulness, concentration, noise, and scoped...
Hypothesis-list builder for Orbit Wars experiments under `backend/pipeline/{imitation|rulebase|reinforce}/case<N>/`. Run...
Weekly experiment tracking loop for MD Home Care. Scans content changes, measures traffic impact via PostHog and GSC, an...
Autonomous experiment loop: hypothesize > modify > test > evaluate > keep/discard > repeat. Run N experiments automatica...
Run a controlled THINK-EXECUTE-REFLECT loop for coding, research, or ML experiments. Use when the user wants iterative i...
STEDII framework for selecting trustworthy experiment metrics. Ensures metric validity and reliability.
Direct a claim-driven research experiment project from post-Idea intake through method realization, prioritized evidence...
Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-re...
Hypothesis-management decision maker and per-iteration `iterN_plan.md` writer for Orbit Wars experiments under `backend/...
Use when exploring, continuing, or accepting a deep-learning or computer-science research idea. Converts claims into pil...
Run a comparison between several candidate solutions honestly: freeze the contract, fan out isolated producers, judge bl...
SSH job queue for multi-seed/multi-config ML experiments with OOM-aware retry, stale-screen cleanup, and wave-transition...
Analyse experiment results, run validity checks (SRM, exposure parity, data integrity, novelty/primacy), interpret causa...
Write experiment readouts for product, growth, pricing, UX, and operational tests. Use when Codex is asked to summarize...
假设 + 指标 + 结果 + 解释 + 决策, 把 A/B 或产品实验转成行动建议
Analyse a finished A/B test and write an honest results readout with real statistics. Use when asked to read out an A/B...
This skill should be used when generating integrated reports from lab notebooks, improving existing reports, or exportin...
Write structured experiment sections (methods + results + discussion) for NQS + SQD projects in this repository, based o...
Interpret A/B test results in plain language and get a ship/rollback/extend recommendation with a stakeholder summary. U...
Turn experiment reports and notes into summaries and new/updated result skills.
Translate an approved experiment spec into a launch runbook — platform binding (PostHog primary), feature flag setup, as...
Implement and execute approved research Experiment, Tuning, or Design Cards with reproducible logs, metrics, environment...
Create a new experiment workspace directory: initialize git, write an AGENTS.md goal doc, and create references/ with in...