Loading...
Loading...
Found 1,603 Skills
Know when your AI breaks in production. Use when you need to monitor AI quality, track accuracy over time, detect model degradation, set up alerts for AI failures, log predictions, measure production quality, catch when a model provider changes behavior, build an AI monitoring dashboard, or prove your AI is still working for compliance. Covers DSPy evaluation for ongoing monitoring, prediction logging, drift detection, and alerting.
Builds dashboards, reports, and data-driven interfaces requiring charts, graphs, or visual analytics. Provides systematic framework for selecting appropriate visualizations based on data characteristics and analytical purpose. Includes 24+ visualization types organized by purpose (trends, comparisons, distributions, relationships, flows, hierarchies, geospatial), accessibility patterns (WCAG 2.1 AA compliance), colorblind-safe palettes, and performance optimization strategies. Use when creating visualizations, choosing chart types, displaying data graphically, or designing data interfaces.
INVOKE THIS SKILL before creating any PR to ensure compliance with branch naming, changelog requirements, and reviewer assignment.
Build WCAG 2.2 AA compliant interfaces with semantic HTML, ARIA, keyboard navigation, focus management, color contrast, and screen reader support. Covers forms, dialogs, tabs, live regions, skip links, alt text, and data tables. Use when implementing accessible UIs, auditing WCAG compliance, fixing screen reader issues, keyboard navigation, focus traps, or troubleshooting "focus outline missing", "aria-label required", "insufficient contrast", "missing alt text", "heading hierarchy".
Apply OceanBase documentation formatting standards including meta tables, notice boxes, spacing, and markdown lint compliance. Use when formatting or reviewing OceanBase documentation.
Prepare R packages for CRAN submission by checking for common ad-hoc requirements not caught by devtools::check(). Use when: (1) Preparing a package for first CRAN release, (2) Preparing a package update for CRAN resubmission, (3) Reviewing a package to ensure CRAN compliance, (4) Responding to CRAN reviewer feedback. Covers documentation requirements, DESCRIPTION field standards, URL validation, examples, and administrative requirements.
Pull request and code review with diff-based routing across five dimensions: code quality and guideline compliance, test coverage analysis, silent failure detection, type design and invariant analysis, and comment quality auditing. Classifies changed files and loads only relevant review methodologies. Produces severity-ranked findings (Critical, Important, Suggestion) with confidence scoring. Replaces pr-review-toolkit plugin. Trigger phrases: "review my PR", "review this code", "check my changes", "is this ready to merge", "audit this PR", "review before committing", "check code quality", "any issues with this code", "pre-merge review", "look over my changes", "code review". Use this skill when reviewing code before commit or merge, checking PR quality, or when the user asks for feedback on recent modifications.
Orchestrates Tizen certification workflow. Coordinates TCT test execution, compliance verification, and certification documentation.
Generate a complete, ready-to-send creator campaign brief from a few inputs — product, platforms, deliverables, messaging, and audience. This skill should be used when writing a campaign brief, building an influencer brief, drafting a creator brief, generating a partnership brief, creating a brief for a product launch, putting together a campaign brief for a new launch, starting a new creator campaign, planning deliverables and content direction, or preparing any document that goes out to creators — even if the user does not call it a "brief." If the user needs brand context first, see brand-context. If the user needs content concepts after the brief, see creator-content-concept-generator. If the user needs outreach messages, see creator-outreach-sequence-generator. If the user needs to check content against the brief, see content-to-brief-compliance-checker.
Guides cleaning and standardizing tabular datasets before analysis, modeling, or reporting—profiling, quality rules, missing values, duplicates, outliers, type coercion, encoding fixes, record linkage, deduplication, high-level PII handling (not legal advice), actuarial/insurance field scrubbing, reproducible scrub pipelines, validation checks, and sign-off. Distinct from warehouse ETL or statistical modeling. Use when the user asks for "data scrubbing", "clean this dataset", "scrub the data", "data cleaning", "dedupe records", "handle missing values", "outlier treatment", "standardize columns", "data quality rules", "profile this table", or "prepare data for modeling". Not warehouse pipelines (data-warehouse-engineer), ML modeling (data-scientist, actuary), privacy programs (compliance-engineer), FinOps only (finops-analyst), or assumption governance (assumption-setting).
Analyze and transform messy, prototype, overgrown, slop-prone, or hard-to-maintain software repositories into maintainable product-shaped codebases while preserving existing product behavior. Use when the user asks to antislop a codebase, clean up a messy repo, run a maintainability migration, write a refactor plan, modernize structure, improve TypeScript/type boundaries, harden tests, reduce large files, clean architecture, coordinate subagent-driven refactors, or produce a final migration audit/report/microsite. Do not use for broader production-readiness specialties such as security audits, observability/logging programs, compliance hardening, SRE/runbook work, or reliability engineering unless the user explicitly scopes those as part of the maintainability refactor.
Code quality improvement: review, refactoring, debugging. Phases: review feedback, systematic refactoring, root cause debugging, verification. Capabilities: SOLID/DRY compliance, code smell detection, complexity reduction, bug investigation, verification gates. Actions: review, refactor, debug, verify, validate code. Keywords: code review, refactor, debug, SOLID, DRY, code smell, bug fix, root cause, verification, technical debt, extract method, test failure, completion claim. Use when: reviewing code changes, improving code quality, fixing bugs, reducing technical debt, validating before merge/commit.