3K skills · sorted by relevance
Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt engineering that scales, AI UX that users trust, and cost optimization that doesn't bankrupt you. Use when: keywords, file_patterns, code_patterns.
The English summary is being prepared. Showing the original description.
Clarify requirements before implementing. Use when serious doubts arise.
The English summary is being prepared. Showing the original description.
ACGME regulatory compliance expertise for medical residency scheduling. Use when validating schedules, checking work hour limits, supervision ratios, or answering compliance questions. Integrates with MCP validation tools.
The English summary is being prepared. Showing the original description.
Invoke connected Unique spaces/subagents through the unique-cli subagent command. Use when the workspace exposes connected-space tools and you need to delegate a question or task to one of those configured assistants.
The English summary is being prepared. Showing the original description.
Ask clarifying questions before implementing to ensure Python requirements are understood. Use when a task lacks detail, dependencies are unclear, or multiple interpretations are possible.
The English summary is being prepared. Showing the original description.
ALWAYS use this skill whenever you would otherwise ask the user a question in free-form chat -- for clarifications, confirmations (especially destructive actions), missing parameters, multiple-choice decisions, or structured form input. Elicitations are routed through the Unique AI Platform UI via `unique-cli elicit create` + `elicit wait` (the default polling pattern) or a single supervised `unique-cli elicit ask` call (only when your agent instructions say your environment supervises the wait) so the user gets a proper structured prompt and you get a structured answer back. Do NOT ask the user in plain chat when you can use this skill instead.
The English summary is being prepared. Showing the original description.
Read and drive Agentic Table (magic table / due-diligence) sheets through the unique-cli agentic-table command. Use when the user or task involves an Agentic Table: inspecting a sheet's state, a cell's value or lock state, a cell's edit history or its export artifacts; writing text into a specific cell; or running the full loop — creating a sheet, importing a questionnaire and sources, waiting for the agent to answer, and exporting the result. Access is enforced per sheet by the platform and varies from sheet to sheet; a denial is reported as `agentic-table: permission denied`.
The English summary is being prepared. Showing the original description.
Use whenever a question is about what the specification says or does — "what happens if", "can X do Y", "which errors can this return", "what does the screen show for", "what fields does this command take", "is there an operation for". Answers by running the Lean executable spec (scenarios, commands,
The English summary is being prepared. Showing the original description.
Use to create, update or verify the Lean 4 executable specification under lean/ from the exploration documents (event-timeline, hotspots, ubiquitous-language, ux-review, model-review) — initial generation, reflecting a session's results, fixing lake build, adding a command or a screen, checking a proposed feature against the model. Formalization questions go to model-review.md as MQ, never to the expert directly.
The English summary is being prepared. Showing the original description.
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
The English summary is being prepared. Showing the original description.
Read, answer and post on the Sandock community forum at community.sandock.ai through its /api/v1/community REST API. Lists categories and posts, reads a thread with its replies, searches, and publishes posts and replies behind an explicit confirmation. Use when the user invokes $sandock-community or /sandock-community, asks what is happening in the Sandock community, wants an unanswered question triaged or answered, or wants something posted or announced there.
The English summary is being prepared. Showing the original description.
Read, answer and post on the Busabase community forum at community.busabase.com through its /api/v1/community REST API. Lists categories and posts, reads a thread with its replies, searches, and publishes posts and replies behind an explicit confirmation. Use when the user invokes $busabase-community or /busabase-community, asks what is happening in the Busabase community, wants an unanswered question triaged or answered, or wants something posted or announced there.
The English summary is being prepared. Showing the original description.
Read, answer and post on the Buda community forum at community.buda.im through its /api/v1/community REST API. Lists categories and posts, reads a thread with its replies, searches, and publishes posts and replies behind an explicit confirmation. Use when the user invokes $buda-community or /buda-community, asks what is happening in the Buda community, wants an unanswered question triaged or answered, or wants something posted or announced there.
The English summary is being prepared. Showing the original description.
Ask a few focused questions to define a goal, checkable finish conditions, evidence of completion, and constraints. Use when the user wants help clarifying what success means before doing the work.
The English summary is being prepared. Showing the original description.
Hand off a task with only the context needed to continue in a fresh session. Use for "handoff", "引き継ぎ", "別セッションへ渡す", or "別マシンで続ける". The orca subcommand launches an independent Orca workspace or terminal tab; without it, produce a paste-ready prompt backed by a verified remote branch or PR. Do not launch sessions for capability questions or design requests.
The English summary is being prepared. Showing the original description.
Check the latest Claude (Anthropic), OpenAI Codex, and Google Gemini model releases from official primary sources, update model selections in this dotfiles repo, and update the Claude Code, Codex, and Gemini CLIs through their configured managers. Every run checks both the model settings and CLI for the selected provider, then scans the invoking repository for hardcoded model IDs. Use when the user asks to "モデル更新", "モデルを最新に", "最新モデル確認", "Codex/Claude Code/Gemini CLI本体の更新", "model bump", "update models", or "update agent CLIs". Do NOT use for one-off model selection in a single conversation, general model questions, or unrelated package updates.
The English summary is being prepared. Showing the original description.
Delegate reading large or multiple files to the `bulk-read` command, which sends the files to a cheaper reader model and returns only its answer. Use when a question needs the content of a file over about 350 lines or of several files at once, when a PreToolUse guard denied an unbounded read, or when the user says "bulk read", "一括読み込み", or "まとめて読んで". Do NOT use for files you are about to edit, for subtle correctness reasoning such as concurrency bugs, or for short files that fit a bounded read.
The English summary is being prepared. Showing the original description.
Guides and best practices for working with Neon Serverless Postgres. Covers getting started, local development with Neon, choosing a connection method, Neon features, authentication (@neondatabase/auth), PostgREST-style data API (@neondatabase/neon-js), Neon CLI, and Neon's Platform API/SDKs. Use for any Neon-related questions.
The English summary is being prepared. Showing the original description.
Full SEO audit: Google Search Console data + URL Inspection API + PageSpeed Insights API + technical crawl + keyword research + metadata audit + schema markup audit + search intent analysis + Core Web Vitals monitoring. Feeds real GSC data and PageSpeed metrics into AI to surface quick wins, diagnose traffic drops, find content gaps, identify metadata mismatches, detect schema gaps, monitor page performance, and produce an actionable 30-day plan. Use this skill whenever the user asks about SEO, search rankings, organic traffic, Google Search Console, keyword performance, traffic drops, content gaps, search visibility, technical SEO, meta tags, schema markup, structured data, URL indexing, keyword research, indexing issues, page speed, performance, Core Web Vitals, LCP, INP, CLS, or Lighthouse scores. Also trigger on: "why is my traffic down", "what keywords am I ranking for", "improve my rankings", "check my search console", "SEO audit", "analyze my SEO", "technical SEO", "meta tags", "indexing issues", "crawl errors", "content strategy", "keyword cannibalization", "search intent", "schema markup", "structured data", "URL inspection", "page speed", "performance score", "core web vitals", "lighthouse", or any organic search question. If in doubt, trigger. This skill handles everything from quick GSC checks to deep technical audits with performance monitoring.
The English summary is being prepared. Showing the original description.
Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route.
The English summary is being prepared. Showing the original description.
Diagnoses bias, anomalies, and strange-looking results on a specific PostHog experiment. Covers empty / 0-exposure experiments, sample ratio mismatch, identity fragmentation, multi-variant exposure, uneven-split exclusion bias, significance traps (peeking, A/A, Bayesian vs Frequentist), PostHog-vs-SQL discrepancies, and surprises after mid-run edits. Symptom-driven dispatch to the right diagnostic. TRIGGER when: user asks 'is my experiment biased?' or 'why 0 exposures?', references the bias banner, says a variant looks strange / wrong / off, sees significance flipping, notices PostHog numbers disagreeing with their SQL, sees an A/A test showing significance, or reports surprises after mid-run edits. DO NOT TRIGGER when: creating a new experiment (use creating-experiments), only configuring rollout (use configuring-experiment-rollout) or metrics (use configuring-experiment-analytics), or only asking lifecycle questions (use managing-experiment-lifecycle).
The English summary is being prepared. Showing the original description.
Set up an LLM-judge evaluation that extracts canonical use cases for a PostHog feature at scale and streams the results to a Slack channel as a live feed. Use when someone wants to understand how users are actually using a specific AI/LLM-powered feature in production — what they're investigating, what questions they're trying to answer, and what patterns surface — without manually reading hundreds of traces. Assumes the feature emits `$ai_generation` and `$ai_evaluation` events with `$session_id` linkage to the trigger user's recording (the standard setup post the session-summary linkage PRs).
The English summary is being prepared. Showing the original description.
End-to-end observational epidemiology analysis — from research question (PECO Population/Exposure/Comparator/Outcome) to publication-ready statistical report. Covers cohort/case-control/cross-sectional design, regression with confounders, propensity scoring, sensitivity analysis. Writes Python code for every step. Use for epidemiology study analysis, NHANES/UK-Biobank-style analyses.
The English summary is being prepared. Showing the original description.
Calculates statistical power for high-dimensional genomics experiments (bulk RNA-seq, scRNA-seq, ATAC-seq, ChIP-seq, methylation, proteomics) under negative-binomial count models using RNASeqPower, PROPER, and simulation via powsimR, distinguishing per-gene from marginal (transcriptome-wide) power, the role of mean expression and dispersion, and the sequencing-depth-versus-replicate tradeoff. Covers simulation as the honest default for overdispersed counts, FDR-aware average power versus single-test power, observed/post-hoc power as an anti-pattern, and the winner's-curse / Type-S / Type-M consequences of underpowering. Use when planning replicate number for a sequencing experiment, deciding whether to add depth or samples, choosing closed-form versus simulation power, estimating power from pilot dispersions, or justifying replication in a grant. For clinical-trial power see clinical-biostatistics/power-and-sample-size; for the inverse sample-size question see experimental-design/sample-size.
The English summary is being prepared. Showing the original description.