Total 54,390 skills, AI & Machine Learning has 9052 skills
Showing 12 of 9052 skills
Audit, prune, and improve agent guidance markdown files in repositories. Use when the user asks to check, audit, update, improve, or fix AGENTS.md, CLAUDE.md, or related guidance files. Adds missing commands and gotchas, removes stale entries, deduplicates, and keeps the file small and relevant. Scan for guidance files, evaluate quality against templates, output a quality report, then make targeted updates.
One-time onboarding for the AI Engineering from Scratch curriculum (503 lessons, 20 phases). Interviews the learner, runs the placement quiz, and writes LEARNING.md — a persistent study plan the /learn skill drives. Trigger phrases: "start learning", "set up the course", "begin the curriculum", "onboard me", "create my learning plan"
Guidance on how to use Claude Code effectively — covering context management, verification strategies, the explore-plan-implement workflow, prompting techniques, session management, parallel sessions, and common failure patterns. Use this skill whenever the user asks how to get the most out of Claude Code, how to write better prompts, how to manage context, when to use plan mode, how to automate tasks, or when they describe a frustrating pattern like Claude repeating mistakes or losing track of instructions.
Advanced om-auto-create-pr for long, multi-step spec implementations needing resumability and strict step tracking — run folder (PLAN/HANDOFF/NOTIFY), one lean commit per Step, checkpoint verification every ~5 Steps with integration tests and UI screenshots, full gate at completion, ready labeled PR. Resumable via om-auto-continue-pr-loop. Use plain om-auto-create-pr for small fixes.
Orchestrate building a brand-new feature end to end — research, plan, TDD implementation, review, and gated commit — by delegating each phase to the matching ECC agent. Use when adding a capability that does not exist yet.
Design a goal-oriented agent loop, and review it for the ways loops go wrong — spinning and burning tokens, Goodhart-gaming the verifier, or running a wrong answer to completion. Two actions: (1) WRITE a loop — gate whether to build it, define a machine-decidable goal, pick the loop type, pick a skeleton; (2) REVIEW a loop — run it past five failure modes plus decidability, boundaries, fallback, judge independence, and keep-judgment-with-the-human red lines. Use when designing an autonomous agent loop, or when you already have one and worry it will spin, cheat, or run a wrong answer to the end. Complements the mechanism-layer loop skills (autonomous-loops, continuous-agent-loop) by covering the judgment layer they don't. 中文触发：写 loop、设计 loop、做一个 loop、检查 loop 对不对、loop 体检、loop 会不会跑飞、可判定目标、五个崩法、plan build judge。English triggers: design an agent loop, write a loop, check a loop, loop review, prevent a runaway loop, goal-oriented loop, decidable goal, plan/build/judge.
Analyze medication adherence and management platforms including dose tracking accuracy (MPR, PDC metrics), drug-drug and drug-food interaction checking completeness, refill prediction algorithms, dosage schedule optimization with conflict detection, caregiver notification escalation workflows, pharmacy system integration (NCPDP, HL7 FHIR), adverse event signal detection, smart dispenser integration, and alert fatigue mitigation for patient safety systems.
Use when building durable AI agents or agentic workflows with Inngest and AgentKit, including model calls, tool calls, multi-agent networks, human approval, realtime progress, provider rate limits, crash-safe execution, and Agent Evals handoff. Covers AgentKit, `step.ai`, `step.run`, `step.waitForEvent`, native realtime, and when to use lower-level Inngest primitives instead of an in-memory agent loop. Use `inngest-agent-evals` with this skill when the user wants scoring, sessions, experiments, deferred scorers, or outcome-based evaluation for the agent.
Build and flash the XIAO ESP32S3 Sense camera web apps in STANDALONE AP (hotspot) mode: a Teachable-Machine-style dataset collector page and a live inference viewer page served by the board itself at http://192.168.4.1. Use this skill whenever the user wants the camera web app WITHOUT a router — classroom/education deployments, demos with no WiFi, per-student boards, or says "AP 모드", "핫스팟", "공유기 없이". For router (STA) mode use the xiao-webcam-sta skill instead.
Train and deploy a TinyML model for the XIAO ESP32S3 (Sense) using the Edge Impulse REST API only — no edge-impulse-cli needed (its serialport dep fails to build on modern Node/Windows). Covers: dataset upload, impulse creation (audio MFCC / vision transfer-learning), training jobs, downloading the Arduino library, and the on-device fixes required to actually run it on the ESP32-S3. Use this skill whenever the user wants to train/retrain a model ("재훈련", "edge impulse", "TinyML 훈련", "모델 배포"), upload a dataset to Edge Impulse, or gets EI Arduino-library build/runtime errors (mel filterbank, objs.a, tensor arena, EI_MAX_OVERFLOW_BUFFER_COUNT).
Turn a vague feature or product idea into an agreed, persisted specification through relentless structured questioning. Never assumes — every gap, ambiguity, or "probably" becomes a question to the developer, and the spec cannot be approved while open questions remain. Produces docs/specs/<NNN>-<slug>.md with acceptance criteria that /plan, /scaffold, and /tdd consume. Use when: "spec", "write a spec", "spec this out", "requirements", "PRD", "acceptance criteria", "define the feature", "user stories", "what should we build", or before planning any feature too big to describe in one sentence.
任意の対象リポジトリに Claude Code の .claude/ 体系（CLAUDE.md・Agents・Rules・Skills・hooks）を 初期セットアップする。「claude セットアップして」「.claude 作って」「CLAUDE.md 初期化」「Agent 整備して」 「claude-code セットアップ」などで使用。既存 .claude/ の差分充実は update-claude を使用。 implement-issue-tree が動く前提（gh auth / sub_issues / workflow js）の整備まで含む。