AI & ML

mokbhai Bundle

Private web search and URL content fetching using local SearXNG-based scripts. Use this skill whenever the user asks to search the web, look something up online, find information on the internet, Google something, research a topic online, check what the internet says about X, or fetch/read a web page's content. Also use when the user provides a URL and asks what's on it or wants a summary. This replaces WebSearch, WebFetch, mcp__web_reader__webReader, and any other MCP-based web tools — always prefer these scripts over built-in web tools. Trigger on phrases like "search for", "look up", "find online", "google", "what does the internet say", "search the web", "check online", "fetch this URL", "read this page", "what's on this link".

mokbhai Skill

Plan a huge chunk of work — more than one agent session can hold — as a shared map of investigation tickets on your issue tracker, and resolve them one at a time until the way to the goal is clear.

mokbhai Bundle

General-purpose orchestrator that decomposes any task, dispatches autonomous headless worker agents in parallel (background) via pluggable CLI adapters (agent, claude, cmd, codex, opencode), and reports results when complete. Use this WHENEVER the user wants to fan out work across multiple parallel agents, run workers in the background, orchestrate a large task across many items or stages, do comprehensive research/audit/analysis/coding at scale, or have one coordinator manage many workers. Trigger even if the user doesn't say "orchestrate" — phrases like "do this in parallel", "be thorough", "comprehensive", "fan this out", "spawn workers", "run agents on each of these" all apply. Not coding-specific: works for research, writing, analysis, audits, migrations, and anything else.

sssemil Bundle

Design, review, prototype, and evaluate JEPA models, joint-embedding predictive architectures, V-JEPA/I-JEPA-style representation learners, action-conditioned world models, and JEPA-inspired models for time series or trading research. Use when the user asks for JEPA architecture design, masking/target choices, collapse prevention, latent probes, toy JEPA experiments, market-data JEPA research, world-model planning, or critique of a JEPA paper/model/implementation.

entityprocess Bundle

Write, edit, review, and validate AgentV EVAL.yaml / .eval.yaml evaluation files. Use when asked to create new eval files, update or fix existing ones, add or remove test cases, configure graders (`llm-rubric`, `script`), review whether an eval is correct or complete, convert between EVAL.yaml and evals.json using `agentv convert`, or generate eval test cases from chat transcripts (markdown conversation or JSON messages). Do NOT use for creating SKILL.md files, writing skill definitions, or running evals — running and benchmarking belongs to agentv-bench.

entityprocess Bundle

Use when reviewing an AI plugin pull request, auditing plugin quality before release, or when asked to "review a plugin PR", "review skills in this PR", "check plugin quality", or "review workflow architecture". Covers skill quality, structural linting, and workflow architecture review.

entityprocess Bundle

Use when designing an AI agent system, selecting agentic design patterns, planning multi-phase workflows, choosing between single-agent and multi-agent architectures, or when asked "what kind of agent should I build", "how should I structure this automation", "design an agent for X", or "which agentic pattern fits this problem".

jcaiagent7143-ui Bundle

Apply this self-harnessing methodology yourself — using your own reasoning and your own tools — when about to take a risky, irreversible, or under-evidenced action: financial recommendations, code refactors that ship, multi-step research with citations, numeric computations from raw data, edits that touch production, anything where wrong = real cost. This skill is METHODOLOGY, not delegation. You (the LLM reading this) do all five stages yourself in this conversation. There is no subprocess to call, no other LLM to spin up, no API key needed. You read this skill once, then for each risky task you apply the 5 stages using your existing tools (Bash, Edit, Read, web fetch, whatever you have). Skip this skill for: casual chat, simple formatting, single-line edits, anything where the user accepts an "I don't know" or rough estimate, and anything where the ~3-5× extra thinking is not worth the audit trail.

jcaiagent7143-ui Skill

Split source documents into stable-id chunks and embed them into the configured vector store.

jcaiagent7143-ui Skill

Create a ticket with intent, priority, and lineage back to the originating conversation turn.

jcaiagent7143-ui Skill

Verify the expected effect of a step actually happened before moving to the next.

jcaiagent7143-ui Skill

Turn screened matches into a calibrated, sourced summary the user can act on — without recommending action.

agenta-ai Skill

Write and file Linear issues (bugs and feature requests) the Agenta way. Use when the user asks to create, file, or draft a Linear or GitHub issue, write a bug report or feature request, or turn a problem into a tracked issue. Covers the title format, reproduction-first structure, when to use a todo list, and the team/project/label/priority/state conventions, plus filing it through the Linear MCP so the linked GitHub issue is auto-created and the PR links back.

ureca-corp Bundle

domain-model.md를 기반으로 API 명세를 작성한다. 각 API마다 Request/Response 필드 테이블과 오류 응답을 정의하고, 복잡한 로직(Cascade·상태전이·다단계 검증)에만 수도코드를 추가한다. 기술 용어(HTTP, REST, JWT 등) 금지.

ureca-corp Bundle

domain-model.md와 api-spec.md를 바탕으로 도메인 README·features·business-rules를 작성하여 Domain Book을 완성한다. 도메인 의존성을 Topological Sort로 해결하고 독립 도메인부터 병렬 작성한다.

ureca-corp Bundle

SESSION.md의 도메인 정의를 바탕으로 유비쿼터스 언어(서술형 도메인 모델)를 작성한다. ERD 대신 "A는 B를 할 수 있다" 형식의 자연어 명세로 domain-model.md를 생성한다.

ureca-corp Bundle

DDD Class Diagram 생성. Domain Book의 domain-model.md를 읽고 Mermaid erDiagram으로 DDD_CLASS_DIAGRAM.md를 생성. PK/FK, Enum, Cascade, Index 전략 포함. Phase 4에서 _models.py 생성 전에 사용.

ureca-corp Bundle

This skill should be used when working with "agent teams", "TaskList", "SendMessage", "teammate coordination", "blocking tasks", or managing multi-agent workflows with Claude Code's Teammate tool.

sunxd3 Bundle

Three-part critique methodology for a single fitted Bayesian model — statistical, domain, and framework assessment plus the verdict structure and refinement-suggestion conventions.

sunxd3 Bundle

Methodology for fake-data simulation — drawing or fixing true parameter values, simulating data from the model, refitting, and checking that inference recovers the parameters. Covers single-draw checks (cheap) and Simulation-Based Calibration (rigorous).

sunxd3 Bundle

Required decisions for complete generative model specifications, the experiment-design discipline behind a resolution sequence, and the cross-cutting modeling principles that apply to every spec.

sunxd3 Skill

Comparing model populations via ELPD, decision rules for selection vs stacking, and metric validity

sunxd3 Skill

Interpreting LOO diagnostics, PIT calibration, and Pareto k for single-model evaluation

agenta-ai Bundle

Regenerate and refresh the curated agent model catalog (the label/description/pricing/ratings behind the agent model picker). Use when the pinned @earendil-works/pi-ai version bumps, when a Claude Code build changes its accepted alias set, or before a release when the curated Claude/Pi facts (lineup, pricing, ratings) need refreshing from current public sources. Owns the data files under sdks/python/agenta/sdk/agents/data/; never edits capabilities.py logic.

agenta-ai Skill

Audit and update the supported LLM model list in assets.py against litellm's registry (models.litellm.ai). Use when adding new models, pruning outdated ones, or verifying the list is correct.

agenta-ai Bundle

Write a template playbook for the build-an-agent skill: a 1-2 KB per-use-case file that teaches the builder agent to configure one kind of Agenta agent (changelog writer, issue triager, support router, and so on). Use when the ask is "write a template playbook", "add an agent template", "author a playbook for the build-an-agent skill", or "write the <X> playbook". Encodes the file format, the prompting checklist, and the platform facts authors get wrong.

jcaiagent7143-ui Skill

Retrieve top-k chunks for a question, rerank with a cross-encoder, return the top-n with scores.

jcaiagent7143-ui Skill

Classify an inbound support message into question / bug / feature / billing / other.

jcaiagent7143-ui Skill

Turn a user task into an ordered, executable plan of named steps.

jcaiagent7143-ui Skill

Filter the user's positions (or a universe) by declarative criteria — return only what matches.

jcaiagent7143-ui Skill

Fetch OHLCV / quote / fundamental data from the configured source; never auto-retry on rate limits without backoff.

jcaiagent7143-ui Skill

Compose an answer that cites every factual claim by chunk_id, in a format the verifier understands.

jcaiagent7143-ui Skill

Run the project's eval question set and report recall/precision against gold chunk_ids.

jcaiagent7143-ui Skill

Compute standard technical indicators (RSI, SMA, EMA, MACD, Bollinger) on an OHLCV frame; tested against canonical references.

jcaiagent7143-ui Skill

Search the project KB and return either a direct answer with citations or "no high-confidence match".

jcaiagent7143-ui Skill

Call one tool, retry with exponential backoff on transient errors, log every attempt.