Data & AI skills

Advises on setting up LLM-based text classification as a validated measurement design. Covers codebook construction, learning-regime and model choice, prompt construction, validation against human coding with kappa and F1, hybrid human-LLM review, downstream measurement error, and reporting, plus a short resumable batch pattern with a rule-based baseline for repeated free text against a closed codebook. Use when the user wants to classify, code, or label text at scale. Category discovery goes to topic-modeling.

The English summary is being prepared. Showing the original description.

Reads model uncertainty from token log-probabilities. Covers collecting logprobs and aggregating multi-token labels, confidence tiers and margins for triage, calibration assessment with ECE, Brier scores, and reliability diagrams against human labels, responsible downstream use of confidence, and reproducibility archives. Use when the user asks about classifier confidence by item, logprobs, top-k tokens, calibration, ECE, Brier, reliability diagrams, or routing low-confidence cases to human review. Codebook and validation design go to text-classification.

The English summary is being prepared. Showing the original description.

Turns a raw Qualtrics conjoint export into an analysis-ready long-format dataset, covering export settings, identifying the implementation, package or manual wide-to-long reshaping, choice-profile alignment, ratings, reference categories, pilot exclusion, and subgroup merges. Use when the user has a conjoint CSV to clean, reshape, or debug, cannot align choices with profiles, or asks what the data must look like before AMCE estimation. Design goes to conjoint-design, validity review to conjoint-diagnostics.

The English summary is being prepared. Showing the original description.

Reads a model's own uncertainty from token log-probabilities: collecting and aggregating label logprobs, confidence tiers and margins for triage, calibration against human labels (ECE, Brier, reliability diagrams), downstream use, and reproducibility. Use for per-item classifier confidence or routing low-confidence cases to human review; codebook and validation design go to text-classification.

The English summary is being prepared. Showing the original description.

Use when finding real role-holders at known company domains from an ICP, especially prompts like 'find all job titles at these companies', 'find qualified titles', 'find RevOps or marketing-ops buyers', or when exact title discovery should precede paid people search.

The English summary is being prepared. Showing the original description.

DRAFT. Build anonymizable host-prep one-pagers for must-meet guests at an in-person event: rank, enrich, light research, warm-intro angles, PDF pack. Not installed by deepline skills. No real customer data in repo samples.

The English summary is being prepared. Showing the original description.

Use this skill when answering business analytics, RevOps, GTM metric, pipeline, revenue, funnel, customer, or warehouse questions with Deepline. Triggers on phrases like 'query Snowflake', 'analyze pipeline', 'total ACV', 'break down by quarter', 'use the semantic layer', 'run a semantic query', or any use of snowflake_get_semantic_layer / snowflake_run_semantic_query. Skip prospecting, enrichment, contact finding, outbound, or personalization workflows; use deepline-gtm for those.

The English summary is being prepared. Showing the original description.

Convert Chinese provinces, municipalities, autonomous regions, cities, counties, ancient cities, and cultural regions into restrained contemporary posters led by one culturally transformed Chinese character. Supports direct one-shot final image generation and layered production. Use when the user asks for a 中国省域文化海报、城市文化海报、地域文化视觉、极简大字海报、地区系列海报、展览主视觉、出版或社交封面，requests 直接生成、一次成图、不合成、不要后期、direct generation, or wants cultural analysis, art direction, image prompts, rendered poster images, or a coherent batch series for places such as 北京、广东、福建、江南、岭南、巴蜀 or 关中.

The English summary is being prepared. Showing the original description.

Build and navigate DSP (Data Structure Protocol) — graph-based long-term structural memory of codebases for LLM agents. Stores entities (modules, functions), their dependencies (imports), public API (shared/exports), and reasons for every connection. Use when: (1) project has a .dsp/ directory, (2) user asks to set up DSP or bootstrap project structure, (3) creating/modifying/deleting code files in a DSP-tracked project, (4) navigating project structure, understanding dependencies, or finding modules, (5) user mentions DSP, dsp-cli, .dsp, or structure mapping.

The English summary is being prepared. Showing the original description.

Use this skill when reviewing, designing, or improving a workshop, lesson, training session, facilitation plan, talk, or educational explanation. Use it when the user provides a topic, concept, or explanation and wants better framing questions, curiosity hooks, opening prompts, discussion questions, learner reflection prompts, or ways to make participants think before being taught.

The English summary is being prepared. Showing the original description.

When an application needs to store config, data, cache, or state files. When designing where user-specific files should live. When code writes to ~/.appname or hardcoded home paths. When implementing cross-platform file storage with platformdirs.

The English summary is being prepared. Showing the original description.

Use when the primary outcome is refining an existing AI-facing artifact without dropping behavior, including SKILL.md, AGENTS.md, CLAUDE.md, rules, prompts, and agent definitions that need sharper invocation, structure, or completion criteria.

The English summary is being prepared. Showing the original description.

Summarize files or a requested directory scope from actual contents. Extract code, config, data and document evidence, preserve exact counts and source locations, and disclose incomplete or unsupported acquisition. Use for file summaries, code explanations and configuration overviews.

The English summary is being prepared. Showing the original description.

Specialist skill for Python data engineering — pandas, polars, DuckDB, numpy, ETL pipelines, tabular data ingestion, and notebook-to-module extraction. Use when working with dataframes, data validation at ingress boundaries, merge/join operations, typed column contracts, or choosing between pandas vs polars vs DuckDB for a data task.

The English summary is being prepared. Showing the original description.

Scan Claude Code session transcripts to find the strongest user reactions to assistant instruction-following failures, reconstruct the triggering assistant output, and render a shareable terminal-style PNG artifact. Use when you want to surface and share a moment where the assistant completely missed what was asked — captures what they were doing, what Claude said, and how the user reacted. Triggers on: "rtfp", "read the fucking prompt", "find my worst AI moment", "make a rage screenshot from this session".

The English summary is being prepared. Showing the original description.

Optimize CLAUDE.md files and Skills for Claude Code CLI. Use when reviewing, creating, or improving system prompts, CLAUDE.md configurations, or Skill files. Transforms negative instructions into positive patterns following Anthropic's official best practices.

The English summary is being prepared. Showing the original description.

Claude Code session log schema — JSONL record types, message structure, tool call/result pairing, subagent file locations, team session layout, task/plan/team configuration paths. Use when parsing ~/.claude/projects/**/*.jsonl files, writing PostToolUse hooks that measure response sizes, building session analyzers, or any agent that reads or queries Claude session transcripts.

The English summary is being prepared. Showing the original description.

Hook recipes and working examples — plugin hooks, frontmatter hooks in skills/agents/commands, prompt-based LLM hooks, and complete code examples in Python and Node.js. Use when building hook scripts, integrating hooks into plugins, implementing prompt-based hooks, or looking for hook configuration patterns.

The English summary is being prepared. Showing the original description.

When calling LLM APIs from Python code. When connecting to llamafile or local LLM servers. When switching between OpenAI/Anthropic/local providers. When implementing retry/fallback logic for LLM calls. When code imports litellm or uses completion() patterns.

The English summary is being prepared. Showing the original description.

Validate whether an implementation plan can achieve its stated outcome before execution. Use to check requirement coverage, task contracts, dependencies, data/artifact flow, testability, ownership, impact coverage, and executable ordering without checking whether implementation already exists.

The English summary is being prepared. Showing the original description.

Use when starting, stopping, or checking the dot-dash live session dashboard — a real-time browser UI that monitors all active Claude Code sessions, streams transcripts, and supports prompt injection

The English summary is being prepared. Showing the original description.

Verify that changed components are actually connected into the intended end-to-end system flow. Use when checking imports/exports, registrations, data/control flow, configuration consumption, call paths, and boundary compatibility after implementation.

The English summary is being prepared. Showing the original description.

Reviews LLM integration, prompt templates, model selection, token/cost budgets, evaluation harnesses, structured outputs, retries, and streaming. Checks trust boundaries and task evidence against the selected provider/model contract rather than prescribing universal model tiers or sampling settings.

The English summary is being prepared. Showing the original description.

Orchestrate parallel agent dispatch as a manager — not a micromanager. Use when coordinating 2+ independent workers, running SAM task waves, relaying discoveries between worker waves, handling blockers, or synthesizing results. Covers both SAM structured dispatch (the task does the work) and ad-hoc dispatch (reference agent-orchestration for prompt template).

The English summary is being prepared. Showing the original description.