Loading...
Loading...
Found 2,126 Skills
Eva Think 2.2.8 Independent Thinking Coaching and Diagnosis Entry. It is used for chatting along, sorting out ideas, untangling confusion, clarifying concepts, positioning content issues, calibrating target audiences as needed during thinking or creative translation, disassembling benchmark samples, checking generic AI tone in text, conducting lightweight inspiration brainstorming, as well as saving, retrieving tasks, inventorying or backing up Eva data, extracting writing styles, collecting persona materials, and diagnosing expression eligibility; it shall not take over explicit code, finance, file processing or other professional execution tasks. Triggers: /eva-think, /eva-reframe, /eva-benchmark-copy, /eva-memory, /eva-persona-memory, /eva-user-voice, /eva-ai-check, help me think, chat with me, my mind is messy, help me look at this topic, benchmark disassembly, AI tone detection, save this idea, retrieve idea cards, inventory Eva memory bank, count memory cards/idea cards/persona cards/writing style cards, export Eva data, back up all Eva memory cards, package Eva data to desktop, extract the tone of my Moments, persona is not convincing. Only when explicitly calling /eva, /eva-persona-memory, nominating Eva persona material collection or using the compatible phrase "persona collection", or currently in Eva's persona material context, shall it handle the disambiguation and boundary of tasks like "build persona, create persona, build IP, account positioning, track positioning"; generalized account strategy tasks outside this context shall not be taken over by this Skill. Ordinary file compression, ordinary project backup and non-Eva data export shall not be taken over by this Skill. When users clearly require discipline-based brainstorming at the general entry, it shall be handled by Eva Lens; when already in a Think conversation, it can read the shared discipline-based brainstorming source as needed, and return to Think after completion. When users explicitly nominate the topic audience identifier or directly ask "who is the target audience, who does it resonate with, who is it for", it shall be handled by the eva-audience-finder primary entry.
Check if the CLI functions newly merged into te-cli are reasonable. Scan from six dimensions: command registration, business domain ↔ skill pairing, skill document coverage, skill internal consistency, user document synchronization, and engineering robustness, to locate issues such as command loading failure, AI agent guessing parameters due to empty documents, and outdated user documents. Use it when merging new command domains/commands, adding or modifying skills, performing pre-release self-checks, or evaluating the completeness of CLI functions.
Train a computer-vision model with the getitune library (the Geti training library) using its Python API or CLI. Use when a user wants to train, fine-tune, or evaluate a model with `create_engine(...)` and `engine.train()/engine.test()`, run `getitune train`/`getitune test`, pick or override a recipe under `getitune.recipe.<task>`, choose a device (cpu/gpu/xpu/cuda), warm-start from a checkpoint, or debug a training run. Covers classification, detection, instance/semantic segmentation, and keypoint detection.
Refactor Scikit-learn and machine learning code to improve maintainability, reproducibility, and adherence to best practices. This skill transforms working ML code into production-ready pipelines that prevent data leakage and ensure reproducible results. It addresses preprocessing outside pipelines, missing random_state parameters, improper cross-validation, and custom transformers not following sklearn API conventions. Implements proper Pipeline and ColumnTransformer patterns, systematic hyperparameter tuning, and appropriate evaluation metrics.
Individual project health assessment skill for evaluating project status across multiple dimensions. Provides early warning of troubled projects.
Run agentlint CLI after code changes to catch patterns for AI evaluation. Activate when finishing code modifications, before committing, or when the developer asks to lint, scan, or review code with agentlint. Covers agentlint check, agentlint list, agentlint review, agentlint init, inline suppression, and output interpretation.
Enforce modern Chinese writing standards including tone, spacing rules (Pangu), full-width punctuation, paragraph structure, and active voice. Provides specific guidelines for blog posts, error messages, UI text, and technical documentation.
Create professional presentations using the Pyramid Principle methodology. Supports PPTX generation, Marp/Reveal.js Markdown slides, chart creation, speaker notes, and self-evaluation rubrics. Minimal intake form to rapid output workflow.
Goal-driven E2E testing where a browser agent (Playwright MCP / computer-use) reads a natural-language goal and explores the app via the accessibility tree to assert outcomes — no pre-written script. Covers when intent-driven beats scripted, making agent runs deterministic (pinned model, temperature 0, seeded data, bounded steps, explicit success assertion, snapshot-not-pixel), cost/latency control, the accessibility-tree-first interaction model, CI gating, and graduating a stable run into a scripted Playwright test. Use when: "agentic browser test," "goal-driven browser test," "let an agent explore the app," "natural-language E2E," "browser agent smoke test," "Playwright MCP test." Not for: Writing/maintaining deterministic scripted Playwright tests — that is playwright-automation. Testing your product's OWN LLM features — that is ai-system-testing. Related: playwright-automation, ai-system-testing, exploratory-testing, test-reliability, qa-project-context.
Iteratively refine code via requested rounds of parallel subagent review and orchestrator-applied fixes, with bounded adaptive continuation enabled by default for productive runs. Use when the user says "let's do three rounds", "fix/review loop", "back-and-forth review", "iterative review", or asks to harden a change with multiple rounds of codex/claude review.
Use when designing or improving HOW users move through the product - task analysis, user flows (screens, branches, error paths), screen states, low-fi wireframes, Figma mockups, heuristic UX evaluation and redesign proposals. Maintains docs/ux/flows.md between foundation (stories) and scenarios. Triggers - "user flow" / "юзер флоу", "screen flow" / "флоу экранов", "user path" / "поток пользователя", "improve UX" / "улучши UX", "fix UX" / "почини UX", "wireframe" / "вайрфрейм", "figma" / "фигма", "design a screen" / "нарисуй дизайн", "mockup" / "мокап", "task analysis", "redesign flow".
When the user needs to evaluate competitors, understand the competitive landscape, or position their product against alternatives.