发现 Skills

Explore the codebase interactively, then create a task for implementation.

Send /new to a provider's pane to start a new session without context injection.

Test connectivity with AI provider (gemini/codex/opencode/droid/claude).

Generates and optimizes resumes for Applicant Tracking Systems (ATS). Use when the user needs to create a professional resume, align their experience with a job description, or ensure for document compatibility with automated screening tools.

Formats Telegram alerts for detected deals. Decides what goes as instant push (top 5%) vs a 3×/day digest. Avoids spam.

Anti-detect browser automation CLI & Skills for AI agents. Use when the user needs to interact with websites with bot detection, CAPTCHAs, or anti-bot blocks, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task that requires bypassing fingerprint checks.

Guide for operating the bitdrift bd CLI and analyzing live bitdrift account data — workflows, charts, sessions, issues, keys, connectors, and app health investigations. Trigger when the user wants to run bd commands, inspect live platform data, debug an app with bitdrift, create or edit workflows, read charts or metrics, triage crashes, inspect session timelines, or automate bitdrift operations from the CLI.

Database integration patterns for Java services using jOOQ and Flyway. Covers code generation, read/write splitting, migration guidelines, and version compatibility. Use when setting up or maintaining PostgreSQL integration.

REST API standards for Java Spring services. Covers Bitso API guidelines, authentication integration, OpenAPI documentation, and RFC-37 service documentation. Use when creating or maintaining REST endpoints.

Scrape documentation websites into local markdown files for AI context. Takes a base URL and crawls the documentation, storing results in ./docs (or custom path). Uses crawl4ai with BFS deep crawling.

Use SweetLink to connect your AI agent to a real browser tab. Like Playwright, but works in your current tab. Enables authentication, screenshots, smoke tests, and DevTools telemetry without headless automation.

Use this when you need to convert Markdown to PDF with Python while preserving tables, code blocks, image paths, and basic CSS styles.

Replace with description of the skill and when Claude should use it.

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

Call HLA alleles from NGS data using OptiType, HLA-HD, or arcasHLA for immunogenomics applications. Use when determining HLA genotype for transplant matching, neoantigen prediction, or pharmacogenomic screening.

<!--

<!--

Send third-party WhatsApp messages or sync/search WhatsApp history via wacli, not normal active chats.

Write agentic prompts including system prompts, workflow prompts, delegation prompts, and meta prompts. Use when creating commands, automating workflows, making tasks reusable, or when the user says "write a prompt", "create a command", or "automate this".

Use this skill when asked to perform an interactive git rebase programmatically, absorb/fixup commits into other commits, squash commits together, reorder commits, or drop commits. Provides a portable approach that works on macOS and Linux without interactive user input.

Decompose a system into well-defined components using structured discovery techniques. Use this skill whenever the user is designing a new system from requirements, breaking down a monolith into modules, deciding how to organize code into packages/services, asking 'what components should this system have?', or struggling with component granularity — even if they don't use the word 'component.'

Audit any set of study habits, training programs, or course designs for ineffective learning practices and replace them with evidence-based alternatives. Use this skill when someone wants a study habits audit, suspects they are making learning mistakes, reports that their studying is not working, relies on rereading, highlighting, or cramming, wonders whether their training design actually produces learning, or asks "what am I doing wrong?" Also triggers on: complaints about ineffective studying, concerns about rereading, assumptions about learning styles, cramming before an exam, blocked practice schedules, highlighting as the primary review method, "I study for hours but nothing sticks," or any study strategy review. Works for individual learners, teachers, corporate trainers, instructional designers, and coaches. Detects five named anti-patterns — the rereading trap, the massed-practice delusion, the illusions-of-knowing cluster, the learning-styles myth, and the errorless-learning myth — and provides mechanism explanations, severity ratings, and direct routing to the corrective skill. Do NOT use this skill to build a study schedule (use retrieval-practice-study-system), to design a practice sequence (use desirable-difficulty-classifier), or to calibrate mastery confidence (use learning-calibration-audit) — this skill diagnoses the problem and routes to those solutions.

Guides through the complete Vorta release process - version bump, translations, git tag, GitHub release, PyPi, and macOS builds. Invoke with /release.

OKR brainstorming and validation using the Radical Focus framework. Generates outcome-focused objectives with measurable key results and counter-metrics. Use when setting quarterly OKRs, validating existing OKRs against quality criteria, aligning team goals to company objectives, or teaching teams the difference between outputs and outcomes in goal-setting.