一键导入
skills
skills 收录了来自 vagkaratzas 的 5 个 skills,并提供仓库级职业覆盖和站内 skill 详情页。
这个仓库中的 skills
How to create or update local Nextflow modules for any pipeline. Use this skill whenever the user asks to create, write, scaffold, add, or update local Nextflow modules — even if they just say "add a module for X" or "write a module that does Y". Local modules live at modules/local/<name>/ and resemble nf-core modules but with relaxed conventions: no nf-core lint required (only nextflow lint), local test fixtures instead of a separate test-datasets repo, nf-test process tests by default, and the modern topic-channel version output instead of versions.yml.
Use this skill only when the user explicitly asks to redesign code, such as "redesign this code", "redesign this module", or invokes $redesign. Do not trigger for ordinary code review, refactoring, cleanup, naming, documentation, or comment-writing requests unless the user specifically asks for a redesign.
Pick the most token-efficient tool for a coding task instead of reflexively reading whole files, dumping raw command output into context, or writing more code than asked. Use this skill BEFORE you explore or explain a codebase, locate a symbol/definition/callers, trace a call path, map an architecture, plan or implement a feature across layers, or run verbose commands (tests, builds, git, grep, directory listings) — and whenever context/token budget, cost, or "make this use fewer tokens" comes up. It routes the scenario to serena, rtk, caveman, Ponytail, or plain tools, with concrete commands and the combinations to use vs. avoid. Reach for it even when the user doesn't name a tool: if you're about to `cat`/Read several files, or about to generate a big implementation, that's the trigger.
Python dependency security auditor using uv. Use this skill whenever asked to audit dependencies, check for security vulnerabilities or CVEs, update packages, fix outdated dependencies, run pip-audit, or keep a Python project's pyproject.toml current and safe. Trigger proactively when the user mentions dependency hygiene, wants to harden their Python project, or asks anything about package versions, security issues, or dependency updates — even if they don't use the word "audit".
Use this skill whenever asked to write, add, update, or review comments in code. Also trigger when the user mentions "self-documenting code" or claims "good code doesn't need comments." Use when documenting a function, module, or API, or when asked to improve comment quality in a codebase.