Showing 14461–14490 of 43470 skills
R machine learning with tidymodels: recipes (preprocessing), parsnip (model specs), workflows (fit pipelines), tune (hyperparameters), rsample (resampling). Engines: ranger (RF), glmnet (lasso/ridge), xgboost, kknn. Model interpretation (permutation importance, PDP/ICE, SHAP via DALEX/iml/kernelshap) and fairness assessment (fairmodels). UMAP via uwot. Use when execution language is R. Python equivalent: scikit-learn. For econometric regression use fixest or r-stats.
DAAF-Contribution-Community/daaf
R data manipulation with dplyr, tidyr, readr, purrr, stringr, forcats, lubridate. Verb pipelines, reshaping, joins, string/date ops, parquet via arrow. Includes data.table for performance. Use when execution language is R. Python equivalent: polars.
DAAF-Contribution-Community/daaf
Typesafe AI's Jev / System One typed-judgment API, called over raw HTTP from DAAF scripts. Jev generates no text: it takes a `state` plus a map of typed `questions` and returns vendor-calibrated probabilities — choice (pick one option, with a distribution and confidence), score (position on 2-10 ordered levels, likewise), and noul (probability a yes/no statement is true); an experimental box type locates something in an image. Load when a task mentions Typesafe, TypeSafe AI, Jev, System One, `api.typesafe.ai`, or `TYPESAFE_API_KEY`, or wants probability-typed judgments over text or images — classify, rank, verify, or locate, into values code can threshold on. This is an external third-party inference API reached with `requests`, not a DAAF data source or dataset; for research data acquisition use the education/election data-source skills. Not for generating prose, code, or explanations. Not for OCR, transcription, or local image processing (scanned PDFs: pdf-reading).
DAAF-Contribution-Community/daaf
DAAF's protocol for retrieving web documents that an agent needs to READ (docs pages, articles, API references, issue threads). Retrieval runs through the framework CLI `bash /daaf/scripts/web_fetch.sh URL DEST_DIR`, which saves the raw response, a deterministic extract, and a provenance manifest to disk — the built-in WebFetch is blocked because it returns an AI paraphrase, not source text. Covers when to fetch at all (check local skills first), tool syntax and flags, the two-artifact + MANIFEST provenance model, the exit-code failure table, the untrusted-content rule, thin-extract diagnosis, extract size rules, and destination conventions. Use when a permitted context (search-agent, data-ingest, debugger, literature-searcher, orchestrator) must pull a specific web page into context to read or quote it. NOT for discovery — WebSearch stays built-in for finding URLs. NOT for pipeline data acquisition — Stage 5 / onboarding scripts fetching datasets into parquet are a separate activity for any pipeline agent.
DAAF-Contribution-Community/daaf
Format a Markdown file to match Liferay conventions — frontmatter order, Title Case headings, braced shell variables, long-form CLI flags, and professional prose. Use when the user asks to format, clean up, polish, or copy-edit a Markdown file destined for the Liferay repository.
liferay/liferay-portal
视频脚本口语化审校,去书面腔让脚本适合说出来。当用户提到"口语化"、"太书面了"、"像说话一样"、"脚本审校"时使用。
alchaincyf/huashu-skills
快速生成3-4个选题方向,含标题、大纲和优劣分析。当用户提到"选题"、"写什么"、"文章方向"、"题目建议"时使用。
alchaincyf/huashu-skills
艺术与视频动画:拆解复刻动画;36种既有实做风格+16种可迁移研究配方;9种解说动画语法,8种可按口播参数渲片段;含口播整片参考代码及框景检查;人用AI生帧;可选已有录音、系统声音与语音复刻,按需配置。
alchaincyf/huashu-art-motion
Character rigging in Blender 5.3 - Rigify metarig fit/generate, bone naming/roll/collections, DEF/MCH/control layers, IK/FK, robust skinning (heat + proxy fallback), weight-painting rules, correctives, engine game skeletons (Unity, Unreal, Roblox R15), rig validation and deformation stress tests. Use for armature, skinning or weights tasks.
EL4CTEO/blender-skills
Evaluate, fix, and answer GitHub PR comments, and fix what failing checks report. Use when the user asks to "resolve PR feedback", "resolve PR comments", "answer review questions", or "fix PR checks".
tobihagemann/turbo
Evaluate, fix, and answer GitHub PR comments, and fix what failing checks report. Use when the user asks to "resolve PR feedback", "resolve PR comments", "answer review questions", or "fix PR checks".
tobihagemann/turbo
Follow a PR to merge: wait for AI reviewers and checks, resolve their feedback, then offer to merge and clean up. Use when the user asks to "land the PR", "follow up on the PR", or "merge when ready".
tobihagemann/turbo
Follow a PR to merge: wait for AI reviewers and checks, resolve their feedback, then offer to merge and clean up. Use when the user asks to "land the PR", "follow up on the PR", or "merge when ready".
tobihagemann/turbo
Shared base for reviewing a diff, a branch or a PR in this plugin. How to read the diff, which repo guidelines to load for the changed paths, and the shape of a finding. Used by the code-review and security-audit agents.
Automattic/wordpress-activitypub
Create a GitHub issue with a drafted title and body. Use when the user asks to "create an issue", "file an issue", "open an issue", "report a bug", or "file a feature request".
tobihagemann/turbo
Review code for bugs, security, API misuse, consistency, simplicity, or test coverage, with peer review in parallel. Use when the user asks to "review my code", "check for bugs", or "security audit".
tobihagemann/turbo
Commit, push, and optionally create or update a PR for the current staged changes. Use when the user asks to "ship", "ship it", "ship changes", "commit push and PR", or "ship this".
tobihagemann/turbo
Create a GitHub issue with a drafted title and body. Use when the user asks to "create an issue", "file an issue", "open an issue", "report a bug", or "file a feature request".
tobihagemann/turbo
Validate .turbo/backlog.md entries, recommend a working set, and run one lane: direct, investigate, or plan. Use when the user asks to "implement the backlog" or "implement improvements".
tobihagemann/turbo
Review code for bugs, security, API misuse, consistency, simplicity, or test coverage, with peer review in parallel. Use when the user asks to "review my code", "check for bugs", or "security audit".
tobihagemann/turbo
Commit, push, and optionally create or update a PR for the current staged changes. Use when the user asks to "ship", "ship it", "ship changes", "commit push and PR", or "ship this".
tobihagemann/turbo
对用户的计划、决策或想法进行层层盘问。当用户想要压力测试自己的思考,或使用任何 'grill' 触发短语时使用。
AUTO-MAS-Project/AUTO-MAS
Assess project-wide technical debt (hotspots, deprecated APIs, duplication, low-value tests) into a ranked report. Use when the user asks to "assess technical debt" or "what should we refactor".
tobihagemann/turbo
Capture an out-of-scope improvement or accepted simplification in .turbo/backlog.md. Use proactively mid-task, or when the user asks to "backlog this", "note this idea", or "track this for later".
tobihagemann/turbo
Shared changelog conventions and formatting rules. Not typically invoked directly.
tobihagemann/turbo
Run autonomous task execution using the codex CLI. Use when the user asks to "codex exec", "run codex exec", "execute a task with codex", or "delegate to codex".
tobihagemann/turbo
Multi-turn consultation with Codex CLI for second opinions or brainstorming. Use when the user asks to "consult codex", "ask codex", "get codex's opinion", or "brainstorm with codex".
tobihagemann/turbo
Consult ChatGPT Pro through browser automation on a problem standard approaches failed to crack. Use when stuck, or when the user asks to "ask the oracle" or "consult chatgpt".
tobihagemann/turbo
Propose a turbo skill improvement as a GitHub issue on the turbo repo. Use when the user asks to "contribute to turbo", "contribute back", or "upstream my changes".
tobihagemann/turbo
Generate a four-level test plan at .turbo/test-plans/[slug].md from what changed. Use when the user asks to "create a test plan", "what should I test", "list test cases", or "test plan for this PR".
tobihagemann/turbo